Skip to content
Back to search

daymade-skills

MarketplaceWorks with Claude CodeGitHubIncomplete

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/daymade/claude-code-skills with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/daymade/claude-code-skills'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/daymade-claude-code-skills/badge.svg)](/listings/daymade-claude-code-skills)

HTML

<a href="/listings/daymade-claude-code-skills"><img src="/api/listings/daymade-claude-code-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**In Claude Code (in-app):**

/plugin marketplace add daymade/claude-code-skills

Then: 1. Select **Browse and install plugins** 2. Select **daymade/claude-code-skills** 3. Select **daymade-skill** (includes skill-creator) 4. Select **Install now**

**From your terminal (CLI):**

claude plugin marketplace add https://github.com/daymade/claude-code-skills
# Marketplace name: daymade-skills (from marketplace.json)
claude plugin install daymade-skill@daymade-skills

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 1,389 lines
  1. {
  2. "name": "daymade-skills",
  3. "owner": {
  4. "name": "daymade",
  5. "email": "daymadev89@gmail.com"
  6. },
  7. "metadata": {
  8. "description": "Professional Claude Code and Codex skills marketplace — production-ready skills spanning GitHub and git operations (including current-base contributor PR review), document conversion and generation (Markdown, PDF, PPTX, DOCX), diagram and UI-design extraction, the full audio pipeline (ASR transcription, TTS, transcript correction, meeting minutes), financial and investment-research data, web scraping and content capture, security/PII tooling and secure repomix packaging, macOS and iOS development, CLI demo and terminal automation, evidence-backed HTML reports and data-visualization judgment, prompt and skill engineering, product growth diagnosis, deep research and fact-checking, QA and LLM-evaluation infrastructure, internationalization, network/Tailscale and remote-desktop diagnostics, local inter-agent messaging, Claude Code operations, technology selection and build-vs-buy decisions, and model-aware Codex workstation setup. Suite plugins bundle related skills under shared namespaces, including the StepFun StepAudio 2.5 audio family. See the Available Skills list in the README for the authoritative per-skill breakdown.",
  9. "version": "3.27.0"
  10. },
  11. "plugins": [
  12. {
  13. "name": "lark-cli-router",
  14. "description": "Routes Feishu/Lark/Doubao operations through the version-matched guides embedded in lark-cli. Use for documents, wiki, sheets, Base, minutes, meetings, calendar, messaging, mail, tasks, approval, authentication, permissions and lark-cli troubleshooting.",
  15. "source": "./lark-cli-router",
  16. "strict": false,
  17. "version": "1.0.4",
  18. "category": "productivity",
  19. "keywords": [
  20. "feishu",
  21. "lark",
  22. "doubao",
  23. "lark-cli",
  24. "documents",
  25. "collaboration"
  26. ]
  27. },
  28. {
  29. "name": "cookie-copy",
  30. "description": "Copies selected-site cookies between local profiles of the same macOS Chrome. Use for cookie copy, 复制 Cookie, 搬登录态 or reusing an existing ChatGPT session in an isolated profile. Supports Google and ChatGPT/OpenAI site selections, destination backups and restore, and expected-account verification for ChatGPT.",
  31. "source": "./cookie-copy",
  32. "strict": false,
  33. "version": "1.0.0",
  34. "category": "utilities",
  35. "keywords": ["cookies", "chrome", "session-migration", "login", "backup", "restore"]
  36. },
  37. {
  38. "name": "floorplan-finder",
  39. "description": "Finds existing residential floor plans online and checks layout, entrance orientation, and source identity. Use for 找户型图、按楼栋房号找原图、核对同款或镜像户型. Not for designing, generating, or certifying architectural drawings.",
  40. "source": "./floorplan-finder",
  41. "strict": false,
  42. "version": "1.0.0",
  43. "category": "utilities",
  44. "keywords": ["floor-plan", "property-search", "layout-verification", "户型图", "房源"]
  45. },
  46. {
  47. "name": "app-evolver",
  48. "description": "Improves an existing application using its code, product contract, authorized work history and competitor evidence. Use for 取长补短、取其精华去其糟粕、参考竞品优化应用 or evolving an app from successful and failed work. Carries authorized changes through implementation and user-result verification, including REA and reverse Skill composition; use skill-evolver for Skills.",
  49. "source": "./app-evolver",
  50. "strict": false,
  51. "version": "1.1.16",
  52. "category": "developer-tools",
  53. "keywords": [
  54. "app-improvement",
  55. "competitor-analysis",
  56. "work-history",
  57. "product-contract",
  58. "取长补短",
  59. "应用优化"
  60. ]
  61. },
  62. {
  63. "name": "skill-evolver",
  64. "description": "Researches and improves a specified existing Skill using successful/failed work and competitor evidence. Use for 优化这个Skill, 从成功和失败经验改进Skill, or 研究竞品后优化指定技能. Routine creation and editing use skill-creator.",
  65. "source": "./skill-evolver",
  66. "strict": false,
  67. "version": "1.0.4",
  68. "category": "developer-tools",
  69. "keywords": [
  70. "skill-improvement",
  71. "research",
  72. "work-history",
  73. "competitor-analysis",
  74. "optimization",
  75. "技能优化"
  76. ]
  77. },
  78. {
  79. "name": "bilibili-source",
  80. "description": "Fetches real, citable Bilibili (B站) video data — stats, metadata, tags, and full danmaku text — via login-free API calls, never hand-typed or estimated. Use when citing view/like/favorite counts, analyzing why a video performed, or archiving a Bilibili source into a knowledge base. Accepts BVID, av numbers, b23.tv links, or full URLs; subtitles and 收藏夹 (favorites) enumeration need the user's Bilibili login.",
  81. "source": "./bilibili-source",
  82. "strict": false,
  83. "version": "1.4.2",
  84. "category": "developer-tools",
  85. "keywords": [
  86. "bilibili",
  87. "b站",
  88. "bilibili-api",
  89. "video-stats",
  90. "danmaku",
  91. "view-count",
  92. "content-analysis",
  93. "web-data",
  94. "claude-code"
  95. ]
  96. },
  97. {
  98. "name": "kimi-use",
  99. "source": "./kimi-use",
  100. "strict": false,
  101. "version": "1.8.6",
  102. "category": "developer-tools",
  103. "keywords": [
  104. "kimi",
  105. "kimi-app",
  106. "computer-use",
  107. "天眼查",
  108. "同花顺",
  109. "ifind",
  110. "data-source",
  111. "financial-data",
  112. "gui-automation"
  113. ]
  114. },
  115. {
  116. "name": "peer-message",
  117. "description": "Bridge local Claude Code and Codex sessions only when the current host's native communication tools do not cover the target. Use for cross-product messages, hooks/scripts posting to sessions, fallback reply lookup and delivery verification, or diagnosing Held peer messages. Also use its coordination guidance when shared-work ownership or an inbound peer assertion needs verification. For ordinary parent/subagent, teammate, or independent-session communication, first discover and use available native tools; do not load this skill merely to send a native message. The bundled network preview for cross-machine pairing is deprecated (existing deployments only; invitations use the peer-message:v1 format). Never bypass a denied or Held message with another transport. Not for spawning agents, moving full history, or granting user approval. Triggers: 跨产品通信、原生工具未覆盖的会话、脚本回帖、peer 送达排查、共享在制品归属核实、peer-message:v1 邀请(既有部署)。",
  118. "source": "./peer-message",
  119. "strict": false,
  120. "version": "1.27.4",
  121. "category": "communication",
  122. "keywords": [
  123. "agent-communication",
  124. "cross-session",
  125. "peer-message",
  126. "claude-code",
  127. "codex",
  128. "codex-queue",
  129. "uds",
  130. "multi-agent",
  131. "broadcast",
  132. "session-coordination",
  133. "crossSessionInbound",
  134. "inbound-assertions"
  135. ]
  136. },
  137. {
  138. "name": "cli-demo-generator",
  139. "description": "Generate professional animated CLI demos and terminal recordings with VHS. Supports automated generation, batch processing, and interactive recording for documentation and tutorials",
  140. "source": "./cli-demo-generator",
  141. "strict": false,
  142. "version": "1.1.0",
  143. "category": "developer-tools",
  144. "keywords": [
  145. "cli",
  146. "demo",
  147. "terminal",
  148. "vhs",
  149. "gif",
  150. "recording",
  151. "animation",
  152. "documentation"
  153. ]
  154. },
  155. {
  156. "name": "cloudflare-troubleshooting",
  157. "description": "Investigate and resolve Cloudflare configuration issues using API-driven evidence gathering. Use when troubleshooting ERR_TOO_MANY_REDIRECTS, SSL errors, DNS issues, or any Cloudflare-related problems. Focus on systematic investigation using Cloudflare API to examine actual configuration rather than making assumptions.",
  158. "source": "./cloudflare-troubleshooting",
  159. "strict": false,
  160. "version": "1.1.2",
  161. "category": "developer-tools",
  162. "keywords": [
  163. "cloudflare",
  164. "troubleshooting",
  165. "ssl",
  166. "dns",
  167. "api",
  168. "debugging",
  169. "devops"
  170. ]
  171. },
  172. {
  173. "name": "competitors-analysis",
  174. "description": "Discover, clone, update, and analyze competitor repositories with evidence-based competitive intelligence. Use when tracking competitors, reviewing competitor source code, adding a competitor repository, comparing product capabilities, building a competitor landscape, checking latest competitor code, or when the user says 竞品分析, competitor scan, analyze competitor, or compare with X. Repository-backed findings must come from local cloned code with file:line citations; market-landscape claims must cite their source and volatility.",
  175. "source": "./competitors-analysis",
  176. "strict": false,
  177. "version": "1.6.7",
  178. "category": "productivity",
  179. "keywords": [
  180. "competitors",
  181. "competitive-analysis",
  182. "competitor-tracking",
  183. "evidence-based",
  184. "market-research",
  185. "竞品分析",
  186. "code-analysis"
  187. ]
  188. },
  189. {
  190. "name": "daymade-claude-code",
  191. "description": "Claude Code operations suite that bundles cross-project prior-work retrieval across code, docs, Skills, meetings, WeChat archives, and conversation history; provider-separated Claude Code and Codex history readers; identity- and lineage-gated continuation workflows; plugin/skill troubleshooting; CLAUDE.md progressive disclosure optimization; statusline configuration; exported .txt repair; full claude.ai conversation extraction with tool-call rendering and file download; plugin marketplace development and suite consolidation; writing/testing/debugging Claude Code hooks; multi-provider profile isolation; personal-memory migration into tool-agnostic AGENTS.md reference docs; one-shot local timers that ping Claude right after subscription quota reset to start a fresh 5-hour usage window; working web search installed on an agent whose relayed model backend cannot execute the built-in one; and terminal-output-to-PNG rendering for visual CLI verification under one shared namespace. Install once to get the full Claude Code power-user toolkit.",
  192. "source": "./daymade-claude-code",
  193. "strict": false,
  194. "version": "5.2.9",
  195. "category": "suite",
  196. "keywords": [
  197. "suite",
  198. "claude-code",
  199. "session-recovery",
  200. "conversation-history",
  201. "local-history",
  202. "prior-work",
  203. "retrieval",
  204. "reuse",
  205. "claude-md",
  206. "statusline",
  207. "troubleshooting",
  208. "marketplace-dev",
  209. "local-source-sync",
  210. "codex",
  211. "terminal-screenshot",
  212. "usage-analyst",
  213. "quota-ping",
  214. "web-conversation-export",
  215. "conversation-file-download",
  216. "memory-migration"
  217. ],
  218. "skills": [
  219. "./claude-code-ops-router",
  220. "./local-conversation-history",
  221. "./read-claude-code-history",
  222. "./read-codex-history",
  223. "./continue-claude-code-work",
  224. "./continue-codex-work",
  225. "./claude-skills-troubleshooting",
  226. "./claude-md-progressive-disclosurer",
  227. "./statusline-generator",
  228. "./claude-export-txt-better",
  229. "./marketplace-dev",
  230. "./terminal-screenshot",
  231. "./claude-usage-analyst",
  232. "./claude-switch-models-setup",
  233. "./read-claude-web-conversation",
  234. "./claude-migrate-memory-to-doc",
  235. "./claude-code-hooks",
  236. "./prior-work-retrieval",
  237. "./claude-code-ping-start-5h-quota",
  238. "./agent-web-search-setup",
  239. "./tech-selection"
  240. ]
  241. },
  242. {
  243. "name": "daymade-codex",
  244. "description": "OpenAI Codex operations and design exploration suite bundling model-aware long-context workstation setup, local Codex delegation, generated-image review, static visual-direction selection, and runnable HTML interaction Design Boards under one shared namespace.",
  245. "source": "./daymade-codex",
  246. "strict": false,
  247. "version": "2.4.16",
  248. "category": "suite",
  249. "keywords": [
  250. "suite",
  251. "codex",
  252. "openai",
  253. "context-window",
  254. "codex-desktop",
  255. "workstation-setup",
  256. "code-review",
  257. "image-gallery",
  258. "design",
  259. "visual-direction",
  260. "interaction-design",
  261. "html-prototype",
  262. "design-board"
  263. ],
  264. "skills": [
  265. "./codex-image-gallery",
  266. "./local-codex",
  267. "./design-style-picker",
  268. "./interaction-design-board",
  269. "./codex-1m-context-window-setup"
  270. ]
  271. },
  272. {
  273. "name": "daymade-docs",
  274. "description": "Word/PDF/PPTX/HTML→MD;MD/Word→PDF;new Word;PDF HTML/translate;Excel/xlsm/Mac;photo/signed scan;Mermaid;DOCX review;doc cleanup Reads one bundled Daymade specialist. New slide decks use deck-creator when installed; generic PDF reading/editing and spreadsheet analysis stay with their own Skills. Retired ppt-creator stays manual-only.",
  275. "source": "./daymade-docs",
  276. "strict": false,
  277. "version": "1.29.7",
  278. "category": "suite",
  279. "keywords": [
  280. "suite",
  281. "documentation",
  282. "markdown",
  283. "mermaid",
  284. "pdf",
  285. "pptx",
  286. "docx",
  287. "word",
  288. "excel",
  289. "xlsx",
  290. "xlsm",
  291. "meeting-minutes",
  292. "scan",
  293. "photo-to-pdf",
  294. "comments",
  295. "track-changes",
  296. "review"
  297. ],
  298. "skills": [
  299. "./docs-router",
  300. "./doc-to-markdown",
  301. "./mermaid-tools",
  302. "./pdf-creator",
  303. "./ppt-creator",
  304. "./docx-creator",
  305. "./docs-cleaner",
  306. "./pdf-to-html",
  307. "./photo-to-scanned-pdf",
  308. "./excel-automation",
  309. "./read-docx-review"
  310. ]
  311. },
  312. {
  313. "name": "daymade-financial",
  314. "description": "Financial data and investment-research suite covering the full China A-share and global equity data pipeline: Bigdata.com (RavenPack) structured financials and news sentiment, US equity fundamentals via yfinance, Gangtise (岗底斯) OpenAPI research suite installation and orchestration, A-share news and policy aggregation, A-share pharmaceutical sector daily reporting, structured devil's-advocate pressure-testing of investment theses, and adversarial due diligence on inflated benchmark claims with replicability mapping. Install once for the complete financial research workflow.",
  315. "source": "./daymade-financial",
  316. "strict": false,
  317. "version": "1.5.2",
  318. "category": "suite",
  319. "keywords": [
  320. "suite",
  321. "financial-data",
  322. "investment-research",
  323. "a-share",
  324. "bigdata",
  325. "ravenpack",
  326. "gangtise",
  327. "pharma",
  328. "news",
  329. "yfinance",
  330. "devils-advocate",
  331. "thesis-pressure-test",
  332. "benchmark",
  333. "due-diligence"
  334. ],
  335. "skills": [
  336. "./financial-router",
  337. "./bigdata-skill",
  338. "./financial-data-collector",
  339. "./gangtise-copilot",
  340. "./ashare-news-fetcher",
  341. "./daymade-sector-research",
  342. "./pharma-daily-report",
  343. "./devils-advocate",
  344. "./benchmark-due-diligence"
  345. ]
  346. },
  347. {
  348. "name": "daymade-macos",
  349. "description": "Apple-platform development and operations suite for macOS window capture, TCC and Keychain dialog diagnosis, Full Disk Access repair, iOS/macOS app development, disk cleanup, and launchd watchdogs.",
  350. "source": "./daymade-macos",
  351. "strict": false,
  352. "version": "1.34.13",
  353. "category": "suite",
  354. "keywords": [
  355. "suite",
  356. "macos",
  357. "ios",
  358. "xcodegen",
  359. "swiftui",
  360. "screenshot",
  361. "disk-space",
  362. "launchd",
  363. "watchdog"
  364. ],
  365. "skills": [
  366. "./capture-screen",
  367. "./developing-ios-apps",
  368. "./macos-cleaner",
  369. "./macos-permissions",
  370. "./macos-watchdog",
  371. "./macos-load-doctor"
  372. ]
  373. },
  374. {
  375. "name": "daymade-audio",
  376. "description": "Audio processing suite covering the full speech pipeline: ASR transcription (Qwen3, StepFun) with batch-mode guards against music-only repetition-loop hallucinations, speaker diarization and CAM++ voiceprint identification for multi-speaker recordings, transcript error correction, structured meeting minutes generation, and TTS voice synthesis (StepFun). Install once for the complete audio workflow.",
  377. "source": "./daymade-audio",
  378. "strict": false,
  379. "version": "1.65.5",
  380. "category": "suite",
  381. "keywords": [
  382. "suite",
  383. "audio",
  384. "asr",
  385. "tts",
  386. "transcription",
  387. "speech-to-text",
  388. "text-to-speech",
  389. "meeting-minutes",
  390. "voice"
  391. ],
  392. "skills": [
  393. "./audio-router",
  394. "./asr-transcribe-to-text",
  395. "./stepfun-asr",
  396. "./transcript-fixer",
  397. "./meeting-minutes-taker",
  398. "./stepfun-tts"
  399. ]
  400. },
  401. {
  402. "name": "daymade-skill",
  403. "description": "Daymade skills core suite. Bundles skill creation, quality review, real Claude/Codex Skill-surface governance, suite-migration reconciliation, and marketplace development tooling under one shared namespace. Skill governance separates canonical source, installed inventory, discovery policy, the fresh model-visible catalog, and router-resolved cold resources instead of optimizing cache counts; it preserves Claude's official versioned-cache lifecycle and verifies selected entries in the real host prompt. Skill verification separates risk classification from evaluation spend: bounded fixes use targeted checks, narrow behavior changes use sampled replays, and paired baselines, graders, benchmarks, or a viewer run only after explicit user authorization or a decision-bearing evidence plan plus opt-in; that authorization does not change the risk tier. Existing-skill edits retain an old-vs-new capability audit and content-bound packaging attestation so prompt compression cannot silently delete runtime contracts. When the official skill-creator plugin is also installed, skill-creator detects the coexistence and offers a consent-based, reversible SessionStart routing hook so the daymade edition wins deterministically; on machines without the official plugin nothing is ever installed.",
  404. "source": "./daymade-skill",
  405. "strict": false,
  406. "version": "1.81.3",
  407. "category": "suite",
  408. "keywords": [
  409. "suite",
  410. "skill-creation",
  411. "skill-review",
  412. "skill-governance",
  413. "marketplace-dev",
  414. "development",
  415. "tooling"
  416. ],
  417. "skills": [
  418. "./skill-creator",
  419. "./skill-reviewer",
  420. "./skills-search",
  421. "./skill-governance"
  422. ]
  423. },
  424. {
  425. "name": "deep-research",
  426. "description": "Generate evidence-tracked research reports with reusable source and claim records, original-source verification, and evidence-family tracking. Coordinate provider-specific Skills across selected modes, retain original artifacts, and synthesize by decision; select depth and routes by the question.",
  427. "source": "./deep-research",
  428. "strict": false,
  429. "version": "2.14.0",
  430. "category": "documentation",
  431. "keywords": [
  432. "research",
  433. "report",
  434. "analysis",
  435. "literature-review",
  436. "market-research",
  437. "citations",
  438. "evidence",
  439. "deepresearch",
  440. "enterprise",
  441. "company-research",
  442. "due-diligence"
  443. ]
  444. },
  445. {
  446. "name": "douban-skill",
  447. "description": "Export and sync Douban (豆瓣) book/movie/music/game collections to local CSV files via Frodo API. Supports full export (all history) and RSS incremental sync (recent items). Use when the user wants to export Douban reading/watching/listening/gaming history, back up their Douban data, set up incremental sync, or mentions 豆瓣/douban collections. Triggers on: 豆瓣, douban, 读书记录, 观影记录, 书影音, 导出豆瓣, export, backup, sync, collection.",
  448. "source": "./douban-skill",
  449. "strict": false,
  450. "version": "1.1.0",
  451. "category": "productivity",
  452. "keywords": [
  453. "douban",
  454. "豆瓣",
  455. "csv",
  456. "export",
  457. "backup",
  458. "rss",
  459. "frodo"
  460. ]
  461. },
  462. {
  463. "name": "fact-checker",
  464. "description": "Verifies factual claims in documents using web search and official sources, then proposes corrections with user confirmation. Use when the user asks to fact-check, verify information, validate claims, check accuracy, or update outdated information in documents. Supports AI model specs, technical documentation, statistics, and general factual statements",
  465. "source": "./fact-checker",
  466. "strict": false,
  467. "version": "1.0.0",
  468. "category": "productivity",
  469. "keywords": [
  470. "fact-checking",
  471. "verification",
  472. "accuracy",
  473. "sources",
  474. "validation",
  475. "corrections",
  476. "web-search"
  477. ]
  478. },
  479. {
  480. "name": "feishu-doc-scraper",
  481. "description": "Extracts Feishu/Lark Docs, Wiki, Sheets, and Minutes (妙记) transcripts into faithful local Markdown via the lark-cli API — no LLM paraphrasing, browser-DOM fallback when lark-cli can't reach content. Use whenever the source is a Feishu/Lark URL and fidelity matters — 导出飞书文档/合集/妙记转写, 把飞书 wiki 转 markdown, or archiving a collection — even if the user just says \"save this\". Also covers owner-exported .docx → Markdown.",
  482. "source": "./feishu-doc-scraper",
  483. "strict": false,
  484. "version": "1.14.1",
  485. "category": "productivity",
  486. "keywords": [
  487. "feishu",
  488. "lark",
  489. "lark-cli",
  490. "markdown",
  491. "wiki",
  492. "minutes",
  493. "transcript",
  494. "collection",
  495. "api",
  496. "docx",
  497. "scraping",
  498. "browser",
  499. "archival",
  500. "comments",
  501. "replies",
  502. "feedback"
  503. ]
  504. },
  505. {
  506. "name": "github-contributor",
  507. "description": "Ships pull requests to open-source projects you don't maintain — CONTRIBUTING compliance, PR-size/scope checks, minimal-diff implementation, AI-disclosure PR descriptions, and rebase or bot-review replies. Use for 提 PR / 上游 PR / 贡献代码, \"open a PR\", \"fix this upstream\", \"rebase against main\", \"respond to the bot review\". Not for reviewing PRs as maintainer (use github-review-pr) or general GitHub CRUD (use github-ops).",
  508. "source": "./github-contributor",
  509. "strict": false,
  510. "version": "1.3.3",
  511. "category": "developer-tools",
  512. "keywords": [
  513. "github",
  514. "open-source",
  515. "contribution",
  516. "pull-request",
  517. "reputation",
  518. "contributor",
  519. "oss",
  520. "rebase",
  521. "conflict-resolution",
  522. "pr-description",
  523. "ai-assisted-disclosure",
  524. "bot-review"
  525. ]
  526. },
  527. {
  528. "name": "github-ops",
  529. "description": "Operates GitHub via gh CLI and REST/GraphQL — PRs, issues, Actions, self-hosted Runner inventory/capacity, repos, collaborators, org permissions, 2FA — with explicit target, authorization, and independent readback. Use when a write reports success but state didn't change, or choosing gh/REST/GraphQL/UI-only. Not for local Git recovery (use git-safety-net), maintainer PR review (use github-review-pr), or upstream contribution (use github-contributor).",
  530. "source": "./github-ops",
  531. "strict": false,
  532. "version": "1.17.2",
  533. "category": "developer-tools",
  534. "keywords": [
  535. "github",
  536. "gh-cli",
  537. "pull-request",
  538. "issues",
  539. "workflows",
  540. "organizations",
  541. "permissions",
  542. "2fa",
  543. "api"
  544. ]
  545. },
  546. {
  547. "name": "github-review-pr",
  548. "description": "Reviews PRs against the live base with immutable objects and three-way merges. Use for PR review/merge readiness, main changed, closed-PR reconsideration, open-PR sweeps, review-led repair, or explicitly requested independent review of your own contribution. Not for GitHub CRUD (use github-ops), authoring/maintaining your PR (use github-contributor), or merging without fresh review.",
  549. "source": "./github-review-pr",
  550. "strict": false,
  551. "version": "1.4.7",
  552. "category": "developer-tools",
  553. "keywords": [
  554. "github",
  555. "pull-request",
  556. "code-review",
  557. "maintainer",
  558. "base-drift",
  559. "merge-readiness",
  560. "three-way-merge",
  561. "contributor",
  562. "open-pr-sweep",
  563. "curation"
  564. ]
  565. },
  566. {
  567. "name": "git-safety-net",
  568. "description": "Audits, preserves and recovers local Git state before cleanup: unpushed or wrong-branch commits, dirty worktrees, duplicate clones, stashes, dangling commits, squash-merge uncertainty. Use when the user fears lost work, wants to recover a commit, asks if a branch is actually merged, asks whether a branch, worktree or clone is safe to delete, or wants one clean main (误删分支 / 还有没有丢的东西). Not for GitHub PR operations.",
  569. "source": "./git-safety-net",
  570. "strict": false,
  571. "version": "1.28.12",
  572. "category": "developer-tools",
  573. "keywords": [
  574. "git",
  575. "reflog",
  576. "dangling-commits",
  577. "lost-commits",
  578. "branch-recovery",
  579. "merge-verification",
  580. "squash-merge",
  581. "disaster-recovery",
  582. "worktree",
  583. "claude-code",
  584. "clone-discovery",
  585. "untracked-backup",
  586. "stale-remote-cache",
  587. "checkout-alignment"
  588. ]
  589. },
  590. {
  591. "name": "i18n-expert",
  592. "description": "Complete internationalization/localization setup and auditing for UI codebases. Configure i18n frameworks, replace hard-coded strings with translation keys, ensure locale parity between en-US and zh-CN, and validate pluralization and formatting. Use when setting up i18n for React/Next.js/Vue apps, auditing existing implementations, replacing hard-coded strings, ensuring proper error code mapping, or validating pluralization and date/time/number formatting across locales",
  593. "source": "./i18n-expert",
  594. "strict": false,
  595. "version": "1.0.0",
  596. "category": "developer-tools",
  597. "keywords": [
  598. "i18n",
  599. "internationalization",
  600. "localization",
  601. "translation",
  602. "react-i18next",
  603. "next-intl",
  604. "vue-i18n",
  605. "locale",
  606. "multilingual",
  607. "globalization"
  608. ]
  609. },
  610. {
  611. "name": "ima-copilot",
  612. "description": "One-stop companion and installer for the official Tencent IMA skill (ima.qq.com). Installs upstream ima-skill to Claude Code/Codex/OpenClaw via npx skills add, guides API key setup, detects and fixes known issues (including the missing-YAML-frontmatter bug in submodule SKILL.md files) with user consent, and implements a personalized fan-out search strategy with priority-based knowledge base boosting and silent truncation detection",
  613. "source": "./ima-copilot",
  614. "strict": false,
  615. "version": "1.2.2",
  616. "category": "developer-tools",
  617. "keywords": [
  618. "ima",
  619. "tencent-ima",
  620. "knowledge-base",
  621. "note-search",
  622. "fan-out-search",
  623. "installer",
  624. "wrapper",
  625. "upstream-fix",
  626. "claude-code",
  627. "codex",
  628. "openclaw"
  629. ]
  630. },
  631. {
  632. "name": "llm-eval-harness",
  633. "description": "Tests/benchmarks a third-party LLM endpoint (OpenAI- or Anthropic-compatible): availability, fidelity, speed, concurrency, protocol compliance, quality regression. Use before hand-rolling a curl loop, when onboarding a provider, or debugging \"system prompt 不生效\" / a tok/s claim — 测评/压测一个模型或渠道. Not for TTS/voice-clone supplier eval (use the audio skill).",
  634. "source": "./llm-eval-harness",
  635. "strict": false,
  636. "version": "1.8.0",
  637. "category": "developer-tools",
  638. "keywords": [
  639. "llm",
  640. "eval",
  641. "benchmark",
  642. "model-comparison",
  643. "speed-test",
  644. "concurrency",
  645. "protocol-compliance",
  646. "tokens-per-second",
  647. "ttft",
  648. "thinking-aware",
  649. "availability",
  650. "fidelity",
  651. "system-prompt",
  652. "gateway-testing",
  653. "vendor-bug-report"
  654. ]
  655. },
  656. {
  657. "name": "llm-icon-finder",
  658. "description": "Find and access AI/LLM model brand icons from lobe-icons library in SVG/PNG/WEBP formats",
  659. "source": "./llm-icon-finder",
  660. "strict": false,
  661. "version": "1.0.0",
  662. "category": "assets",
  663. "keywords": [
  664. "icons",
  665. "ai-models",
  666. "llm",
  667. "branding",
  668. "lobe-icons"
  669. ]
  670. },
  671. {
  672. "name": "product-analysis",
  673. "description": "Multi-path parallel product analysis with cross-model test-time compute scaling. Spawns parallel agents (Claude Code + Codex CLI) for multi-perspective exploration, then synthesizes findings into actionable optimization plans. Supports self-audit, UX audit, API audit, architecture review, and competitive benchmarking via competitors-analysis skill",
  674. "source": "./product-analysis",
  675. "strict": false,
  676. "version": "1.0.3",
  677. "category": "productivity",
  678. "keywords": [
  679. "product-analysis",
  680. "self-review",
  681. "ux-audit",
  682. "parallel-agents",
  683. "cross-model",
  684. "test-time-compute",
  685. "codex",
  686. "synthesis",
  687. "product-audit",
  688. "information-architecture"
  689. ]
  690. },
  691. {
  692. "name": "prompt-optimizer",
  693. "description": "Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) methodology. Use when users provide loose requirements, ambiguous feature descriptions, need to enhance prompts for AI-generated code/products/documents, request prompt optimization, or want to improve requirements engineering. Applies domain theories (GTD, BJ Fogg, Gestalt, AIDA, Zero Trust) and structured Role/Skills/Workflows/Examples/Formats framework",
  694. "source": "./prompt-optimizer",
  695. "strict": false,
  696. "version": "1.2.0",
  697. "category": "productivity",
  698. "keywords": [
  699. "prompt-engineering",
  700. "ears",
  701. "requirements",
  702. "specifications",
  703. "optimization",
  704. "domain-theory",
  705. "prompt-enhancement",
  706. "ai-prompting"
  707. ]
  708. },
  709. {
  710. "name": "promptfoo-evaluation",
  711. "description": "Configures and runs LLM evaluation using Promptfoo framework. Use when setting up prompt testing, creating evaluation configs (promptfooconfig.yaml), writing Python custom assertions, implementing llm-rubric for LLM-as-judge, or managing few-shot examples in prompts. Triggers on keywords like promptfoo, eval, LLM evaluation, prompt testing, or model comparison",
  712. "source": "./promptfoo-evaluation",
  713. "strict": false,
  714. "version": "1.1.0",
  715. "category": "developer-tools",
  716. "keywords": [
  717. "promptfoo",
  718. "evaluation",
  719. "llm-testing",
  720. "prompt-testing",
  721. "assertions",
  722. "llm-rubric",
  723. "few-shot",
  724. "model-comparison"
  725. ]
  726. },
  727. {
  728. "name": "qa-expert",
  729. "description": "QA process setup with AAA test cases, P0-P4 bug tracking, metrics reports, OWASP security testing and third-party handoffs. Use for test planning, approved-batch execution and checkpoint recovery through the bundled master prompt.",
  730. "source": "./qa-expert",
  731. "strict": false,
  732. "version": "1.2.16",
  733. "category": "developer-tools",
  734. "keywords": [
  735. "qa",
  736. "testing",
  737. "test-cases",
  738. "bug-tracking",
  739. "google-standards",
  740. "owasp",
  741. "security",
  742. "automation",
  743. "quality-gates",
  744. "metrics"
  745. ]
  746. },
  747. {
  748. "name": "repomix-safe-mixer",
  749. "description": "Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing. Use when packaging code for distribution, creating reference packages, or when the user mentions security concerns about sharing code with repomix",
  750. "source": "./repomix-safe-mixer",
  751. "strict": false,
  752. "version": "1.0.2",
  753. "category": "security",
  754. "keywords": [
  755. "repomix",
  756. "security",
  757. "credentials",
  758. "secrets-scanning",
  759. "safe-packaging",
  760. "secret-detection",
  761. "code-security"
  762. ]
  763. },
  764. {
  765. "name": "repomix-unmixer",
  766. "description": "Extract files from repomix packaged formats (XML, Markdown, JSON) with automatic format detection and validation",
  767. "source": "./repomix-unmixer",
  768. "strict": false,
  769. "version": "1.0.1",
  770. "category": "utilities",
  771. "keywords": [
  772. "repomix",
  773. "unmix",
  774. "extract",
  775. "xml",
  776. "conversion"
  777. ]
  778. },
  779. {
  780. "name": "scrapling-skill",
  781. "description": "Install, troubleshoot, and use Scrapling CLI for extracting HTML, Markdown, or text from webpages. Diagnoses missing extras, Playwright browser runtime issues, TLS verification failures, and WeChat public article extraction patterns. Use when users mention Scrapling, `scrapling extract`, `uv tool install scrapling`, or need to decide between static and browser-backed fetching",
  782. "source": "./scrapling-skill",
  783. "strict": false,
  784. "version": "1.0.3",
  785. "category": "developer-tools",
  786. "keywords": [
  787. "scrapling",
  788. "web-scraping",
  789. "html",
  790. "markdown",
  791. "playwright",
  792. "wechat",
  793. "extraction",
  794. "cli"
  795. ]
  796. },
  797. {
  798. "name": "slides-creator",
  799. "description": "Deprecated slide-creation entry retained as a compatibility notice. Use to check the retirement status of slides-creator or identify a legacy installation. This package does not generate slides or delegate presentation creation.",
  800. "source": "./slides-creator",
  801. "strict": false,
  802. "version": "2.1.1",
  803. "category": "content-creation",
  804. "keywords": [
  805. "slides",
  806. "presentation",
  807. "ppt",
  808. "deck",
  809. "narrative",
  810. "storytelling",
  811. "ABCDEFG"
  812. ]
  813. },
  814. {
  815. "name": "teams-channel-post-writer",
  816. "description": "Create professional Microsoft Teams channel posts with Adaptive Cards, formatted announcements, and corporate communication standards",
  817. "source": "./teams-channel-post-writer",
  818. "strict": false,
  819. "version": "1.1.0",
  820. "category": "communication",
  821. "keywords": [
  822. "teams",
  823. "microsoft",
  824. "adaptive-cards",
  825. "communication",
  826. "announcements"
  827. ]
  828. },
  829. {
  830. "name": "terraform-skill",
  831. "description": "Diagnoses and designs safe Terraform releases, provisioners (remote-exec/local-exec/file, cloud-init, Compose, Caddy), multi-environment isolation, and fresh-host bootstrap. Use when writing or reviewing plan/apply wrappers or provisioners; when staging/production config may differ; when a rollout can mutate a shared gateway; or debugging drift, TLS, container restarts, DNS duplication, or snapshot contamination.",
  832. "source": "./terraform-skill",
  833. "strict": false,
  834. "version": "1.5.16",
  835. "category": "developer-tools",
  836. "keywords": [
  837. "terraform",
  838. "iac",
  839. "provisioner",
  840. "devops",
  841. "infrastructure",
  842. "cloud-init",
  843. "cloudflare",
  844. "release-safety"
  845. ]
  846. },
  847. {
  848. "name": "tunnel-doctor",
  849. "description": "MUST be used first for tunnel / proxy-path connectivity failures or slow throughput (网络故障 / 连不上 / 代理或隧道下超时). Diagnoses Tailscale, proxy, TUN, DNS and SSH-tunnel problems on macOS and Windows/WSL, e.g. Tailscale ping works but SSH fails, curl works but browser gets 503, Git/Docker fails behind the proxy, or downloads crawl despite a reachable proxy. Not for application-layer bugs (use debugging-network-issues).",
  850. "source": "./tunnel-doctor",
  851. "strict": false,
  852. "version": "1.18.1",
  853. "category": "developer-tools",
  854. "keywords": [
  855. "tailscale",
  856. "vpn",
  857. "shadowrocket",
  858. "clash",
  859. "surge",
  860. "route-conflict",
  861. "wsl",
  862. "ssh",
  863. "ssh-tunnel",
  864. "autossh",
  865. "proxy",
  866. "proxycommand",
  867. "git-push",
  868. "networking",
  869. "macos",
  870. "makefile",
  871. "remote-development",
  872. "local-domain"
  873. ]
  874. },
  875. {
  876. "name": "twitter-reader",
  877. "description": "Fetch Twitter/X post content including long-form Articles with full images and metadata. Use when Claude needs to retrieve tweet/article content, author info, engagement metrics (likes, retweets, bookmarks), and embedded media. Supports individual posts and X Articles (long-form content). Automatically downloads all images to local attachments folder and generates complete Markdown with proper image references. Preferred over Jina for X Articles with images.",
  878. "source": "./twitter-reader",
  879. "strict": false,
  880. "version": "1.4.0",
  881. "category": "utilities",
  882. "keywords": [
  883. "twitter",
  884. "x",
  885. "social-media",
  886. "jina",
  887. "content-fetching",
  888. "api",
  889. "scraping",
  890. "threads",
  891. "images",
  892. "attachments",
  893. "markdown"
  894. ]
  895. },
  896. {
  897. "name": "ui-designer",
  898. "description": "Extract design systems from reference UI images and generate implementation-ready UI design prompts. Use when users provide UI screenshots/mockups and want to create consistent designs",
  899. "source": "./ui-designer",
  900. "strict": false,
  901. "version": "1.0.0",
  902. "category": "design",
  903. "keywords": [
  904. "ui",
  905. "design-system",
  906. "mockup",
  907. "screenshot",
  908. "design-extraction",
  909. "mvp"
  910. ]
  911. },
  912. {
  913. "name": "video-comparer",
  914. "description": "Compare two videos and generate interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Use when analyzing compression results, evaluating codec performance, or assessing video quality differences",
  915. "source": "./video-comparer",
  916. "strict": false,
  917. "version": "1.0.0",
  918. "category": "media",
  919. "keywords": [
  920. "video",
  921. "comparison",
  922. "quality-analysis",
  923. "psnr",
  924. "ssim",
  925. "compression",
  926. "ffmpeg",
  927. "codec"
  928. ]
  929. },
  930. {
  931. "name": "windows-remote-desktop-connection-doctor",
  932. "description": "Diagnoses Windows App (Remote Desktop / AVD / W365 / direct PC) connection problems on macOS: transport selection (UDP Shortpath vs WebSocket), VPN/proxy interference, and stuck \"Configuring remote PC...\" dialogs. Use when a VDI connection is slow/stuck, transport shows WebSocket not UDP, or Windows App freezes at a progress dialog. Not for general network diagnosis (use debugging-network-issues or tunnel-doctor).",
  933. "source": "./windows-remote-desktop-connection-doctor",
  934. "strict": false,
  935. "version": "1.2.0",
  936. "category": "developer-tools",
  937. "keywords": [
  938. "rdp",
  939. "avd",
  940. "wvd",
  941. "w365",
  942. "windows-app",
  943. "remote-desktop",
  944. "shortpath",
  945. "udp",
  946. "websocket",
  947. "stun",
  948. "turn",
  949. "vpn",
  950. "macos",
  951. "networking"
  952. ]
  953. },
  954. {
  955. "name": "youtube-downloader",
  956. "description": "Fetch existing YouTube transcripts/subtitles or archive spoken video content as text, and download YouTube videos/audio or HLS streams (m3u8) with yt-dlp and ffmpeg. Use for transcript/subtitle retrieval, text-first video archiving, video/audio downloads, protected streams with authentication headers, and download failures including nsig, 403 or browser-cookie issues.",
  957. "source": "./youtube-downloader",
  958. "strict": false,
  959. "version": "1.4.0",
  960. "category": "utilities",
  961. "keywords": [
  962. "youtube",
  963. "yt-dlp",
  964. "video-download",
  965. "audio-extraction",
  966. "mp3",
  967. "download",
  968. "hls",
  969. "m3u8",
  970. "ffmpeg",
  971. "streaming",
  972. "mux",
  973. "vimeo"
  974. ]
  975. },
  976. {
  977. "name": "debugging-network-issues",
  978. "description": "Investigates network, streaming and protocol failures with falsification-first layered experiments, the general fallback for unknown root causes. Use for ECONNRESET / RST_STREAM / SSE stalls, CDN/CGNAT timeouts or certificate errors, throughput collapse where everything returns 200 but transfers crawl, or LAN identity/topology mysteries. Not for known Tailscale/TUN/DNS/proxy-path conflicts (use tunnel-doctor).",
  979. "source": "./debugging-network-issues",
  980. "strict": false,
  981. "version": "1.12.4",
  982. "category": "developer-tools",
  983. "keywords": [
  984. "debugging",
  985. "network",
  986. "sse",
  987. "http2",
  988. "rst",
  989. "econnreset",
  990. "cloudflare",
  991. "streaming",
  992. "troubleshooting",
  993. "methodology",
  994. "proxy",
  995. "tun",
  996. "vpn",
  997. "cname",
  998. "dns",
  999. "lan",
  1000. "mdns",
  1001. "throughput",
  1002. "bandwidth",
  1003. "performance"
  1004. ]
  1005. },
  1006. {
  1007. "name": "auto-repo-setup",
  1008. "description": "Evidence-driven repository setup, repair, handoff, and safe Git workflow for Claude Code or Codex. Detects the actual stack from project instructions and manifests instead of assuming Python, ffmpeg, uv, or .env; preserves local work during sync/conflict handling; diagnoses repeated SessionStart output before editing config; and defaults routine startup behavior to AGENTS.md/CLAUDE.md or a normal Agent request. Lifecycle hooks are an explicit pre-prompt exception with guarded, idempotent Claude Code setup and runtime-specific Codex verification.",
  1009. "source": "./auto-repo-setup",
  1010. "strict": false,
  1011. "version": "2.2.4",
  1012. "category": "developer-tools",
  1013. "keywords": [
  1014. "repo-setup",
  1015. "environment",
  1016. "onboarding",
  1017. "git",
  1018. "configuration",
  1019. "claude-code",
  1020. "project-instructions",
  1021. "session-start-diagnosis",
  1022. "pii-guard",
  1023. "codex",
  1024. "git-sync"
  1025. ]
  1026. },
  1027. {
  1028. "name": "llm-wiki-setup",
  1029. "description": "Co-creates a personal investment-research LLM Wiki (Karpathy's pattern) by interviewing the user for THEIR OWN analysis framework, not a template — a living CLAUDE.md of pure markdown + wikilinks, no RAG in place of compilation. Use to build a compounding 投研第二大脑 / 投研知识库 / 个人投研 wiki, ingest research reports / earnings calls into an existing wiki, or run post-earnings prediction→fulfillment reviews.",
  1030. "source": "./llm-wiki-setup",
  1031. "strict": false,
  1032. "version": "1.2.0",
  1033. "category": "documentation",
  1034. "keywords": [
  1035. "llm-wiki",
  1036. "karpathy",
  1037. "investment-research",
  1038. "投研第二大脑",
  1039. "knowledge-base",
  1040. "markdown-wiki",
  1041. "compounding-notes",
  1042. "analyst-tracking",
  1043. "second-brain",
  1044. "投研知识库"
  1045. ]
  1046. },
  1047. {
  1048. "name": "marketplace-health-check",
  1049. "description": "Runs an evidence-based health audit of this skills marketplace repo — code safety, docs/SSOT, security/PII, PR/issue triage, manifest integrity — via a parallel workflow, then verifies findings by priority. Use for 全面体检 / 检查仓库状态 / 审计一下仓库, a pre-release sweep, or \"is this repo OK\" even without saying \"workflow\". Not for building marketplace.json (use marketplace-dev) or cache drift (use skill-governance).",
  1050. "source": "./marketplace-health-check",
  1051. "strict": false,
  1052. "version": "1.2.0",
  1053. "category": "developer-tools",
  1054. "keywords": [
  1055. "health-check",
  1056. "audit",
  1057. "marketplace",
  1058. "workflow",
  1059. "pii",
  1060. "code-review",
  1061. "repo-audit"
  1062. ]
  1063. },
  1064. {
  1065. "name": "setup-notifications-via-wecom",
  1066. "description": "Set up and send technical status notifications through WeCom (Enterprise WeChat) webhooks. Use this skill whenever the user needs to send notifications, alerts, backup completion reports, or status updates via WeCom; when they mention 企业微信, 企微机器人, webhook, or alerting; or when a message needs to be clear, unambiguous, and technically precise rather than vague or condescending.",
  1067. "source": "./setup-notifications-via-wecom",
  1068. "strict": false,
  1069. "version": "1.3.0",
  1070. "category": "developer-tools",
  1071. "keywords": [
  1072. "wecom",
  1073. "enterprise-wechat",
  1074. "notifications",
  1075. "webhook",
  1076. "alerts",
  1077. "企业微信",
  1078. "企微机器人",
  1079. "status-updates",
  1080. "claude-code"
  1081. ]
  1082. },
  1083. {
  1084. "name": "notify-wecom",
  1085. "description": "Send a single one-off message to a WeCom (Enterprise WeChat) group bot. Use this skill whenever the user says \"/notify-wecom\", \"send a quick WeCom message\", \"企微通知一下\", \"临时发一条企业微信\", or any one-shot notification that does not need a reusable template or setup workflow.",
  1086. "source": "./notify-wecom",
  1087. "strict": false,
  1088. "version": "1.1.1",
  1089. "category": "developer-tools",
  1090. "keywords": [
  1091. "wecom",
  1092. "enterprise-wechat",
  1093. "notify",
  1094. "one-shot",
  1095. "企业微信",
  1096. "企微机器人",
  1097. "claude-code"
  1098. ]
  1099. },
  1100. {
  1101. "name": "github-sensitive-data-cleanup",
  1102. "description": "Scan and remove sensitive data (secrets, API keys, private domains/IPs, PII) from GitHub repository history. Use this skill whenever the user says scan sensitive data, clean git history, remove secrets from repo, sanitize GitHub history, 清理敏感数据, 历史重写, force push, 泄露, or needs to repair a public repo after accidental secret/private context leakage. Also use before any force push to a public repository to verify visibility, backup, and scan results.",
  1103. "source": "./github-sensitive-data-cleanup",
  1104. "strict": false,
  1105. "version": "2.1.0",
  1106. "category": "security",
  1107. "keywords": [
  1108. "github",
  1109. "sensitive-data",
  1110. "secrets",
  1111. "history-rewrite",
  1112. "git-filter-repo",
  1113. "gitleaks",
  1114. "pii",
  1115. "force-push",
  1116. "cleanup",
  1117. "claude-code"
  1118. ]
  1119. },
  1120. {
  1121. "name": "frontend-visual-qa",
  1122. "description": "Audits rendered UI and specific task/object-link handoffs; excludes ordinary source citations alone. Audits already-rendered UI and Markdown/Obsidian image layout — web app, deck/slide, dashboard, design-system, or Electron/native app — via real-browser/native-app journeys and a Playwright sweep. Use after UI implementation to find typography, overflow, responsive, routing, data-viz, browser-output, or native-shell defects, or to compare a render against a reference. Not for greenfield UI design (use ui-designer) or QA-program setup (use qa-expert).",
  1123. "source": "./frontend-visual-qa",
  1124. "strict": false,
  1125. "version": "1.21.52",
  1126. "category": "design",
  1127. "keywords": [
  1128. "frontend",
  1129. "visual-qa",
  1130. "layout",
  1131. "line-breaks",
  1132. "responsive",
  1133. "chrome",
  1134. "playwright",
  1135. "ai-slop",
  1136. "design-review",
  1137. "Markdown",
  1138. "Obsidian",
  1139. "image-sizing"
  1140. ]
  1141. },
  1142. {
  1143. "name": "openclaw",
  1144. "description": "Manage OpenClaw (龙虾 / lobster) instance configurations, gateway health, and plugin lifecycle — audit, diff, copy, add-model, list, and switch models across openclaw.json files; diagnose a parked or down gateway, plugin register failures, and hooks blocked after an upgrade; confirm whether an install is out of date. Use when juggling multiple OpenClaw / Claude Code wrapper instances, applying DeepSeek model patches, managing default models and aliases, or validating config.",
  1145. "source": "./openclaw",
  1146. "strict": false,
  1147. "version": "1.3.1",
  1148. "category": "claude-code",
  1149. "keywords": [
  1150. "openclaw",
  1151. "lobster",
  1152. "config",
  1153. "model-management",
  1154. "deepseek",
  1155. "claude-code",
  1156. "config-validation"
  1157. ]
  1158. },
  1159. {
  1160. "name": "download-gemini-images",
  1161. "description": "Download, export, save, or package images from a Google Gemini conversation page — uploaded images or generated image previews. Use when the task needs logged-in Chrome/Gemini state, opening Gemini image lightboxes, downloading the larger displayed files, renaming them in order, and producing a ZIP archive.",
  1162. "source": "./download-gemini-images",
  1163. "strict": false,
  1164. "version": "1.0.0",
  1165. "category": "media",
  1166. "keywords": [
  1167. "gemini",
  1168. "images",
  1169. "download",
  1170. "chrome",
  1171. "lightbox",
  1172. "zip",
  1173. "export"
  1174. ]
  1175. },
  1176. {
  1177. "name": "gemini-history-analyzer",
  1178. "description": "Analyze Google Takeout exports of Gemini conversation history — extract, categorize, and mine transcripts and attachments for insights, then optionally distill them into a personal knowledge base. Use when the user mentions Gemini Takeout, Gemini export, Gemini history, analyzing Gemini conversation data, or drags a takeout zip into the project.",
  1179. "source": "./gemini-history-analyzer",
  1180. "strict": false,
  1181. "version": "1.0.1",
  1182. "category": "productivity",
  1183. "keywords": [
  1184. "gemini",
  1185. "takeout",
  1186. "history",
  1187. "analysis",
  1188. "conversation",
  1189. "export",
  1190. "transcript",
  1191. "knowledge-base"
  1192. ]
  1193. },
  1194. {
  1195. "name": "wps-doc-scraper",
  1196. "description": "Faithfully archive public WPS / KDocs / 金山文档 links — especially embedded ProcessOn .pof mind maps and canvases — as raw source data, original SVG/PNG, and Markdown. Use when a user gives a kdocs.cn or wps.processon.com link and asks to scrape, save, download, 扒下来, 归档, or 转 Markdown without logging in.",
  1197. "source": "./wps-doc-scraper",
  1198. "strict": false,
  1199. "version": "1.0.0",
  1200. "category": "productivity",
  1201. "keywords": [
  1202. "wps",
  1203. "kdocs",
  1204. "processon",
  1205. "mindmap",
  1206. "scraper",
  1207. "markdown",
  1208. "archive"
  1209. ]
  1210. },
  1211. {
  1212. "name": "openclaw-model-switch",
  1213. "description": "Switch or repair the model configuration of an OpenClaw instance (e.g., Kimi k2p6 → k3): change the default model, add model definitions, and fix model-config failures — 401 \"Invalid token\", \"No available channel / model not found\", thinking-level rejections, and config edits that don't take effect. Ships a config-discovering switch script with backup + mirror sync, an endpoint probe protocol, and a field-tested trap catalog (env-var key hijack, provider-plugin thinking restrictions, relay availability).",
  1214. "source": "./openclaw-model-switch",
  1215. "strict": false,
  1216. "version": "1.2.1",
  1217. "category": "claude-code",
  1218. "keywords": [
  1219. "claude-code",
  1220. "config",
  1221. "deepseek",
  1222. "gateway",
  1223. "k2.7",
  1224. "k3",
  1225. "kimi",
  1226. "lobster",
  1227. "model-management",
  1228. "model-repair",
  1229. "model-switch",
  1230. "openclaw",
  1231. "relay",
  1232. "thinking-levels"
  1233. ]
  1234. },
  1235. {
  1236. "name": "tibo-reset-codex",
  1237. "description": "查询 ChatGPT/Codex 重置公告及多个 Pro 账号的剩余额度、备用 Full reset;复用 Google 登录逐个核实并恢复网页账号,换算北京时间。区分 Tibo 官宣、未官宣的平台静默重置、banked reset 与账户级周期重置。Use when 用户问「什么时候重置」「额度什么时候恢复」「下次全员重置几点」 「banked reset 到了吗」「Tibo 说了什么」「usage limit when reset」,或说「额度突然回到 100%」「好像/肯定又重置了」,或问「几个账号都用完了吗」「哪个还满额」。必须用实时产品状态、独立用户实测与公告交叉核验;禁止因 Tibo Radar 没有新条目就否定已经发生的重置,并须把太平洋时间当场换算为北京时间。",
  1238. "source": "./tibo-reset-codex",
  1239. "strict": false,
  1240. "version": "2.8.2",
  1241. "category": "utilities",
  1242. "keywords": [
  1243. "chatgpt",
  1244. "codex",
  1245. "openai",
  1246. "usage-limit",
  1247. "reset",
  1248. "tibo",
  1249. "quota",
  1250. "额度重置",
  1251. "timezone"
  1252. ]
  1253. },
  1254. {
  1255. "name": "excalidraw-use",
  1256. "description": "Places existing images onto an Excalidraw whiteboard, turns a slide deck into clean per-slide images, and inspects a .excalidraw file. Use whenever someone mentions Excalidraw, a whiteboard/canvas, .excalidraw, 白板 or 画板 — e.g. \"put these screenshots on my board\" — or a workshop delivered by hand-drawing over screenshots on a shared canvas. Not for generating a diagram from a text description.",
  1257. "source": "./excalidraw-use",
  1258. "strict": false,
  1259. "version": "1.1.0",
  1260. "category": "developer-tools",
  1261. "keywords": [
  1262. "excalidraw",
  1263. "whiteboard",
  1264. "canvas",
  1265. "screenshot",
  1266. "slide-deck",
  1267. "image-layout",
  1268. "puppeteer",
  1269. "白板"
  1270. ]
  1271. },
  1272. {
  1273. "name": "meme-creator",
  1274. "description": "Creates video/GIF memes by overlaying images (logos, avatars, stickers) onto moving objects in a clip with frame-accurate tracking, then exports MP4 + GIF. Use whenever the user wants a meme, 梗图, 表情包, or reaction GIF from footage; to cover faces in a video; or asks to 把 logo/头像贴到视频里跟着动. Not for transcript-driven editing, programmatic scene generation, or subtitle work.",
  1275. "source": "./meme-creator",
  1276. "strict": false,
  1277. "version": "1.1.1",
  1278. "category": "media",
  1279. "keywords": [
  1280. "meme",
  1281. "梗图",
  1282. "表情包",
  1283. "gif",
  1284. "video-overlay",
  1285. "object-tracking",
  1286. "csrt",
  1287. "sticker",
  1288. "avatar",
  1289. "logo"
  1290. ]
  1291. },
  1292. {
  1293. "name": "data-visualization-discipline",
  1294. "description": "数据可视化的判断层 SSOT——画任何图表、dashboard、看板之前先加载它,不是画完之后。管\"该不该这么画\":这张图想让读者得出什么结论、用均值还是中位数、能不能聚合、堆叠还是折线、能不能上双轴、配色与颜色数量、同一实体跨图是否同色同位、表格该留几列。介质无关:HTML 报告页、React/Vue dashboard、PPT 原生图表、matplotlib/plotly/ECharts/D3、渲染成 PNG 的图,一律适用。Use when 动手画图之前,或评审既有图表(\"这几张图有什么问题\"、\"图例为什么不一致\")。Not for 报告页的排版/组件/交互(用 report-with-html:report-with-html)或 PPT 原生图表的实现与渲染陷阱(用 deck-creator:deck-creator)。",
  1295. "source": "./data-visualization-discipline",
  1296. "strict": false,
  1297. "version": "1.1.10",
  1298. "category": "documentation",
  1299. "keywords": [
  1300. "数据可视化",
  1301. "图表",
  1302. "chart",
  1303. "dashboard",
  1304. "看板",
  1305. "可视化纪律",
  1306. "图型选择",
  1307. "统计量",
  1308. "中位数",
  1309. "堆叠图",
  1310. "双轴",
  1311. "配色",
  1312. "图例",
  1313. "Cleveland",
  1314. "Tufte",
  1315. "Bertin",
  1316. "data visualization",
  1317. "chart critique",
  1318. "图表评审"
  1319. ]
  1320. },
  1321. {
  1322. "name": "report-with-html",
  1323. "description": "Produces the reader-facing HTML artifact — report, dashboard, architecture view, data browser, or review workbench — evidence-backed, browser-verified. Use when the deliverable IS a visual HTML report, or the user asks for an HTML/web presentation. Load data-visualization-discipline for chart judgment. Not for chat status or Markdown prose unless asked to become a report; not for PowerPoint (deck-creator Route C).",
  1324. "source": "./report-with-html",
  1325. "strict": false,
  1326. "version": "1.7.3",
  1327. "category": "documentation",
  1328. "keywords": [
  1329. "HTML报告",
  1330. "可视化报告",
  1331. "一页纸",
  1332. "数据报告",
  1333. "半年报",
  1334. "系统可视化",
  1335. "差距地图",
  1336. "架构可视化",
  1337. "用户旅程",
  1338. "决策看板",
  1339. "事故时间线",
  1340. "对比看板",
  1341. "dashboard",
  1342. "html",
  1343. "html one-pager",
  1344. "数据浏览器",
  1345. "归档浏览器",
  1346. "审核工作台",
  1347. "review workbench"
  1348. ]
  1349. },
  1350. {
  1351. "name": "ghostty-use",
  1352. "description": "Snapshots local Codex/Claude CLI sessions across terminals and restores IDs in Ghostty after reboot (保存会话/重启前备份/恢复窗口), audits survivors, and makes change-only automatic backups (定期增量快照). Handles unmanaged Codex account switches (额度耗尽换号); Minions native_runtime uses Account Manager. Not --resume help, screenshots or tmux.",
  1353. "source": "./ghostty-use",
  1354. "strict": false,
  1355. "version": "1.15.2",
  1356. "category": "developer-tools",
  1357. "keywords": [
  1358. "ghostty",
  1359. "terminal",
  1360. "session-restore",
  1361. "reboot",
  1362. "snapshot",
  1363. "claude-code",
  1364. "codex",
  1365. "终端会话",
  1366. "会话恢复",
  1367. "重启恢复"
  1368. ]
  1369. },
  1370. {
  1371. "name": "product-growth",
  1372. "description": "Diagnose growth from business data and actively discovered feedback; distinguish attribution from causal effects and validate useful actions across product types. Use for growth sources, missing channels/metrics, activation, retention, revenue or ecosystem adoption.",
  1373. "source": "./product-growth",
  1374. "strict": false,
  1375. "version": "1.0.2",
  1376. "category": "productivity",
  1377. "keywords": [
  1378. "growth",
  1379. "product-growth",
  1380. "customer-feedback",
  1381. "retention",
  1382. "activation",
  1383. "causal-inference",
  1384. "增长",
  1385. "留存"
  1386. ]
  1387. }
  1388. ]
  1389. }
README.md · README · 3,933 lines · 2 findings marked
  1. # Claude Code Skills Marketplace
  2. <div align="center">
  3. [![English](https://img.shields.io/badge/Language-English-blue)](./README.md)
  4. [![简体中文](https://img.shields.io/badge/语言-简体中文-red)](./README.zh-CN.md)
  5. [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
  6. [![Claude Code](https://img.shields.io/badge/Claude%20Code-2.0.13+-purple.svg)](https://claude.com/code)
  7. [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](./CONTRIBUTING.md)
  8. [![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/daymade/claude-code-skills/graphs/commit-activity)
  9. </div>
  10. Professional Claude Code skills marketplace for development, research, content, and residential floor plan searches.
  11. For ordinary file reads and command-output capture, use the standalone
  12. [bounded I/O tools](references/bounded-io.md). These commands do not enter Skill development.
  13. ---
  14. ## 🌟 Essential Skill: skill-creator
  15. **⭐ Start here if you want to create your own skills!**
  16. The `skill-creator` is the **meta-skill** that enables you to build, validate, and package your own Claude Code skills. It's the most important tool in this marketplace because it empowers you to extend Claude Code with your own specialized workflows.
  17. ### Why This skill-creator?
  18. This is a **production-hardened fork** of [Anthropic's official skill-creator](https://github.com/anthropics/skills/tree/main/skills/skill-creator), born from building real skills and hitting every wall the official version doesn't warn you about.
  19. **The official skill-creator tells you _what_ to build. Ours also tells you _what not to try_ — and why.**
  20. | You're trying to... | Official | This Fork |
  21. |---------------------|----------|-----------|
  22. | Research before building | "Check available MCPs" | Ordered search protocol with decision matrix: Adopt / Extend / Build |
  23. | Create a skill interactively | Prose-based instructions | Structured AskUserQuestion checkpoints — user never loses context |
  24. | Avoid common mistakes | No guidance | Cache edit warnings, prerequisite checks, security scan gate |
  25. | Know the architecture options | Not mentioned | Inline vs Fork decision guide with examples (choosing wrong silently breaks your skill) |
  26. | Validate before shipping | Basic YAML check | Expanded structural validator plus provenance-checked old-vs-new capability audit; packaging re-verifies the completed review instead of trusting a marker |
  27. | Match validation cost to risk | One full create-test-review loop | Risk tier and evaluation spend are separate: targeted checks first; paired benchmarks require explicit authorization or a decision-bearing evidence plan plus opt-in |
  28. | Check secrets and archive paths | No tooling | `security_scan.py`: Gitleaks plus scoped Python archive-path analysis; required before packaging |
  29. | Learn from real failures | No failure cases | Battle-tested methodology with documented failure patterns and gotchas |
  30. | Distill past conversations safely | Not covered | Explicit local manifest, message-level time window, redaction, opaque source IDs, ignored `.enrich/` staging, and manual promotion into references/scripts |
  31. | Turn approved artifacts into skill behavior | Not covered | Artifact-corpus distillation workflow: script-measured pattern extraction (≥3-artifact threshold), cataloging≠distillation gate, invariant-vs-register boundary, independent completeness audit |
  32. | Survive concurrent sessions on one skill repo | Not covered | git-ref baselines, re-read-before-write, HEAD check before commit, own-paths-only staging, one-bump-per-outcome versioning |
  33. | Ground knowledge skills in evidence | General advice | Authority ladder from real calls and machine-readable specs through production code, plus executable-example smoke checks and evidence-boundary rules |
  34. | Have both installed at once | Coin flip — the two descriptions are near-identical | Detects the clash on trigger and offers a one-command, reversible SessionStart routing hook (only ever installed when both coexist); the official plugin stays usable by explicit request |
  35. | Your own skill collides with an installed plugin | Not covered | `generate_supersede_kit.py` stamps the same conditional routing kit into your skill, plus a measured precedence decision guide (rename → description tiebreaker → hook → disable) |
  36. > Full methodology: [skill-creator/references/skill-development-methodology.md](./daymade-skill/skill-creator/references/skill-development-methodology.md)
  37. ### Quick Install
  38. **In Claude Code (in-app):**
  39. ```text
  40. /plugin marketplace add daymade/claude-code-skills
  41. ```
  42. Then:
  43. 1. Select **Browse and install plugins**
  44. 2. Select **daymade/claude-code-skills**
  45. 3. Select **daymade-skill** (includes skill-creator)
  46. 4. Select **Install now**
  47. **From your terminal (CLI):**
  48. ```bash
  49. claude plugin marketplace add https://github.com/daymade/claude-code-skills
  50. # Marketplace name: daymade-skills (from marketplace.json)
  51. claude plugin install daymade-skill@daymade-skills
  52. ```
  53. ### What You Can Do
  54. After installing skill-creator, simply ask Claude Code:
  55. ```
  56. "Create a new skill called my-awesome-skill in ~/my-skills"
  57. "Validate my skill at ~/my-skills/my-awesome-skill"
  58. "Package my skill at ~/my-skills/my-awesome-skill for distribution"
  59. ```
  60. Claude Code, with skill-creator loaded, will guide you through the entire skill creation process - from understanding your requirements to packaging the final skill.
  61. 📚 **Full documentation**: [daymade-skill/skill-creator/SKILL.md](./daymade-skill/skill-creator/SKILL.md)
  62. ### Live Demos
  63. **📝 Initialize New Skill**
  64. ![Initialize Skill Demo](./demos/skill-creator/init-skill.gif)
  65. **✅ Validate Skill Structure**
  66. ![Validate Skill Demo](./demos/skill-creator/validate-skill.gif)
  67. **📦 Package Skill for Distribution**
  68. ![Package Skill Demo](./demos/skill-creator/package-skill.gif)
  69. ---
  70. ## 🚀 Quick Installation
  71. ### Install Inside Claude Code (In-App)
  72. ```text
  73. /plugin marketplace add daymade/claude-code-skills
  74. ```
  75. Then:
  76. 1. Select **Browse and install plugins**
  77. 2. Select **daymade/claude-code-skills**
  78. 3. Select the plugin you want
  79. 4. Select **Install now**
  80. ### Generate Installation Commands
  81. These scripts print commands for you to run in your terminal. Download and run
  82. the script locally to choose from the featured-plugin menu or make a custom selection.
  83. **macOS/Linux:**
  84. ```bash
  85. bash -o pipefail -c 'curl -fsSL https://raw.githubusercontent.com/daymade/claude-code-skills/main/scripts/install.sh | bash'
    • Note: Pipes a downloaded script directly into a shell (curl | sh / wget | bash)
    • Line 126 on GitHub
  86. ```
  87. **Windows (PowerShell):**
  88. ```powershell
  89. iwr -useb https://raw.githubusercontent.com/daymade/claude-code-skills/main/scripts/install.ps1 | iex
  90. ```
  91. ### Manual Installation
  92. Add the marketplace:
  93. ```bash
  94. claude plugin marketplace add https://github.com/daymade/claude-code-skills
  95. ```
  96. Marketplace name is `daymade-skills` (from marketplace.json). Use `@daymade-skills` when installing plugins.
  97. Do not use the repo path as a marketplace name (e.g. `@daymade/claude-code-skills` will fail).
  98. In Claude Code, use `/plugin ...` slash commands. In your terminal, use `claude plugin ...`.
  99. **Essential Skill** (recommended first install):
  100. ```bash
  101. # skill-creator ships inside the daymade-skill suite
  102. claude plugin install daymade-skill@daymade-skills
  103. ```
  104. **Documentation Suite** (shared namespace for document workflows):
  105. ```bash
  106. claude plugin install daymade-docs@daymade-skills
  107. ```
  108. This suite exposes related skills under one namespace, including:
  109. ```text
  110. /daymade-docs:docs-router
  111. /daymade-docs:doc-to-markdown
  112. /daymade-docs:mermaid-tools
  113. /daymade-docs:pdf-creator
  114. /daymade-docs:ppt-creator
  115. /daymade-docs:docs-cleaner
  116. /daymade-docs:excel-automation
  117. /daymade-docs:read-docx-review
  118. ```
  119. These skills ship as a bundle — there are no separate single-skill plugins. All documentation skills live under `daymade-docs/` and install together from the suite.
  120. The router handles automatic selection. The specialist commands remain available for manual use;
  121. For the retained PPT command, read the [compatibility notice](./daymade-docs/ppt-creator/SKILL.md).
  122. **Apple Platform Suite** (shared namespace for macOS and iOS development/operations):
  123. ```bash
  124. claude plugin install daymade-macos@daymade-skills
  125. ```
  126. ```text
  127. /daymade-macos:capture-screen
  128. /daymade-macos:developing-ios-apps
  129. /daymade-macos:macos-cleaner
  130. /daymade-macos:macos-load-doctor
  131. /daymade-macos:macos-permissions
  132. /daymade-macos:macos-watchdog
  133. ```
  134. These skills are bundle-only under `daymade-macos`.
  135. **Codex Suite** (shared namespace for Codex workstation setup, assisted coding, and visual exploration):
  136. ```bash
  137. claude plugin install daymade-codex@daymade-skills
  138. ```
  139. Codex CLI and Desktop users can install the same suite through Codex's plugin
  140. marketplace:
  141. ```bash
  142. codex plugin marketplace add daymade/claude-code-skills
  143. codex plugin add daymade-codex@daymade-skills
  144. ```
  145. ```text
  146. /daymade-codex:codex-image-gallery
  147. /daymade-codex:local-codex
  148. /daymade-codex:design-style-picker
  149. /daymade-codex:interaction-design-board
  150. /daymade-codex:codex-1m-context-window-setup
  151. ```
  152. These skills are bundle-only under `daymade-codex`.
  153. **Claude Code Operations Suite** (shared namespace for Claude Code power-user workflows):
  154. ```bash
  155. claude plugin install daymade-claude-code@daymade-skills
  156. ```
  157. This suite bundles the skills that extend Claude Code itself — cross-project prior-work retrieval across code, docs, Skills, meetings, WeChat archives, and conversation history; fast local conversation discovery across Claude Code and Codex; session recovery; CLAUDE.md tuning; troubleshooting; statusline configuration; export repair; marketplace development and suite consolidation; terminal screenshot rendering; usage analysis; and multi-provider model switching:
  158. ```text
  159. /daymade-claude-code:claude-code-ops-router
  160. /daymade-claude-code:local-conversation-history
  161. /daymade-claude-code:read-claude-code-history
  162. /daymade-claude-code:read-codex-history
  163. /daymade-claude-code:continue-claude-code-work
  164. /daymade-claude-code:continue-codex-work
  165. /daymade-claude-code:claude-skills-troubleshooting
  166. /daymade-claude-code:claude-md-progressive-disclosurer
  167. /daymade-claude-code:statusline-generator
  168. /daymade-claude-code:fixing-claude-export-conversations
  169. /daymade-claude-code:marketplace-dev
  170. /daymade-claude-code:terminal-screenshot
  171. /daymade-claude-code:claude-usage-analyst
  172. /daymade-claude-code:claude-switch-models-setup
  173. /daymade-claude-code:read-claude-web-conversation
  174. /daymade-claude-code:claude-migrate-memory-to-doc
  175. /daymade-claude-code:claude-code-hooks
  176. /daymade-claude-code:prior-work-retrieval
  177. /daymade-claude-code:claude-code-ping-start-5h-quota
  178. /daymade-claude-code:agent-web-search-setup
  179. /daymade-claude-code:tech-selection
  180. ```
  181. Installed names render as `daymade-claude-code:<skill>` under a single shared namespace. These skills are bundle-only — install the suite to get all members.
  182. **Financial Data Suite** (shared namespace for investment-research and financial data workflows):
  183. ```bash
  184. claude plugin install daymade-financial@daymade-skills
  185. ```
  186. This suite bundles the skills that fetch and analyze financial data — Bigdata.com (RavenPack) structured financials and sentiment, US equity fundamentals via yfinance, Gangtise (岗底斯) OpenAPI research suite orchestration, A-share news and policy aggregation, A-share pharmaceutical sector daily reporting, structured devil's-advocate pressure-testing of investment theses, and adversarial due diligence on inflated benchmark claims:
  187. ```text
  188. /daymade-financial:financial-router
  189. /daymade-financial:bigdata-skill
  190. /daymade-financial:financial-data-collector
  191. /daymade-financial:gangtise-copilot
  192. /daymade-financial:ashare-news-fetcher
  193. /daymade-financial:daymade-sector-research
  194. /daymade-financial:pharma-daily-report
  195. /daymade-financial:devils-advocate
  196. /daymade-financial:benchmark-due-diligence
  197. ```
  198. Installed names render as `daymade-financial:<skill>` under a single shared namespace. These skills are bundle-only — install the suite to get all members.
  199. **Install Other Skills:**
  200. ```bash
  201. # Research-driven improvement of a specified existing Skill
  202. claude plugin install skill-evolver@daymade-skills
  203. # GitHub operations
  204. claude plugin install github-ops@daymade-skills
  205. # Teams communication
  206. claude plugin install teams-channel-post-writer@daymade-skills
  207. # Local Claude/Codex agent messaging
  208. claude plugin install peer-message@daymade-skills
  209. # Ghostty terminal session snapshot/restore
  210. claude plugin install ghostty-use@daymade-skills
  211. # Repomix extraction
  212. claude plugin install repomix-unmixer@daymade-skills
  213. # AI/LLM icons
  214. claude plugin install llm-icon-finder@daymade-skills
  215. # CLI demo generation
  216. claude plugin install cli-demo-generator@daymade-skills
  217. # Cloudflare diagnostics
  218. claude plugin install cloudflare-troubleshooting@daymade-skills
  219. # UI design system extraction
  220. claude plugin install ui-designer@daymade-skills
  221. # YouTube video/audio downloading
  222. claude plugin install youtube-downloader@daymade-skills
  223. # Secure repomix packaging
  224. claude plugin install repomix-safe-mixer@daymade-skills
  225. # Full audio suite (ASR + transcript correction + meeting minutes + TTS)
  226. claude plugin install daymade-audio@daymade-skills
  227. # Video comparison and quality analysis
  228. claude plugin install video-comparer@daymade-skills
  229. # QA testing infrastructure with autonomous execution
  230. claude plugin install qa-expert@daymade-skills
  231. # Prompt optimization using EARS methodology
  232. claude plugin install prompt-optimizer@daymade-skills
  233. # CCPM skill registry search and management
  234. claude plugin install daymade-skill@daymade-skills
  235. # Promptfoo LLM evaluation framework
  236. claude plugin install promptfoo-evaluation@daymade-skills
  237. # Twitter/X content fetching
  238. claude plugin install twitter-reader@daymade-skills
  239. # Skill quality review and improvement
  240. claude plugin install daymade-skill@daymade-skills
  241. # GitHub contribution strategy
  242. claude plugin install github-contributor@daymade-skills
  243. # Windows Remote Desktop / AVD connection diagnosis
  244. claude plugin install windows-remote-desktop-connection-doctor@daymade-skills
  245. # Product analysis and optimization
  246. claude plugin install product-analysis@daymade-skills
  247. # Scrapling CLI extraction and troubleshooting
  248. claude plugin install scrapling-skill@daymade-skills
  249. # Tencent IMA knowledge base companion and installer
  250. claude plugin install ima-copilot@daymade-skills
  251. # Export Douban (豆瓣) book/movie/music/game collections to CSV
  252. claude plugin install douban-skill@daymade-skills
  253. # Terraform operational traps and multi-environment reliability patterns
  254. claude plugin install terraform-skill@daymade-skills
  255. # Evaluate any LLM endpoint across speed, concurrency, protocol, and quality
  256. claude plugin install llm-eval-harness@daymade-skills
  257. # Video/GIF memes with motion-tracked image overlays
  258. claude plugin install meme-creator@daymade-skills
  259. ```
  260. Standalone plugins can be installed independently; suite members install together with their suite.
  261. ---
  262. ## 🇨🇳 Chinese User Guide
  263. **For Chinese users:** We highly recommend using [CC-Switch](https://github.com/farion1231/cc-switch) to manage Claude Code API provider configurations.
  264. CC-Switch enables you to:
  265. - ✅ Quickly switch between different API providers (DeepSeek, Qwen, GLM, etc.)
  266. - ✅ Test endpoint response times to find the fastest provider
  267. - ✅ Manage MCP server configurations
  268. - ✅ Auto-backup and import/export settings
  269. - ✅ Cross-platform support (Windows, macOS, Linux)
  270. **Setup:** Download from [Releases](https://github.com/farion1231/cc-switch/releases), install, add your API configs, and switch via UI or system tray.
  271. ### Complete Chinese Documentation
  272. For full documentation in Chinese, see [README.zh-CN.md](./README.zh-CN.md).
  273. ---
  274. ## 📦 Other Available Skills
  275. ### **github-ops** - GitHub Operations Suite
  276. GitHub operations through gh CLI and GitHub APIs, with explicit targets, impact previews, and
  277. independent state verification.
  278. **When to use:**
  279. - Creating, viewing, or managing pull requests
  280. - Managing issues and repository settings
  281. - Managing collaborators, teams, organization permissions, and 2FA enforcement
  282. - Querying GitHub API endpoints
  283. - Working with GitHub Actions workflows
  284. - Automating GitHub operations
  285. **Key features:**
  286. - Verified mutation workflow for PRs, issues, repositories, and Actions
  287. - Parallel and superseded PR convergence
  288. - Organization access, member privileges, and 2FA preflight
  289. - REST, GraphQL, and documented UI-path selection
  290. - Enterprise GitHub support
  291. **🎬 Live Demo**
  292. ![GitHub Ops Demo](./demos/github-ops/create-pr.gif)
  293. ---
  294. ### **docs-router** - Daymade Document Routing
  295. > **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:docs-router`)
  296. Selects the bundled specialist for document conversion, Word and PDF production,
  297. Mermaid images, macOS Excel automation, scanned PDFs, DOCX review extraction, or
  298. documentation cleanup. It reads the selected specialist's full instructions and
  299. required references. Specialist slash commands remain available for manual use.
  300. For the retained PPT command, read the [compatibility notice](./daymade-docs/ppt-creator/SKILL.md).
  301. ---
  302. ### **doc-to-markdown** - Document Conversion Suite
  303. > **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:doc-to-markdown`)
  304. Converts documents to markdown with Windows/WSL path handling and PDF image extraction.
  305. **When to use:**
  306. - Converting .doc/.docx/PDF/PPTX to markdown
  307. - Converting saved HTML/HTM with source-link checks and explicit heading offsets
  308. - Extracting images from PDF files
  309. - Processing Confluence exports
  310. - Handling Windows/WSL path conversions
  311. **Key features:**
  312. - Multi-format document conversion
  313. - PDF image extraction using PyMuPDF
  314. - Windows/WSL path automation
  315. - Confluence export processing
  316. - Helper scripts for path conversion and image extraction
  317. ---
  318. ### **mermaid-tools** - Diagram Generation
  319. > **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:mermaid-tools`)
  320. Extracts Mermaid diagrams from markdown and generates high-quality PNG images.
  321. **When to use:**
  322. - Converting Mermaid diagrams to PNG
  323. - Extracting diagrams from markdown files
  324. - Processing documentation with embedded diagrams
  325. - Creating presentation-ready visuals
  326. **Key features:**
  327. - Automatic diagram extraction
  328. - High-resolution PNG generation
  329. - Smart sizing based on diagram type
  330. - Customizable dimensions and scaling
  331. - WSL2 Chrome/Puppeteer support
  332. **🎬 Live Demo**
  333. ![Mermaid Tools Demo](./demos/mermaid-tools/extract-diagrams.gif)
  334. ---
  335. ### **claude-code-ops-router** - Claude Code Setup Router
  336. > **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:claude-code-ops-router`)
  337. Routes plugin and Skill repair, marketplace work, statusline, model profiles and source sync, 1M context-window repair, usage and quota timers, memory migration, and exported `.txt` repair to one bundled specialist. The selected Skill's full instructions are read at use time; its original slash command remains available for manual use.
  338. ---
  339. ### **statusline-generator** - Statusline Customization
  340. > **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:statusline-generator`)
  341. Configures Claude Code statuslines with multi-line layouts and cost tracking.
  342. **When to use:**
  343. - Customizing Claude Code statusline
  344. - Adding cost tracking (session/daily)
  345. - Displaying git status
  346. - Multi-line layouts for narrow screens
  347. - Color customization
  348. **Key features:**
  349. - Multi-line statusline layouts
  350. - ccusage cost integration
  351. - Git branch status indicators
  352. - Customizable colors
  353. - Portrait screen optimization
  354. **🎬 Live Demo**
  355. ![Statusline Generator Demo](./demos/statusline-generator/customize-statusline.gif)
  356. ---
  357. ### **teams-channel-post-writer** - Teams Communication
  358. Creates educational Teams channel posts for internal knowledge sharing.
  359. **When to use:**
  360. - Writing Teams posts about features
  361. - Sharing Claude Code best practices
  362. - Documenting lessons learned
  363. - Creating internal announcements
  364. - Teaching effective prompting patterns
  365. **Key features:**
  366. - Post templates with proven structure
  367. - Writing guidelines for quality content
  368. - "Normal vs Better" example patterns
  369. - Emphasis on underlying principles
  370. - Ready-to-use markdown templates
  371. **🎬 Live Demo**
  372. ![Teams Channel Post Writer Demo](./demos/teams-channel-post-writer/write-post.gif)
  373. ---
  374. ### **peer-message** - Local Claude/Codex Agent Communication
  375. Follow the [local coordination workflow](peer-message/references/local-coordination.md)
  376. for task/resource declarations, native preflight installation, recovery and receiver checks.
  377. An experimental [paired-network route](peer-message/references/network-preview.md) adds invitations and cited answers from owner-selected documents through existing Claude/Codex hosts. It requires an operator-provided relay; the public hosted network and user-adoption claims are not part of this preview.
  378. > **Install**: `claude plugin install peer-message@daymade-skills`
  379. Follow the [routing contract](peer-message/SKILL.md) for native communication and transport gaps.
  380. **When to use:**
  381. - Sending a dependency, pause, handoff, or completion notice to an independently identified target outside the current native tools' scope
  382. - Finding replies to a specific coordination message without manually inspecting local message stores
  383. - Reaching a Claude inbox from a script or another product when native tools do not cover it; a third-party provider alone is not a reason to use the fallback
  384. - Unblocking messages held for per-message manual approval on an unattended endpoint (`crossSessionInbound`)
  385. - An inbound peer message asserting facts about your session or shared state, or asking you to pause/release — verify the premise against its own authority before acting
  386. - Another session's uncommitted edits, lock, or branch is in your way on a shared checkout — verify it is live, then ask the owner before waiting or working around it
  387. - Broadcasting one explicit coordination message to a reviewed target list
  388. 📚 [Execution entry and detailed SOPs](./peer-message/SKILL.md).
  389. ---
  390. ### **repomix-unmixer** - Repository Extraction
  391. Extracts files from repomix-packed repositories and restores directory structures.
  392. **When to use:**
  393. - Unmixing repomix output files
  394. - Extracting packed repositories
  395. - Restoring file structures
  396. - Reviewing repomix content
  397. - Converting repomix to usable files
  398. **Key features:**
  399. - Multi-format support (XML, Markdown, JSON)
  400. - Auto-format detection
  401. - Directory structure preservation
  402. - UTF-8 encoding support
  403. - Comprehensive validation workflows
  404. **🎬 Live Demo**
  405. ![Repomix Unmixer Demo](./demos/repomix-unmixer/extract-repo.gif)
  406. ---
  407. ### **llm-icon-finder** - AI/LLM Brand Icon Finder
  408. Access 100+ AI model and LLM provider brand icons from lobe-icons library.
  409. **When to use:**
  410. - Finding brand icons for AI models/providers
  411. - Downloading logos for Claude, GPT, Gemini, etc.
  412. - Getting icons in multiple formats (SVG/PNG/WEBP)
  413. - Building AI tool documentation
  414. - Creating presentations about LLMs
  415. **Key features:**
  416. - 100+ AI/LLM model icons
  417. - Multiple format support (SVG, PNG, WEBP)
  418. - URL generation for direct access
  419. - Local download capabilities
  420. - Searchable icon catalog
  421. **🎬 Live Demo**
  422. ![LLM Icon Finder Demo](./demos/llm-icon-finder/find-icons.gif)
  423. ---
  424. ### **cli-demo-generator** - CLI Demo Generation
  425. Generate professional animated CLI demos and terminal recordings with VHS automation.
  426. **When to use:**
  427. - Creating demos for documentation
  428. - Recording terminal workflows as GIFs
  429. - Generating animated tutorials
  430. - Batch-generating multiple demos
  431. - Showcasing CLI tools
  432. **Key features:**
  433. - Automated demo generation from command lists
  434. - Batch processing with YAML/JSON configs
  435. - Interactive recording with asciinema
  436. - Smart timing based on command complexity
  437. - Multiple output formats (GIF, MP4, WebM)
  438. - VHS tape file templates
  439. **🎬 Live Demo**
  440. ![CLI Demo Generator Demo](./demos/cli-demo-generator/generate-demo.gif)
  441. ---
  442. ### **cloudflare-troubleshooting** - Cloudflare Diagnostics
  443. Investigate and resolve Cloudflare configuration issues using API-driven evidence gathering.
  444. **When to use:**
  445. - Site shows ERR_TOO_MANY_REDIRECTS
  446. - SSL/TLS configuration errors
  447. - DNS resolution problems
  448. - Email Routing aliases, destination verification and forwarding delivery
  449. - Cloudflare-related issues
  450. **Key features:**
  451. - Evidence-based investigation methodology
  452. - Comprehensive Cloudflare API reference
  453. - SSL/TLS mode troubleshooting (Flexible, Full, Strict)
  454. - DNS, cache, and firewall diagnostics
  455. - Agentic approach with optional helper scripts
  456. ---
  457. ### **ui-designer** - UI Design System Extractor
  458. Extract design systems from reference UI images and generate implementation-ready design prompts.
  459. **When to use:**
  460. - Have UI screenshots/mockups to analyze
  461. - Need to extract color palettes, typography, spacing
  462. - Building MVP UI matching reference aesthetics
  463. - Creating consistent design systems
  464. - Generating multiple UI variations
  465. **Key features:**
  466. - Systematic design system extraction from images
  467. - Color palette, typography, component analysis
  468. - Interactive MVP PRD generation
  469. - Template-driven workflow (design system → PRD → implementation prompt)
  470. - Multi-variation UI generation (3 mobile, 2 web)
  471. - React + Tailwind CSS + Lucide icons
  472. **🎬 Live Demo**
  473. ![UI Designer Demo](./demos/ui-designer/extract-design-system.gif)
  474. ---
  475. ### **ppt-creator** - Compatibility Notice
  476. Read the [retirement and installation-compatibility notice](./daymade-docs/ppt-creator/SKILL.md)
  477. before using the legacy `daymade-docs:ppt-creator` command.
  478. ---
  479. ### **youtube-downloader** - YouTube Video & Audio Downloader
  480. Download YouTube videos and audio using yt-dlp with robust error handling and automatic workarounds for common issues.
  481. For spoken-content text, reuse existing transcripts first, then fetch original subtitles; download audio for ASR only when those checked routes miss. File-download requests keep the existing workflow.
  482. **When to use:**
  483. - Downloading YouTube videos or playlists
  484. - Extracting audio from YouTube videos as MP3
  485. - Experiencing yt-dlp download failures or nsig extraction errors
  486. - Need help with format selection or quality options
  487. - Working with YouTube content in regions with access restrictions
  488. **Key features:**
  489. - Native yt-dlp clients first; optional PO Token setup after an explicit token diagnostic
  490. - Browser-cookie verification for “not a bot” prompts (privacy-friendly)
  491. - Audio-only download with MP3 conversion
  492. - Format listing and custom format selection
  493. - Output directory customization
  494. - Proxy-aware downloads for restricted environments
  495. **🎬 Live Demo**
  496. ![YouTube Downloader Demo](./demos/youtube-downloader/download-video.gif)
  497. ---
  498. ### **repomix-safe-mixer** - Secure Repomix Packaging
  499. Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing.
  500. **When to use:**
  501. - Packaging code with repomix for distribution or sharing
  502. - Creating reference packages from proprietary codebases
  503. - Security concerns about accidentally exposing credentials
  504. - Pre-commit security checks for hardcoded secrets
  505. - Auditing codebases for credential exposure
  506. **Key features:**
  507. - Detects 20+ credential patterns (AWS, Supabase, Stripe, OpenAI, etc.)
  508. - Scan → Report → Pack workflow with automatic blocking
  509. - Standalone security scanner for pre-commit hooks
  510. - Environment variable replacement guidance
  511. - JSON output for CI/CD integration
  512. - Exclude patterns for false positive handling
  513. **🎬 Live Demo**
  514. *Coming soon*
  515. ---
  516. ### **transcript-fixer** - ASR Transcription Correction
  517. > **Install**: `claude plugin install daymade-audio@daymade-skills` (suite-only — invoked as `daymade-audio:transcript-fixer`)
  518. Correct speech-to-text (ASR/STT) errors with a Stage 1 dictionary pre-filter, a required Native AI whole-transcript pass, and evidence-based review of unresolved wording, names, numbers, and entities.
  519. **When to use:**
  520. - Correcting meeting notes, lecture recordings, or interview transcripts
  521. - Fixing Chinese/English homophone errors and technical terminology
  522. - Reviewing one exact transcript's unresolved items with available evidence instead of searching a global queue
  523. - Improving future transcripts without turning one-off fixes into broad dictionary rules
  524. - Collaborating with teams on shared correction knowledge bases
  525. **Key features:**
  526. - Stage 1 + Native AI correction pipeline; Stage 1 alone is never completion
  527. - Frozen review packets and checked file/segment coverage for split or resumed Native reviews; malformed results stay unready and valid work can be reused
  528. - Exact-file review queue, deep-linked dashboard, timestamped audio playback, and machine-readable zero-pending readback
  529. - Conservative pattern learning: file-only, dictionary, roster, and context have separate admission rules
  530. - Domain-specific dictionaries (general, embodied_ai, finance, medical)
  531. - SQLite-based correction repository
  532. - Team collaboration with import/export
  533. - Optional [versioned Stage 1 history](daymade-audio/transcript-fixer/references/historical_stage1.md) with shared-source refresh and guarded preservation of manual file edits
  534. - GLM API integration for AI corrections
  535. - Cost optimization through dictionary promotion
  536. **Example workflow:**
  537. ```bash
  538. # Initialize and add corrections
  539. uv run scripts/fix_transcription.py --init
  540. uv run scripts/fix_transcription.py --add "错误词" "正确词" --domain general
  541. # Run Stage 1
  542. uv run scripts/fix_transcription.py --input meeting.md --stage 1
  543. # Next, load transcript-fixer and complete the Native AI whole-transcript pass.
  544. # Resolve remaining pending items from available evidence; use audio when available.
  545. uv run scripts/review-dashboard/server.py --file "/absolute/meeting.md"
  546. # Read back the review state; pending_total must be 0 before final delivery
  547. uv run scripts/fix_transcription.py \
  548. --list-review --review-file "/absolute/meeting.md" \
  549. --review-status all --json
  550. ```
  551. 📚 **Documentation**: See [daymade-audio/transcript-fixer/references/](./daymade-audio/transcript-fixer/references/) for workflow guides, SQL queries, troubleshooting, best practices, team collaboration, and API setup.
  552. **Requirements**: Python 3.10+ and uv. Native AI correction uses the active agent; an external API key is needed only for the optional agent-less API route.
  553. ---
  554. ### **video-comparer** - Video Comparison and Quality Analysis
  555. Compare two videos and generate interactive HTML reports with quality metrics and frame-by-frame visual comparisons.
  556. **When to use:**
  557. - Comparing original and compressed videos
  558. - Analyzing video compression quality and efficiency
  559. - Evaluating codec performance or bitrate reduction impact
  560. - Assessing before/after compression results
  561. - Quality analysis for video encoding workflows
  562. **Key features:**
  563. - Quality metrics calculation (PSNR, SSIM)
  564. - Frame-by-frame visual comparison with three viewing modes:
  565. - Slider mode: Drag to reveal differences
  566. - Side-by-side mode: Simultaneous display
  567. - Grid mode: Compact 2-column layout
  568. - Video metadata extraction (codec, resolution, bitrate, duration, file size)
  569. - Self-contained HTML reports (no server required, works offline)
  570. - Security features (path validation, resource limits, timeout controls)
  571. - Multi-platform FFmpeg support (macOS, Linux, Windows)
  572. **Example usage:**
  573. ```bash
  574. # Basic comparison
  575. python3 scripts/compare.py original.mp4 compressed.mp4
  576. # Custom output and frame interval
  577. python3 scripts/compare.py original.mp4 compressed.mp4 -o report.html --interval 10
  578. # Batch processing
  579. for original in originals/*.mp4; do
  580. compressed="compressed/$(basename "$original")"
  581. output="reports/$(basename "$original" .mp4).html"
  582. python3 scripts/compare.py "$original" "$compressed" -o "$output"
  583. done
  584. ```
  585. **🎬 Live Demo**
  586. *Coming soon*
  587. 📚 **Documentation**: See [video-comparer/references/](./video-comparer/references/) for quality metrics interpretation, FFmpeg commands, and configuration options.
  588. **Requirements**: Python 3.8+, FFmpeg/FFprobe (install via `brew install ffmpeg`, `apt install ffmpeg`, or `winget install ffmpeg`)
  589. ---
  590. ### **qa-expert** - QA Test Planning, Execution & Reporting
  591. Set up test cases, execution tracking, bug reports and QA handoffs using AAA test structure and OWASP security categories.
  592. **When to use:**
  593. - Setting up QA infrastructure for new or existing projects
  594. - Writing standardized test cases following Google Testing Standards (AAA pattern)
  595. - Implementing security testing (OWASP Top 10 coverage)
  596. - Executing comprehensive test plans with automatic progress tracking
  597. - Filing bugs with proper P0-P4 severity classification
  598. - Calculating quality metrics and assessing project release criteria
  599. - Enabling autonomous LLM-driven test execution
  600. - Preparing QA documentation for third-party team handoffs
  601. **Key features:**
  602. - **One-command initialization**: QA directories, templates and example CSVs
  603. - **Autonomous execution**: Follow the approved project plan with result tracking and bug reports
  604. - **Runtime compatibility**: Compare adapter outputs with the target runtime's actual semantics and distinguish modeled inputs from native execution
  605. - **Release acceptance**: Apply the project's release policy; an overall pass rate does not override a failed critical user task
  606. - **Ground Truth Principle**: Prevents doc/CSV sync issues (test docs = authoritative source)
  607. - **Bug tracking**: P0-P4 classification with detailed repro steps and environment info
  608. - **Onboarding**: Guide for new QA engineers
  609. - **LLM prompts**: Ready-to-use prompts for specific QA tasks
  610. - **Metrics report**: Test execution progress, pass rate, linked bugs and built-in check results
  611. **Example usage:**
  612. ```bash
  613. # Resolve qa-expert-dir from the loaded Skill; use a fresh project root
  614. uv run "<qa-expert-dir>/scripts/init_qa_project.py" my-app "<project-root>"
  615. # Report metrics after test execution
  616. uv run "<qa-expert-dir>/scripts/calculate_metrics.py" "<project-root>/tests/docs/templates/TEST-EXECUTION-TRACKING.csv"
  617. ```
  618. Initialization creates templates. Before execution, replace example rows, supply test specifications and verify the project harness. Follow [the execution SOP](./qa-expert/references/master_qa_prompt.md) for preparation, recovery and handoff. The metrics command reports results; it does not decide release acceptance.
  619. 📚 **Documentation**: Start with [qa-expert](./qa-expert/SKILL.md) for test selection, execution and reporting.
  620. **Requirements**: Python 3.8+, uv
  621. ---
  622. ### **prompt-optimizer** - Prompt Engineering with EARS Methodology
  623. Transform vague prompts into precise, well-structured specifications using EARS (Easy Approach to Requirements Syntax) - a methodology created by Rolls-Royce for converting natural language into testable requirements.
  624. **Methodology inspired by:** [阿星AI工作室 (A-Xing AI Studio)](https://mp.weixin.qq.com/s/yUVX-9FovSq7ZGChkHpuXQ), which pioneered combining EARS with domain theory grounding for practical prompt enhancement.
  625. **When to use:**
  626. - Converting loose requirements into structured specifications
  627. - Optimizing prompts for AI code generation or content creation
  628. - Breaking down vague feature requests into atomic, testable statements
  629. - Adding domain theory grounding to technical requirements
  630. - Transforming "build X" requests into detailed implementation specs
  631. - Learning prompt engineering best practices with proven frameworks
  632. **Key features:**
  633. - **EARS transformation**: 5 sentence patterns (ubiquitous, event-driven, state-driven, conditional, unwanted behavior)
  634. - **6-step optimization workflow**: Analyze → Transform → Identify theories → Extract examples → Enhance → Present
  635. - **Domain theory catalog**: 40+ frameworks mapped to 10 domains (productivity, UX, gamification, learning, e-commerce, security)
  636. - **Structured prompt framework**: Role/Skills/Workflows/Examples/Formats template
  637. - **Advanced techniques**: Multi-stakeholder requirements, non-functional specs, complex conditional logic
  638. - **Complete examples**: Procrastination app, e-commerce product page, learning dashboard, password reset
  639. - **Theory grounding**: GTD, BJ Fogg Behavior Model, Gestalt Principles, AIDA, Zero Trust, and more
  640. - **Progressive disclosure**: Bundled references (ears_syntax.md, domain_theories.md, examples.md)
  641. **Example usage:**
  642. ```markdown
  643. # Before (vague)
  644. "Build me a password reset feature"
  645. # After EARS transformation (7 atomic requirements)
  646. 1. When user clicks "Forgot Password", the system shall display email input field
  647. 2. When user submits valid email, the system shall send password reset link valid for 1 hour
  648. 3. When user clicks reset link, the system shall verify token has not expired
  649. 4. When token is valid, the system shall display password creation form requiring minimum 12 characters, 1 uppercase, 1 number, 1 special character
  650. 5. When user submits new password meeting requirements, the system shall hash password with bcrypt and invalidate reset token
  651. 6. When user attempts password reset more than 3 times in 1 hour, the system shall block further attempts for 1 hour
  652. 7. If reset token has expired, the system shall display error message and option to request new link
  653. # Enhanced with domain theories
  654. - Zero Trust Architecture (verify at each step)
  655. - Defense in Depth (rate limiting + token expiration + password complexity)
  656. - Progressive Disclosure (multi-step UX flow)
  657. # Full prompt includes Role, Skills, Workflows, Examples, Formats
  658. ```
  659. **🎬 Live Demo**
  660. *Coming soon*
  661. 📚 **Documentation**: See [prompt-optimizer/references/](./prompt-optimizer/references/) for:
  662. - `ears_syntax.md` - Complete EARS patterns and transformation rules
  663. - `domain_theories.md` - 40+ theories mapped to domains with selection guidance
  664. - `examples.md` - Full transformation examples with before/after comparisons
  665. **💡 Innovation**: EARS methodology eliminates ambiguity by forcing explicit conditions, triggers, and measurable criteria. Combined with domain theory grounding (GTD, BJ Fogg, Gestalt, etc.), it transforms "build a todo app" into a complete specification with behavioral psychology principles, UX best practices, and concrete test cases - enabling test-driven development from day one.
  666. ---
  667. ### **local-conversation-history** - Cross-Provider History Entry Point
  668. > **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:local-conversation-history`)
  669. See the [Skill's usage and routing contract](daymade-claude-code/local-conversation-history/SKILL.md)
  670. for history recall, interrupted work and conversation-backup health checks.
  671. ---
  672. ### **read-claude-code-history** - Read Local Claude Code History
  673. > **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:read-claude-code-history`)
  674. Inspect prior work without resuming the old task. Start with the
  675. [result router](./daymade-claude-code/read-claude-code-history/SKILL.md#route-by-the-requested-result)
  676. for the current workflow, prerequisites and coverage limits.
  677. **Choose the requested result:**
  678. - Unknown Session or remembered topic: [indexed discovery](./daymade-claude-code/read-claude-code-history/SKILL.md#indexed-content-search)
  679. - Known Session: [chronological evidence](./daymade-claude-code/read-claude-code-history/SKILL.md#exact-session-evidence)
  680. - Original command and its receipt: [tool call/result evidence](./daymade-claude-code/read-claude-code-history/SKILL.md#original-tool-callresult-evidence)
  681. - Verbatim human wording: [human-input export](./daymade-claude-code/read-claude-code-history/SKILL.md#human-input-export)
  682. - Deleted or overwritten files: [recovery workflow](./daymade-claude-code/read-claude-code-history/SKILL.md#deleted-content-recovery)
  683. Use the commands in those entries rather than a separate README recipe.
  684. ---
  685. ### **docs-cleaner** - Documentation Consolidation
  686. > **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:docs-cleaner`)
  687. Consolidate redundant documentation while preserving all valuable content.
  688. **When to use:**
  689. - Cleaning up documentation bloat across projects
  690. - Merging redundant docs covering the same topics
  691. - Reducing documentation sprawl after rapid development
  692. - Consolidating multiple files into authoritative sources
  693. **Key features:**
  694. - **Content preservation**: Never lose valuable information during cleanup
  695. - **Redundancy detection**: Identify overlapping documentation
  696. - **Smart merging**: Combine related docs while maintaining structure
  697. - **Validation**: Ensure consolidated docs are complete and accurate
  698. **🎬 Live Demo**
  699. *Coming soon*
  700. ---
  701. ### **skills-search** - Local Repositories and CCPM Search
  702. Find Skills in configurable local repositories first, then approved sources and the CCPM registry. Preserve existing CCPM installation and management commands.
  703. **When to use:**
  704. - Finding skills for specific tasks (e.g., "find PDF skills")
  705. - Installing skills by name
  706. - Listing currently installed skills
  707. - Getting detailed information about a skill
  708. - Managing your Claude Code skill collection
  709. **Key features:**
  710. - **Local-first discovery**: Persist repository paths and trust tiers outside the Skill package; inspect every configured owned source before expanding
  711. - **Progressive reading**: Search cached name/description metadata, then open the selected Skill at its exact Git commit
  712. - **Registry search**: Search CCPM registry with `ccpm search <query>`
  713. - **Skill installation**: Install skills with `ccpm install <skill-name>`
  714. - **Version support**: Install specific versions with `@version` syntax
  715. - **Bundle installation**: Install pre-configured skill bundles (web-dev, content-creation, developer-tools)
  716. - **Multiple formats**: Supports registry names, GitHub owner/repo, and full URLs
  717. - **Skill info**: Get detailed skill information with `ccpm info <skill-name>`
  718. **Example usage:**
  719. ```bash
  720. # Search configured local repositories first (<skill-dir> is this loaded Skill)
  721. uv run --script <skill-dir>/scripts/local_sources.py search pdf --tier owned
  722. # Expand to the external registry when needed
  723. ccpm search pdf # Find PDF-related skills
  724. ccpm search "code review" # Find code review skills
  725. # Install skills
  726. ccpm install skill-creator # From registry
  727. ccpm install daymade/skill-creator # From GitHub
  728. ccpm install skill-creator@1.0.0 # Specific version
  729. # List and manage
  730. ccpm list # List installed skills
  731. ccpm info skill-creator # Get skill details
  732. ccpm uninstall pdf-processor # Remove a skill
  733. # Install bundles
  734. ccpm install-bundle web-dev # Install web development skills bundle
  735. ```
  736. **🎬 Live Demo**
  737. *Coming soon*
  738. 📚 **Documentation**: See [daymade-skill/skills-search/SKILL.md](./daymade-skill/skills-search/SKILL.md) for configuration, coverage and commands
  739. **Requirements**: Python 3.10+, Git and uv for local search; CCPM CLI only for external registry/install/manage operations
  740. ---
  741. ### **pdf-creator** - PDF Creation with Chinese Font Support
  742. > **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:pdf-creator`)
  743. Create professional PDF documents from markdown with proper Chinese typography using WeasyPrint.
  744. **When to use:**
  745. - Converting markdown to PDF for sharing or printing
  746. - Generating formal documents (legal filings, reports)
  747. - Ensuring correct Chinese font rendering
  748. **Key features:**
  749. - pandoc + WeasyPrint conversion pipeline (dual backend: WeasyPrint or headless Chrome)
  750. - Built-in Chinese/Japanese/Korean (CJK) font fallbacks with auto CJK code-block rendering
  751. - Theme system (default for formal docs, cjk-auto for content-driven tables, warm-terra for training materials, mobile for phone reading)
  752. - A4 layout defaults with print-friendly margins
  753. - Batch conversion scripts
  754. **Example usage:**
  755. ```bash
  756. uv run --with weasyprint scripts/md_to_pdf.py input.md output.pdf
  757. ```
  758. **🎬 Live Demo**
  759. *Coming soon*
  760. 📚 **Documentation**: See [daymade-docs/pdf-creator/SKILL.md](./daymade-docs/pdf-creator/SKILL.md) for setup and workflow details.
  761. **Requirements**: Python 3.8+, `pandoc` (system install), `weasyprint` (or Chrome as fallback backend)
  762. ---
  763. ### **claude-md-progressive-disclosurer** - CLAUDE.md Optimization
  764. > **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:claude-md-progressive-disclosurer`)
  765. Optimize user CLAUDE.md files using progressive disclosure to reduce context bloat while preserving critical rules.
  766. **When to use:**
  767. - CLAUDE.md is too long or repetitive
  768. - Need to move detailed procedures into references
  769. - Want to extract reusable workflows into skills
  770. **Key features:**
  771. - Section classification (keep/move/extract/remove)
  772. - Before/after line-count reporting
  773. - Reference file and pointer formats
  774. - Best-practice optimization workflow
  775. **Example usage:**
  776. ```
  777. "Optimize my ~/.claude/CLAUDE.md using progressive disclosure and propose a plan."
  778. ```
  779. **🎬 Live Demo**
  780. *Coming soon*
  781. 📚 **Documentation**: See [claude-md-progressive-disclosurer/SKILL.md](./daymade-claude-code/claude-md-progressive-disclosurer/SKILL.md).
  782. ---
  783. ### **promptfoo-evaluation** - Promptfoo LLM Evaluation
  784. Configure and run LLM evaluations with Promptfoo for prompt testing and model comparisons.
  785. **When to use:**
  786. - Setting up prompt tests and eval configs
  787. - Comparing LLM outputs across providers
  788. - Adding custom assertions or LLM-as-judge grading
  789. **Key features:**
  790. - promptfooconfig.yaml templates
  791. - Python custom assertions
  792. - llm-rubric scoring guidance
  793. - Built-in preview (echo provider) workflows
  794. **Example usage:**
  795. ```bash
  796. npx promptfoo@latest init
  797. npx promptfoo@latest eval
  798. npx promptfoo@latest view
  799. ```
  800. **🎬 Live Demo**
  801. *Coming soon*
  802. 📚 **Documentation**: See [promptfoo-evaluation/references/promptfoo_api.md](./promptfoo-evaluation/references/promptfoo_api.md).
  803. **Requirements**: Node.js (Promptfoo via `npx promptfoo@latest`)
  804. ---
  805. ### **developing-ios-apps** - iOS App Development
  806. > **Install**: `claude plugin install daymade-macos@daymade-skills` (suite-only — invoked as `daymade-macos:developing-ios-apps`)
  807. Build, configure, and debug iOS apps with XcodeGen, SwiftUI, and Swift Package Manager.
  808. **When to use:**
  809. - Setting up XcodeGen `project.yml`
  810. - Fixing SPM dependency or embed issues
  811. - Handling code signing and device deployment errors
  812. - Debugging camera/AVFoundation problems
  813. **Key features:**
  814. - XcodeGen project templates
  815. - SPM dynamic framework embedding fixes
  816. - Code signing and provisioning guidance
  817. - Device deployment and troubleshooting checklists
  818. **Example usage:**
  819. ```bash
  820. xcodegen generate
  821. xcodebuild -destination 'platform=iOS Simulator,name=iPhone 17' build
  822. ```
  823. **🎬 Live Demo**
  824. *Coming soon*
  825. 📚 **Documentation**: See [developing-ios-apps/references/xcodegen-full.md](./daymade-macos/developing-ios-apps/references/xcodegen-full.md).
  826. **Requirements**: macOS + Xcode, XcodeGen
  827. ---
  828. ### **twitter-reader** - Twitter/X Content Fetching
  829. Fetch Twitter/X post and article content. Single-post text goes through the
  830. fxtwitter mirror API (login-free, key-free, full long-form body); X Articles
  831. with images go through `fetch_article.py`; the Jina API path remains as a
  832. fallback with a known intermittent-ban risk.
  833. **When to use:**
  834. - Retrieving tweet content for analysis or documentation
  835. - Fetching X Articles (long-form) with all images downloaded locally
  836. - Extracting images and media from posts
  837. - Batch downloading multiple tweets for reference
  838. **Key features:**
  839. - Single posts: fxtwitter mirror — no key, no login, full `tweet.text` body including note_tweet long-form
  840. - No JavaScript rendering or browser automation needed
  841. - No Twitter authentication required
  842. - Returns markdown-formatted content with metadata
  843. - Supports both individual and batch fetching
  844. - Includes author, timestamp, post text, images, and replies
  845. - Environment variable configuration for secure API key management
  846. **Example usage:**
  847. ```bash
  848. # Single post text (preferred): fxtwitter mirror, no key needed
  849. curl -sS "https://api.fxtwitter.com/USER/status/TWEET_ID" \
  850. | python3 -c "import json,sys; t=json.load(sys.stdin)['tweet']; print(t['text'])"
  851. # X Article with images (full mode)
  852. uv run --with pyyaml python scripts/fetch_article.py \
  853. "https://x.com/USER/status/TWEET_ID" ./Clippings
  854. # Jina fallback (intermittent — see SKILL.md risk note)
  855. export JINA_API_KEY="your_api_key_here"
  856. curl "https://r.jina.ai/https://x.com/USER/status/TWEET_ID" \
  857. -H "Authorization: Bearer ${JINA_API_KEY}"
  858. # Batch fetch multiple tweets
  859. scripts/fetch_tweets.sh \
  860. "https://x.com/user/status/123" \
  861. "https://x.com/user/status/456"
  862. # Fetch to file using Python script
  863. python scripts/fetch_tweet.py https://x.com/user/status/123 output.md
  864. ```
  865. **🎬 Live Demo**
  866. *Coming soon*
  867. 📚 **Documentation**: See [twitter-reader/SKILL.md](./twitter-reader/SKILL.md) for full details and URL format support.
  868. **Requirements**:
  869. - **curl** (pre-installed on most systems) — single-post path needs nothing else
  870. - **Python 3.6+** (for Python scripts)
  871. - **Jina.ai API key** (only for the Jina fallback; intermittent-ban risk, and the shared repo key is currently out of balance / 402)
  872. ---
  873. ### **macos-cleaner** - Intelligent macOS Disk Space Recovery
  874. > **Install**: `claude plugin install daymade-macos@daymade-skills` (suite-only — invoked as `daymade-macos:macos-cleaner`)
  875. 📚 **Documentation**: [macOS Cleaner](./daymade-macos/macos-cleaner/SKILL.md); for uv cache diagnosis or retirement, enter the Skill's [uv target semantics](./daymade-macos/macos-cleaner/references/cleanup_targets.md#uv-cache-retirement).
  876. **Example usage:**
  877. ```text
  878. My Mac is running out of space, help me analyze what's using storage
  879. ```
  880. ---
  881. ### **fact-checker** - Document Fact-Checking
  882. Verify factual claims in documents using web search and official sources, then propose corrections with user confirmation.
  883. **When to use:**
  884. - Fact-checking documents for accuracy
  885. - Verifying AI model specifications and technical documentation
  886. - Updating outdated information in documents
  887. - Validating statistical claims and benchmarks
  888. - Checking API capabilities and version numbers
  889. **Key features:**
  890. - Web search integration with authoritative sources
  891. - AI model specification verification
  892. - Technical documentation accuracy checks
  893. - Statistical data validation
  894. - Automated correction reports with user confirmation
  895. - Supports general factual statements and technical claims
  896. **Example usage:**
  897. ```bash
  898. # Install the skill
  899. claude plugin install fact-checker@daymade-skills
  900. # Fact-check a document
  901. "Please fact-check this section about AI model capabilities"
  902. # Verify technical specs
  903. "Check if these Claude model specifications are still accurate"
  904. # Update outdated info
  905. "Verify and update the version numbers in this documentation"
  906. ```
  907. **🎬 Live Demo**
  908. *Coming soon*
  909. 📚 **Documentation**: See [fact-checker/SKILL.md](./fact-checker/SKILL.md) for full workflow and claim types.
  910. **Requirements**:
  911. - Web search access (via Claude Code)
  912. ---
  913. ### **skill-reviewer** - Skill Quality Review & Improvement
  914. Review and improve Claude Code skills against official best practices with three powerful modes.
  915. **When to use:**
  916. - Validating your own skills before publishing
  917. - Evaluating others' skill repositories
  918. - Contributing improvements to open-source skills via auto-PR
  919. - Ensuring skills follow marketplace standards
  920. **Key features:**
  921. - **Self-review mode**: Run the bundled reviewer backed by canonical skill-creator validation
  922. - **External review mode**: Clone, analyze, and generate improvement reports
  923. - **Auto-PR mode**: Fork → improve → submit PR with additive-only changes
  924. - **Evaluation checklist**: Frontmatter, instructions, resources verification
  925. - **Additive-only principle**: Never delete files when contributing to others
  926. - **PR guidelines**: Tone recommendations and professional templates
  927. - **Reliable automation**: Distinguishes review findings from invocation/runtime failures with structured JSON output
  928. - **Evidence-based design review**: Score six dimensions with exact source citations; keep documented design quality separate from measured task benefit
  929. - **Read-only batch review**: Inventory collections against declared host contracts, prepare complete selected-source packets, and export JSON/CSV/Markdown with explicit coverage and invalid decisions quarantined
  930. **Example usage:**
  931. ```bash
  932. # Install the skill
  933. claude plugin install daymade-skill@daymade-skills
  934. # Self-review your skill
  935. "Validate my skill at ~/my-skills/my-awesome-skill"
  936. # Review external skill repository
  937. "Review the skills at https://github.com/user/skill-repo"
  938. # Auto-PR improvements
  939. "Fork, improve, and submit PR for https://github.com/user/skill-repo"
  940. ```
  941. **🎬 Live Demo**
  942. *Coming soon*
  943. 📚 **Documentation**: See [daymade-skill/skill-reviewer/references/](./daymade-skill/skill-reviewer/references/) for:
  944. - `evaluation_checklist.md` - Complete skill evaluation criteria
  945. - `pr_template.md` - Professional PR description template
  946. ---
  947. ### **github-contributor** - GitHub Contribution Strategy
  948. Strategic guide for becoming an effective GitHub contributor and building your open-source reputation.
  949. **When to use:**
  950. - Looking for projects to contribute to
  951. - Learning contribution best practices
  952. - Building your GitHub presence and reputation
  953. - Understanding how to write high-quality PRs
  954. **Key features:**
  955. - **Four contribution types**: Documentation, Code Quality, Bug Fixes, Features
  956. - **Project selection criteria**: What makes a good first project vs red flags
  957. - **PR excellence workflow**: Before → During → After submission checklist
  958. - **Reputation building ladder**: Documentation → Bug Fixes → Features → Maintainer
  959. - **GitHub CLI commands**: Quick reference for fork, PR, issue operations
  960. - **Conventional commit format**: Type, scope, description structure
  961. - **Common mistakes**: What to avoid and best practices
  962. **Contribution types explained:**
  963. ```
  964. Level 1: Documentation fixes (lowest barrier, high impact)
  965. ↓ (build familiarity)
  966. Level 2: Code quality (medium effort, demonstrates skill)
  967. ↓ (understand codebase)
  968. Level 3: Bug fixes (high impact, builds trust)
  969. ↓ (trusted contributor)
  970. Level 4: Feature additions (highest visibility)
  971. ↓ (potential maintainer)
  972. ```
  973. **Example usage:**
  974. ```bash
  975. # Install the skill
  976. claude plugin install github-contributor@daymade-skills
  977. # Find good first issues
  978. "Help me find projects with good first issues in Python"
  979. # Write a high-quality PR
  980. "Guide me through creating a PR for this bug fix"
  981. # Build contribution strategy
  982. "Help me plan a contribution strategy for building my GitHub profile"
  983. ```
  984. **🎬 Live Demo**
  985. *Coming soon*
  986. 📚 **Documentation**: See [github-contributor/references/](./github-contributor/references/) for:
  987. - `pr_checklist.md` - Complete PR quality checklist
  988. - `project_evaluation.md` - How to evaluate projects for contribution
  989. - `communication_templates.md` - Issue and PR communication templates
  990. ---
  991. ### **i18n-expert** - Internationalization & Localization
  992. Complete internationalization/localization setup and auditing for UI codebases. Configure i18n frameworks, replace hard-coded strings with translation keys, ensure locale parity between en-US and zh-CN, and validate pluralization and formatting.
  993. **When to use:**
  994. - Setting up i18n for new React/Next.js/Vue applications
  995. - Auditing existing i18n implementations for key parity and completeness
  996. - Replacing hard-coded strings with translation keys
  997. - Ensuring proper error code mapping to localized messages
  998. - Validating pluralization, date/time/number formatting across locales
  999. - Implementing language switching and SEO metadata localization
  1000. **Key features:**
  1001. - Library selection and setup (react-i18next, next-intl, vue-i18n)
  1002. - Key architecture and locale file organization (JSON, YAML, PO, XLIFF)
  1003. - Translation generation strategy (AI, professional, manual)
  1004. - Routing and language detection/switching
  1005. - SEO and metadata localization
  1006. - RTL support for applicable locales
  1007. - Key parity validation between en-US and zh-CN
  1008. - Pluralization and formatting validation
  1009. - Error code mapping to localized messages
  1010. - Bundled i18n_audit.py script for key usage extraction
  1011. **Example usage:**
  1012. ```bash
  1013. # Install the skill
  1014. claude plugin install i18n-expert@daymade-skills
  1015. # Setup i18n for a new project
  1016. "Set up i18n for my React app with English and Chinese support"
  1017. # Audit existing i18n implementation
  1018. "Audit the i18n setup and find missing translation keys"
  1019. # Replace hard-coded strings
  1020. "Replace all hard-coded strings in this component with i18n keys"
  1021. ```
  1022. **🎬 Live Demo**
  1023. *Coming soon*
  1024. 📚 **Documentation**: See [i18n-expert/SKILL.md](./i18n-expert/SKILL.md) for complete workflow and architecture guidance.
  1025. **Requirements**:
  1026. - **Python 3.6+** (for audit script)
  1027. - **React/Next.js/Vue** (framework-specific i18n library)
  1028. ---
  1029. ### **claude-skills-troubleshooting** - Plugin & Skill Troubleshooting
  1030. > **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:claude-skills-troubleshooting`)
  1031. Diagnose and resolve Claude Code plugin and skill configuration issues. Debug plugin installation, enablement, and activation problems with systematic workflows.
  1032. **When to use:**
  1033. - Plugins installed but not showing in available skills list
  1034. - Skills not activating as expected despite installation
  1035. - Troubleshooting enabledPlugins configuration in settings.json
  1036. - Debugging "plugin not working" or "skill not showing" issues
  1037. - Understanding plugin state architecture and lifecycle
  1038. **Key features:**
  1039. - Quick diagnosis via diagnostic script (detects installed vs enabled mismatch)
  1040. - Plugin state architecture documentation (installed_plugins.json vs settings.json)
  1041. - Marketplace cache freshness detection and update guidance
  1042. - Known GitHub issues tracking (#17832, #19696, #17089, #13543, #16260)
  1043. - Batch enable script for missing plugins from a marketplace
  1044. - Skills vs Commands architecture explanation
  1045. - Comprehensive diagnostic commands reference
  1046. **Example usage:**
  1047. ```bash
  1048. # Run diagnostic
  1049. python3 scripts/diagnose_plugins.py
  1050. # Batch enable missing plugins
  1051. python3 scripts/enable_all_plugins.py daymade-skills
  1052. ```
  1053. **🎬 Live Demo**
  1054. *Coming soon*
  1055. 📚 **Documentation**: See [claude-skills-troubleshooting/SKILL.md](./daymade-claude-code/claude-skills-troubleshooting/SKILL.md) for complete troubleshooting workflow and architecture guidance.
  1056. **Requirements**: None (uses Claude Code built-in Python)
  1057. ---
  1058. ### **audio-router** - StepFun Speech and Meeting-Minutes Routing
  1059. > **Install**: `claude plugin install daymade-audio@daymade-skills` (suite-only — invoked as `daymade-audio:audio-router`)
  1060. Selects the installed StepFun ASR, StepFun TTS, or transcript-to-minutes specialist and reads its full instructions at use time. Their original slash commands remain available manually. General audio transcription and transcript correction retain direct automatic entries.
  1061. ---
  1062. ### **meeting-minutes-taker** - Meeting Minutes Generator
  1063. > **Install**: `claude plugin install daymade-audio@daymade-skills` (suite-only — invoked as `daymade-audio:meeting-minutes-taker`)
  1064. 📚 [Canonical inputs, workflow, prerequisites and templates](./daymade-audio/meeting-minutes-taker/SKILL.md#quick-start).
  1065. ---
  1066. ### **deep-research** - Research Reports and Provider Runs
  1067. Generate research reports from a durable study record: original sources, claim-level citations, rejected leads, and prior studies remain available for the next question. When several AI products or modes investigate one decision, coordinate their existing Skills and agents in parallel, preserve original outputs, and synthesize against the underlying sources and business question.
  1068. **When to use:**
  1069. - Need a structured research report, literature review, or market/industry analysis
  1070. - Require strict section formatting or a template to be enforced
  1071. - Need evidence mapping, citations, and source quality review
  1072. - Want multi-pass synthesis to avoid missing key findings
  1073. **Key features:**
  1074. - Report spec and format contract workflow
  1075. - Evidence table with source quality rubric
  1076. - Multi-pass complete drafting with UNION merge
  1077. - Citation verification and conflict handling
  1078. - Project-local source and claim records for single-route and multi-route studies, with a searchable catalog for reuse
  1079. - Exact seed-document handoff, persistent session aliases, and verified-source-first catalog search
  1080. - Local provider × mode task and artifact ledger with provenance and hash checks
  1081. - Read-only parallel dispatch board that separates shared app control, active tasks, completed reports and held routes; actual provider calls follow their own Skills and authorization rules
  1082. - Ready-to-use report template and formatting rules
  1083. **Example usage:**
  1084. ```bash
  1085. # Install the skill
  1086. claude plugin install deep-research@daymade-skills
  1087. # Then provide a report spec or template and request a deep research report
  1088. ```
  1089. **🎬 Live Demo**
  1090. *Coming soon*
  1091. 📚 **Documentation**: See [deep-research/SKILL.md](./deep-research/SKILL.md), [research-asset-contract.md](./deep-research/references/research-asset-contract.md), and [research_report_template.md](./deep-research/references/research_report_template.md).
  1092. **Requirements**: None
  1093. ---
  1094. ### **competitors-analysis** - Evidence-Based Competitor Intelligence
  1095. Discover, clone, update, and analyze competitor repositories with evidence-based competitive intelligence. Repository-backed findings must come from local cloned code; market-landscape claims must cite their source and volatility.
  1096. **When to use:**
  1097. - Track and analyze competitor products or technologies
  1098. - Discover GitHub competitors for a product or market
  1099. - Create evidence-based competitor profiles
  1100. - Generate competitive landscape and opportunity reports
  1101. - Check whether competitor code has changed
  1102. - Need to document technical decisions with cited sources
  1103. **Key features:**
  1104. - Durable competitor workspace convention using `$HOME/workspace/competitors/{product}/`
  1105. - GitHub discovery workflow for shortlisting relevant repositories
  1106. - Repository ingest/update flow with remote + commit recording
  1107. - Required source citation format for repository facts (`file:line_number`)
  1108. - Landscape synthesis for positioning, strengths, weaknesses, opportunities, and risks
  1109. - Tech stack analysis guides for Node.js, Python, Rust projects
  1110. - Bundled templates: profile template, analysis checklist
  1111. - Management script for discover/clone-url/clone/pull/status operations
  1112. **Example usage:**
  1113. ```bash
  1114. # Install the skill
  1115. claude plugin install competitors-analysis@daymade-skills
  1116. # Then ask Claude to analyze a competitor
  1117. "分析竞品 https://github.com/org/repo"
  1118. "添加竞品到 flowzero 产品的竞品列表"
  1119. "看看 claude-flow-viewer 这个方向最近有哪些竞品更新"
  1120. ```
  1121. **🎬 Live Demo**
  1122. *Coming soon*
  1123. 📚 **Documentation**: See [competitors-analysis/SKILL.md](./competitors-analysis/SKILL.md) and [competitors-analysis/references/](./competitors-analysis/references/) for templates.
  1124. **Requirements**: Git (for cloning repositories)
  1125. ---
  1126. ### **tunnel-doctor** - Tailscale + Proxy/VPN Conflict Fixer
  1127. Diagnose and fix conflicts when using Tailscale alongside proxy/VPN tools (Shadowrocket, Clash, Surge) on macOS. Covers four independent conflict layers with specific guidance for SSH access to WSL instances.
  1128. **When to use:**
  1129. - Tailscale ping works but SSH/TCP connections time out
  1130. - Proxy tools hijack the Tailscale CGNAT range (100.64.0.0/10)
  1131. - Browser returns HTTP 503 but curl and SSH work
  1132. - `git push/pull` fails with "failed to begin relaying via HTTP"
  1133. - Setting up Tailscale SSH to WSL and encountering `operation not permitted`
  1134. - Need to make Tailscale and Shadowrocket/Clash/Surge coexist on macOS
  1135. **Key features:**
  1136. - Four-layer diagnostic model: route hijacking, HTTP env vars, system proxy bypass, SSH ProxyCommand double tunneling
  1137. - Per-tool fix guides for Shadowrocket, Clash, and Surge
  1138. - SSH ProxyCommand double tunnel detection and fix (git push/pull failures)
  1139. - Tailscale SSH ACL configuration (`check` vs `accept`)
  1140. - WSL snap vs apt Tailscale installation (snap sandbox breaks SSH)
  1141. - Remote development SOP with proxy-safe Makefile patterns
  1142. **Example usage:**
  1143. ```bash
  1144. # Install the skill
  1145. claude plugin install tunnel-doctor@daymade-skills
  1146. # Then ask Claude to diagnose
  1147. "Tailscale ping works but SSH times out"
  1148. "Fix Tailscale and Shadowrocket route conflict on macOS"
  1149. "git push fails with failed to begin relaying via HTTP"
  1150. "Set up Tailscale SSH to my WSL instance"
  1151. ```
  1152. **🎬 Live Demo**
  1153. *Coming soon*
  1154. 📚 **Documentation**: See [tunnel-doctor/references/proxy_conflict_reference.md](./tunnel-doctor/references/proxy_conflict_reference.md) for per-tool configuration and conflict architecture.
  1155. ---
  1156. ### **windows-remote-desktop-connection-doctor** - AVD/W365 Connection Quality Diagnostician
  1157. Diagnose Windows App (Microsoft Remote Desktop / Azure Virtual Desktop / W365) connection quality issues on macOS, with focus on transport protocol optimization (UDP Shortpath vs WebSocket fallback).
  1158. **When to use:**
  1159. - VDI connection is slow with high RTT (>100ms)
  1160. - Transport Protocol shows WebSocket instead of UDP
  1161. - RDP Shortpath fails to establish
  1162. - Connection quality degraded after changing network location
  1163. - Need to identify VPN/proxy interference with STUN/TURN
  1164. **Key features:**
  1165. - 5-step diagnostic workflow from connection info collection to fix verification
  1166. - Transport protocol analysis (UDP Shortpath > TCP > WebSocket hierarchy)
  1167. - VPN/proxy interference detection (ShadowRocket TUN mode, Tailscale exit node)
  1168. - Windows App log parsing for health check failures, certificate errors, FetchClientOptions timeouts
  1169. - ISP UDP restriction testing with STUN connectivity checks
  1170. - Chinese ISP-specific guidance for UDP throttling issues
  1171. - Working vs broken log comparison methodology
  1172. **Example usage:**
  1173. ```bash
  1174. # Install the skill
  1175. claude plugin install windows-remote-desktop-connection-doctor@daymade-skills
  1176. # Then ask Claude to diagnose
  1177. "My VDI connection shows WebSocket instead of UDP, RTT is 165ms"
  1178. "Diagnose why RDP Shortpath is not working"
  1179. "Windows App transport protocol stuck on WebSocket"
  1180. ```
  1181. **🎬 Live Demo**
  1182. *Coming soon*
  1183. 📚 **Documentation**: See [windows-remote-desktop-connection-doctor/references/](./windows-remote-desktop-connection-doctor/references/) for log analysis patterns and AVD transport protocol details.
  1184. ---
  1185. ### **product-analysis** - Multi-Path Product Analysis & Optimization
  1186. Audit UX, API, architecture and selected competitor implementations using parallel exploration and evidence-based synthesis.
  1187. **When to use:**
  1188. - Product launch readiness reviews
  1189. - Multi-perspective codebase and UX audits before release
  1190. - API quality checks with endpoint and consumption consistency reviews
  1191. - Competitive benchmarking against selected competitor repos
  1192. **Key features:**
  1193. - Auto-detects tool context (project stack + optional `codex` availability)
  1194. - Select the applicable [audit scope](product-analysis/SKILL.md#scope-modes)
  1195. - Evidence verification and priority selection through the [synthesis method](product-analysis/references/synthesis_methodology.md)
  1196. - Built-in comparison hooks with `competitors-analysis`
  1197. **Example usage:**
  1198. ```bash
  1199. # Install the skill
  1200. claude plugin install product-analysis@daymade-skills
  1201. # Then ask Claude for analysis
  1202. "Run product-analysis in full mode for launch audit"
  1203. "Audit UX navigation and verify its effects on the user's task"
  1204. "Trace API consumers and identify routes safe to retire"
  1205. "Compare this product with our top competitors"
  1206. ```
  1207. **🎬 Live Demo**
  1208. *Coming soon*
  1209. 📚 **Documentation**: See [product-analysis/SKILL.md](./product-analysis/SKILL.md) and [product-analysis/references/analysis_dimensions.md](./product-analysis/references/analysis_dimensions.md) for dimension definitions and workflow guidance.
  1210. **Requirements**: Optional `codex` CLI (for multi-model parallel mode). Skill runs with Claude only if `codex` is not installed.
  1211. ---
  1212. ### **financial-data-collector** - Financial Data Collection for US Equities
  1213. > **Install**: `claude plugin install daymade-financial@daymade-skills` (suite-only — invoked as `daymade-financial:financial-data-collector`)
  1214. Collect real financial data for any US publicly traded company from free public sources (yfinance). Output structured JSON with market data, historical financials (income statement, cash flow, balance sheet), WACC inputs, and analyst estimates - ready for downstream DCF modeling, comps analysis, or earnings review.
  1215. **When to use:**
  1216. - Collecting structured financial data before building DCF or valuation models
  1217. - Pulling market data (price, shares, beta, market cap) for any US equity ticker
  1218. - Gathering historical income statement, cash flow, and balance sheet data
  1219. - Getting risk-free rate (10Y Treasury) and analyst consensus estimates
  1220. **Key features:**
  1221. - Robust yfinance field mapping with alias chains (handles API instability across versions)
  1222. - NaN year detection and transparent reporting (never fills with estimates)
  1223. - 9-check validation: field completeness, market cap cross-check, CapEx sign convention, net debt consistency
  1224. - NO FALLBACK principle: missing data returns `null` with `_source` attribution, never default values
  1225. - FCF definition mismatch flagging (yfinance FCF ≠ investment bank FCF due to SBC)
  1226. **Example usage:**
  1227. ```bash
  1228. # Install the suite
  1229. claude plugin install daymade-financial@daymade-skills
  1230. # Then ask Claude to collect data
  1231. "Collect financial data for META"
  1232. "Get financials for AAPL --years 3"
  1233. "Pull DCF inputs for NVDA"
  1234. ```
  1235. **🎬 Live Demo**
  1236. *Coming soon*
  1237. 📚 **Documentation**: See [financial-data-collector/SKILL.md](./daymade-financial/financial-data-collector/SKILL.md), [output-schema.md](./daymade-financial/financial-data-collector/references/output-schema.md), and [yfinance-pitfalls.md](./daymade-financial/financial-data-collector/references/yfinance-pitfalls.md).
  1238. **Requirements**: Python 3.11+, `yfinance`, `pandas` (auto-installed via uv inline dependencies).
  1239. ---
  1240. ### **excel-automation** - Excel Creation, Parsing, and macOS Control
  1241. > **Install**: `claude plugin install daymade-docs@daymade-skills` (suite-only — invoked as `daymade-docs:excel-automation`)
  1242. Create professionally formatted Excel files, parse complex `.xlsm` models with stdlib XML/ZIP workflows, and control Microsoft Excel windows on macOS via AppleScript.
  1243. **When to use:**
  1244. - Building finance-ready spreadsheets with consistent formatting rules
  1245. - Parsing complex bank/broker `.xlsm` files that fail in `openpyxl`
  1246. - Extracting targeted sheet/cell data without loading huge workbooks
  1247. - Automating Excel window operations (zoom, scroll, select) on macOS
  1248. **Key features:**
  1249. - Production template for formatted workbook generation via `openpyxl`
  1250. - Complex workbook parser using `zipfile` + `xml.etree` (no heavy dependencies)
  1251. - Corrupted `definedNames` repair workflow for problematic files
  1252. - Verified AppleScript command patterns with timeout safeguards
  1253. - Bundled formatting reference for colors, number formats, and table patterns
  1254. **Example usage:**
  1255. ```bash
  1256. # Install the documentation suite
  1257. claude plugin install daymade-docs@daymade-skills
  1258. # Then ask Claude to automate Excel workflows
  1259. "Create a formatted valuation template workbook"
  1260. "Parse this .xlsm and extract the DCF sheet"
  1261. "Generate an AppleScript sequence to zoom and scroll Excel before screenshot"
  1262. ```
  1263. **🎬 Live Demo**
  1264. *Coming soon*
  1265. 📚 **Documentation**: See [excel-automation/SKILL.md](./daymade-docs/excel-automation/SKILL.md) and [formatting-reference.md](./daymade-docs/excel-automation/references/formatting-reference.md).
  1266. **Requirements**: Python 3.8+, `uv`, `openpyxl` (auto via `uv run --with openpyxl`), macOS for AppleScript window control.
  1267. ---
  1268. ### **capture-screen** - Programmatic macOS Screenshot Capture
  1269. > **Install**: `claude plugin install daymade-macos@daymade-skills` (suite-only — invoked as `daymade-macos:capture-screen`)
  1270. For desktop or app-window screenshots, start with the Skill's
  1271. [observation and control boundary](./daymade-macos/capture-screen/SKILL.md#select-observation-or-foreground-control),
  1272. then select its [capture route](./daymade-macos/capture-screen/SKILL.md#quick-start).
  1273. ### **macos-permissions** - Diagnose and Repair macOS Privacy Permissions
  1274. > **Install**: `claude plugin install daymade-macos@daymade-skills` (suite-only — invoked as `daymade-macos:macos-permissions`)
  1275. For visible permission or Keychain dialogs, start with
  1276. [observation and classification](./daymade-macos/macos-permissions/SKILL.md#observe-and-classify-the-reported-problem-first).
  1277. For protected-data failures without a visible dialog, enter the
  1278. [TCC request procedure](./daymade-macos/macos-permissions/SKILL.md#reproduce-the-reported-denial-first).
  1279. ---
  1280. ### **continue-claude-code-work** - Resume Interrupted Claude Work
  1281. > **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:continue-claude-code-work`)
  1282. Continue a verified Claude Code Session without reopening the old interactive
  1283. session. The continuation layer first consumes `read-claude-code-history`, then
  1284. reconstructs the original business outcome, unfulfilled requests, corrections,
  1285. proven prior assets, and one next action that directly advances the goal.
  1286. **When to use:**
  1287. - A user provides a Claude session ID and wants the task continued
  1288. - You need to inspect local `.claude` JSONL files instead of running `claude --resume`
  1289. - A previous session was interrupted and the next concrete step must be reconstructed
  1290. - A multi-agent workflow was interrupted and you need to know which subagents completed
  1291. **Key features:**
  1292. - Requires a chronological read receipt rather than separate user/assistant tail lists
  1293. - Restores original outcome, remaining work, rejected routes, and successful assets
  1294. - Verifies current files, git state, external writes, and background work before duplicating anything
  1295. - Makes the business result—not parser success, review completion, or subprocess exit—the completion unit
  1296. **Example usage:**
  1297. ```bash
  1298. # Then ask Claude to resume from local artifacts
  1299. "continue work from session 123e4567-e89b-12d3-a456-426614174000"
  1300. "don't resume, just read the .claude files and continue"
  1301. "check what I was working on in the last session and keep going"
  1302. ```
  1303. 📚 **Documentation**: See [continue-claude-code-work/SKILL.md](./daymade-claude-code/continue-claude-code-work/SKILL.md).
  1304. **Requirements**: Python 3.8+, `git` for workspace reconciliation.
  1305. ---
  1306. ### **scrapling-skill** - Reliable Scrapling CLI Workflows
  1307. Install, troubleshoot, and use Scrapling CLI with a verified static-first workflow for extracting HTML, Markdown, or text from webpages. Includes a diagnostic script for broken extras installs, Playwright browser runtime checks, and smoke tests against real URLs.
  1308. **When to use:**
  1309. - Users mention Scrapling, `uv tool install scrapling`, or `scrapling extract`
  1310. - You need to choose between static and browser-backed fetching
  1311. - You need to extract article bodies from WeChat public pages (`mp.weixin.qq.com`)
  1312. - A Scrapling install works partially but fails on missing extras, browser runtime, or TLS verification
  1313. **Key features:**
  1314. - Bundled `diagnose_scrapling.py` script for CLI, browser runtime, and live URL smoke tests
  1315. - Verified default path: start with `extract get`, escalate to `extract fetch` only when needed
  1316. - WeChat extraction pattern using `#js_content` for clean article Markdown
  1317. - Troubleshooting guidance for missing `click`, Playwright runtime setup, and `curl: (60)` trust-store failures
  1318. - Output validation workflow using file size and content checks instead of exit-code assumptions
  1319. **Example usage:**
  1320. ```bash
  1321. # Install the skill
  1322. claude plugin install scrapling-skill@daymade-skills
  1323. # Then ask Claude to work through Scrapling for you
  1324. "Install Scrapling CLI and verify the setup"
  1325. "Extract this WeChat article into Markdown with Scrapling"
  1326. "Decide whether this page needs static or browser-backed fetching"
  1327. ```
  1328. **🎬 Live Demo**
  1329. *Coming soon*
  1330. 📚 **Documentation**: See [scrapling-skill/SKILL.md](./scrapling-skill/SKILL.md) and [scrapling-skill/references/troubleshooting.md](./scrapling-skill/references/troubleshooting.md).
  1331. **Requirements**: Python 3.6+, `uv`, Scrapling CLI, and Playwright browser runtime for browser-backed fetches.
  1332. ---
  1333. ### **ima-copilot** - Tencent IMA Companion & Installer
  1334. One-stop wrapper for the official Tencent IMA skill (`ima.qq.com`). Installs upstream `ima-skill` to Claude Code, Codex, and OpenClaw via `npx skills add`, guides API key setup, detects and repairs known upstream issues under user consent, and implements a personalized fan-out search strategy that floats priority knowledge bases to the top.
  1335. **When to use:**
  1336. - Users mention IMA, 腾讯 IMA, ima.qq.com, or need to install the official ima-skill
  1337. - Users report `Skipped loading skill(s) due to invalid SKILL.md` warnings related to ima-skill
  1338. - You need to search across IMA knowledge bases with KB-priority boosting
  1339. - You need to configure or rotate IMA API credentials
  1340. - Upstream ima-skill ships a known issue (e.g., missing YAML frontmatter in submodule files)
  1341. **Key features:**
  1342. - Zero-config installation to Claude Code / Codex / OpenClaw via [vercel-labs/skills](https://github.com/vercel-labs/skills) with auto-detection and default symlink mode (fix or upgrade once, every agent sees it)
  1343. - XDG-style credential management at `~/.config/ima/{client_id, api_key}` with env-var fallback
  1344. - `scripts/diagnose.sh` read-only health check (install presence, credential liveness, known issues)
  1345. - `scripts/search_fanout.py` client-side cross-KB search with priority lists, subset-skip lists, and 100-hit silent-truncation detection
  1346. - Wrapper-only architecture: never vendors upstream files, never forks — every repair is a runtime instruction executed with explicit consent and automatic timestamped backups
  1347. - Two user-selectable repair strategies for the frontmatter issue (rename to `MODULE.md` or prepend minimal frontmatter)
  1348. - Personalization via `~/.config/ima/copilot.json` with illustrative-only template values
  1349. **Example usage:**
  1350. ```bash
  1351. # Install the skill
  1352. claude plugin install ima-copilot@daymade-skills
  1353. # Then ask Claude to drive the flow
  1354. "Install ima-skill and configure my IMA API key"
  1355. "Run diagnose on my ima-skill and fix whatever is broken"
  1356. "Search my IMA knowledge bases for embedding model comparisons, priority to my curated KB"
  1357. ```
  1358. **🎬 Live Demo**
  1359. *Coming soon*
  1360. 📚 **Documentation**: See [ima-copilot/SKILL.md](./ima-copilot/SKILL.md) and [ima-copilot/references/known_issues.md](./ima-copilot/references/known_issues.md).
  1361. **Requirements**: Node.js 18+ (for `npx skills`), `curl`, `unzip`, Python 3.6+. IMA OpenAPI credentials from [https://ima.qq.com/agent-interface](https://ima.qq.com/agent-interface).
  1362. ---
  1363. ### **claude-export-txt-better** - Fix Claude Code Export Formatting
  1364. > **Install**: `claude plugin install daymade-claude-code@daymade-skills` (suite-only — invoked as `daymade-claude-code:fixing-claude-export-conversations`)
  1365. Reconstruct broken line wrapping in Claude Code exported `.txt` conversation files. Rebuilds tables, paragraphs, paths, and tool calls that were hard-wrapped at fixed column widths, and ships with an automated 53-check validation suite (file-agnostic, catches over- and under-merging regressions).
  1366. **When to use:**
  1367. - Users have a Claude Code export file where tables, paths, or tool output got mangled by line wrapping
  1368. - Users mention "fix export", "fix conversation", "make export readable"
  1369. - Users reference a file matching `YYYY-MM-DD-HHMMSS-*.txt`
  1370. - Users want to post-process `/export` output before sharing or archiving it
  1371. **Key features:**
  1372. - Deterministic Python script (`fix-claude-export.py`) with `--stats` mode for before/after metrics
  1373. - 53-check automated validator (`validate-claude-export-fix.py`) that catches regressions
  1374. - Evals directory with real fixture cases
  1375. - No external dependencies beyond `uv` and Python 3.8+
  1376. **Example usage:**
  1377. ```bash
  1378. # Fix and show stats
  1379. uv run daymade-claude-code/claude-export-txt-better/scripts/fix-claude-export.py broken.txt --stats
  1380. # Custom output path
  1381. uv run daymade-claude-code/claude-export-txt-better/scripts/fix-claude-export.py broken.txt -o fixed.txt
  1382. # Validate the fix
  1383. uv run daymade-claude-code/claude-export-txt-better/scripts/validate-claude-export-fix.py broken.txt fixed.txt
  1384. ```
  1385. **🎬 Live Demo**
  1386. *Coming soon*
  1387. 📚 **Documentation**: See [claude-export-txt-better/SKILL.md](./daymade-claude-code/claude-export-txt-better/SKILL.md) and the bundled `evals/` fixtures.
  1388. **Requirements**: Python 3.8+, `uv` package manager.
  1389. ---
  1390. ### **douban-skill** - Douban Collection Export & Sync
  1391. Export and sync Douban (豆瓣) book / movie / music / game collections to local CSV files via the reverse-engineered Frodo API. Full export covers all history; RSS incremental sync keeps daily updates current. No login, no cookies, no browser — just a user ID and it works.
  1392. **When to use:**
  1393. - Users want to back up their Douban reading/watching/listening/gaming history
  1394. - Users mention 豆瓣, douban, 读书记录, 观影记录, 书影音
  1395. - Users need incremental sync of recent Douban activity
  1396. - Users want CSV output compatible with Excel (UTF-8 BOM)
  1397. **Key features:**
  1398. - Full export of all 4 categories (books/movies/music/games) via Frodo API
  1399. - RSS incremental sync for daily updates (last ~10 items per feed)
  1400. - Pre-flight user-ID validation (fail-fast on wrong ID)
  1401. - UTF-8 BOM CSV output, Excel-compatible, cross-platform
  1402. - Bundled troubleshooting log documenting 7 tested scraping approaches and why each failed (Douban PoW challenges block every web-scraping approach — only Frodo API works)
  1403. - `.gitleaks.toml` allowlist for the public Android APK credentials
  1404. **Example usage:**
  1405. ```bash
  1406. # Full export of user's collections
  1407. uv run douban-skill/scripts/douban-frodo-export.py <douban-user-id>
  1408. # Incremental RSS sync (last ~10 items per category)
  1409. uv run douban-skill/scripts/douban-rss-sync.py <douban-user-id>
  1410. ```
  1411. **🎬 Live Demo**
  1412. *Coming soon*
  1413. 📚 **Documentation**: See [douban-skill/SKILL.md](./douban-skill/SKILL.md) and [douban-skill/references/troubleshooting.md](./douban-skill/references/troubleshooting.md) for the complete failure log of rejected approaches.
  1414. **Requirements**: Python 3.8+, `uv` package manager. No login or cookies required.
  1415. ---
  1416. ### **terraform-skill** - Terraform Operational Traps
  1417. Designs and diagnoses safe Terraform releases as well as the provisioner traps learned from real incidents. It keeps staging and production on one required configuration schema, validates exact candidate bytes + the Compose-rendered environment + the immutable runtime before live mutation, and binds saved plans to staging evidence, source provenance, explicit production authorization, and independent readback.
  1418. **When to use:**
  1419. - Writing `null_resource` provisioners or `remote-exec` blocks that SSH into fresh instances
  1420. - Setting up multi-environment (prod/staging/dev) Terraform with shared modules
  1421. - Debugging containers that are Restarting/unhealthy after `terraform apply`
  1422. - Hitting "docker: not found" in remote-exec, rsync connection drops in local-exec, or TLS cert errors
  1423. - Troubleshooting drift or provisioner failures during re-runs
  1424. - Configuring Caddy/gateway resources with Cloudflare credentials
  1425. - Reviewing a saved plan or broad deploy resource that may also mutate a shared gateway
  1426. - Closing staging/production config drift, receipt, provenance, or production-approval gaps
  1427. **Key features:**
  1428. - One required-key contract for every environment; values may differ, requiredness may not
  1429. - Exact-bundle prevalidation for every normal and recovery writer before any live write/restart
  1430. - Saved-plan, staging-receipt, remote-main provenance, production-approval, and live-readback gates
  1431. - Corrected provider/provisioner patterns for cloud-init, Docker, DNS, TLS, snapshots, and fresh hosts
  1432. **Example usage:**
  1433. ```bash
  1434. # Trigger the skill naturally during Terraform work

Lines 2,001–3,933 are not shown. The link to the file on GitHub has every line.

daymade-audio/transcript-fixer/scripts/source_clip.py · Bundled script · 254 lines · 1 finding marked
  1. #!/usr/bin/env python3
  2. """Prepare a local/authorized SSH source and fetch identity-bound audio windows.
  3. SSH is opt-in through an exact host, hostname and account. Credentials and machine
  4. addresses belong in the caller's private source spec, never the shipped package.
  5. """
  6. from __future__ import annotations
  7. import argparse
  8. import hashlib
  9. import json
  10. import math
  11. import os
  12. from pathlib import Path
  13. import re
  14. import subprocess
  15. import sys
  16. import tempfile
  17. import time
  18. SCHEMA = "transcript-source-v1"
  19. CLIP_SCHEMA = "transcript-source-clip-v1"
  20. MAX_WINDOW = 180.0
  21. # One implementation runs locally or over the existing SSH command plane.
  22. # The request is JSON data on stdin; paths never become shell commands.
  23. WORKER = r'''
  24. import getpass,hashlib,json,os,pathlib,socket,subprocess,sys,tempfile
  25. def fingerprint(p):
  26. s=p.stat()
  27. if not p.is_file() or p.is_symlink(): raise ValueError("source must be a regular physical file")
  28. return {k:getattr(s,"st_"+k) for k in ("dev","ino","size","mtime_ns","ctime_ns")}
  29. def main(a):
  30. p=pathlib.Path(a["path"])
  31. if not p.is_absolute(): raise ValueError("absolute source path required")
  32. if a.get("hostname") and socket.gethostname()!=a["hostname"]: raise ValueError("SSH hostname mismatch")
  33. if a.get("user") and getpass.getuser()!=a["user"]: raise ValueError("SSH account mismatch")
  34. before=fingerprint(p)
  35. if a.get("fingerprint") is not None and before!=a["fingerprint"]: raise ValueError("source version changed")
  36. if a["action"]=="probe":
  37. digest=hashlib.sha256()
  38. with p.open("rb") as f:
  39. for b in iter(lambda:f.read(1048576),b""): digest.update(b)
  40. if digest.hexdigest()!=a["sha256"]: raise ValueError("source SHA-256 mismatch")
  41. duration=float(subprocess.check_output([a.get("ffprobe","ffprobe"),"-v","error","-show_entries","format=duration","-of","default=nw=1:nk=1",str(p)],timeout=30))
  42. if before!=fingerprint(p): raise ValueError("source changed during probe")
  43. print(json.dumps({"fingerprint":before,"duration":duration,"hostname":socket.gethostname(),"user":getpass.getuser()}));return
  44. if a["action"]=="check":
  45. print(json.dumps({"fingerprint":before}));return
  46. with tempfile.TemporaryDirectory(prefix="transcript-source-clip-") as td:
  47. out=pathlib.Path(td)/"clip.wav"
  48. cp=subprocess.run([a.get("ffmpeg","ffmpeg"),"-nostdin","-hide_banner","-loglevel","error","-ss",str(a["start"]),"-i",str(p),"-t",str(a["end"]-a["start"]),"-vn","-ac","1","-ar","16000","-c:a","pcm_s16le",str(out)],capture_output=True,timeout=90)
  49. if cp.returncode: raise ValueError("ffmpeg extraction failed: "+cp.stderr.decode(errors="replace")[-600:])
  50. duration=float(subprocess.check_output([a.get("ffprobe","ffprobe"),"-v","error","-show_entries","format=duration","-of","default=nw=1:nk=1",str(out)],timeout=15))
  51. if abs(duration-(a["end"]-a["start"]))>0.05: raise ValueError("truncated or mis-sized clip")
  52. if before!=fingerprint(p): raise ValueError("source changed during extraction")
  53. data=out.read_bytes()
  54. print(json.dumps({"sha256":hashlib.sha256(data).hexdigest(),"size":len(data),"duration":duration}),flush=True)
  55. sys.stdout.buffer.write(data);sys.stdout.buffer.flush()
  56. try: main(json.load(sys.stdin))
  57. except Exception as e:
  58. print(type(e).__name__+": "+str(e),file=sys.stderr);sys.exit(2)
  59. '''
  60. def sha256(path: Path) -> str:
  61. digest = hashlib.sha256()
  62. with path.open("rb") as source:
  63. for block in iter(lambda: source.read(1048576), b""):
  64. digest.update(block)
  65. return digest.hexdigest()
  66. def atomic_write(path: Path, data: bytes, *, replace: bool = True) -> None:
  67. path.parent.mkdir(parents=True, exist_ok=True)
  68. if path.is_symlink():
  69. raise ValueError("refusing symlink output")
  70. fd, temp = tempfile.mkstemp(prefix=".clip-", dir=path.parent)
  71. try:
  72. with os.fdopen(fd, "wb") as out:
  73. out.write(data)
  74. out.flush()
  75. os.fsync(out.fileno())
  76. if replace:
  77. os.replace(temp, path)
  78. else:
  79. os.link(temp, path) # Exclusive publication; never replace an existing source/spec.
  80. finally:
  81. if os.path.exists(temp):
  82. os.unlink(temp)
  83. def run_worker(spec: dict, request: dict) -> bytes:
  84. if spec.get("kind") not in ("local", "ssh"):
  85. raise ValueError("source kind must be local or ssh; existing --audio URLs remain supported separately")
  86. if not isinstance(spec.get("path"), str) or not spec["path"].startswith("/"):
  87. raise ValueError("absolute physical source path required")
  88. command = [sys.executable, "-c", WORKER]
  89. for tool in ("ffmpeg", "ffprobe"):
  90. if tool in spec:
  91. if not isinstance(spec[tool], str) or not Path(spec[tool]).is_absolute():
  92. raise ValueError("explicit media tool paths must be absolute on the source host")
  93. request = {**request, tool: spec[tool]}
  94. if spec["kind"] == "ssh":
  95. ssh = spec.get("ssh", {})
  96. if (not isinstance(ssh, dict) or any(not isinstance(ssh.get(k), str) or not ssh[k].strip()
  97. for k in ("host", "hostname", "user"))
  98. or not re.fullmatch(r"[A-Za-z0-9_][A-Za-z0-9_.@:-]*", ssh["host"])):
  99. raise ValueError("SSH requires a safe explicit alias, expected hostname and user")
  100. request = {**request, "hostname": ssh["hostname"], "user": ssh["user"]}
  101. # Fixed command, encoded program in argv; the request remains stdin data.
  102. import base64
  103. encoded = base64.b64encode(WORKER.encode()).decode()
  104. remote = "python3 -c 'import base64;exec(base64.b64decode(\"" + encoded + "\"))'"
    • Note: Runs code it decodes (base64, hex, character codes, reversed text or a compressed blob), which hides what runs from a reader
    • Line 114 on GitHub
  105. command = ["ssh", "-o", "BatchMode=yes", "-o", "ConnectTimeout=10", "--", ssh["host"], remote]
  106. result = subprocess.run(command, input=json.dumps({**request, "path": spec["path"]}).encode(),
  107. capture_output=True, timeout=120)
  108. if result.returncode:
  109. raise ValueError("source operation failed: " + result.stderr.decode(errors="replace")[-900:])
  110. return result.stdout
  111. def prepare(spec: dict) -> dict:
  112. if not re.fullmatch(r"[0-9a-f]{64}", spec.get("sha256", "")):
  113. raise ValueError("expected source SHA-256 is required")
  114. proof = json.loads(run_worker(spec, {"action": "probe", "sha256": spec["sha256"]}))
  115. if not math.isfinite(proof["duration"]) or proof["duration"] <= 0:
  116. raise ValueError("invalid source duration")
  117. return {**spec, "schema": SCHEMA, "fingerprint": proof["fingerprint"],
  118. "duration": proof["duration"], "verified_at": time.time()}
  119. class SourceClips:
  120. def __init__(self, spec_path: str | Path, cache: str | Path):
  121. self.spec_path = Path(spec_path).resolve()
  122. self.spec = json.loads(self.spec_path.read_text())
  123. if (self.spec.get("schema") != SCHEMA or not self.spec.get("fingerprint")
  124. or not re.fullmatch(r"[0-9a-f]{64}", self.spec.get("sha256", ""))
  125. or not math.isfinite(self.spec.get("duration", 0)) or self.spec["duration"] <= 0):
  126. raise ValueError("prepare and verify the source spec before fetching clips")
  127. self.duration = self.spec["duration"]
  128. self.cache = Path(cache).expanduser().resolve()
  129. self.cache.mkdir(parents=True, exist_ok=True)
  130. def check(self):
  131. json.loads(run_worker(self.spec, {"action": "check", "fingerprint": self.spec["fingerprint"]}))
  132. def fetch(self, start: float, end: float, output: str | Path) -> dict:
  133. if (not all(math.isfinite(v) for v in (start, end)) or start < 0
  134. or start >= end or end > self.duration + 0.001 or end-start > MAX_WINDOW):
  135. raise ValueError("invalid source-clock window (maximum 180 seconds)")
  136. self.check()
  137. identity = {"schema": CLIP_SCHEMA,
  138. "source": {k: v for k, v in self.spec.items() if k != "verified_at"},
  139. "start": start, "end": end,
  140. "sample_rate": 16000, "channels": 1, "codec": "pcm_s16le"}
  141. target = Path(output).expanduser().absolute()
  142. sidecar = Path(str(target)+".source.json")
  143. reserved = {self.spec_path}
  144. if self.spec["kind"] == "local":
  145. reserved.add(Path(self.spec["path"]).resolve())
  146. if any(p.is_symlink() or p.resolve() in reserved for p in (target, sidecar)):
  147. raise ValueError("output conflicts with a source/spec or symlink")
  148. if target.exists() or sidecar.exists():
  149. try:
  150. previous = json.loads(sidecar.read_text())
  151. if not isinstance(previous, dict) or previous.get("identity") != identity or (target.exists() and sha256(target) != previous["clip_sha256"]):
  152. raise ValueError("unbound existing output")
  153. except (OSError, ValueError, KeyError, TypeError) as exc:
  154. raise ValueError("refusing to replace an existing output without its matching clip receipt") from exc
  155. key = hashlib.sha256(json.dumps(identity, sort_keys=True).encode()).hexdigest()
  156. cached, metadata = self.cache / (key+".wav"), self.cache / (key+".json")
  157. lock = self.cache / (key+".lock")
  158. if any(path.resolve() in reserved for path in (cached, metadata, lock)):
  159. raise ValueError("cache path conflicts with the source/spec")
  160. try:
  161. fd = os.open(lock, os.O_WRONLY | os.O_CREAT | os.O_EXCL, 0o600)
  162. except FileExistsError as exc:
  163. raise ValueError("clip key is in use; reuse the current writer's result after it finishes") from exc
  164. os.close(fd)
  165. try:
  166. reused = False
  167. if cached.is_file() and metadata.is_file() and not cached.is_symlink() and not metadata.is_symlink():
  168. try:
  169. proof = json.loads(metadata.read_text())
  170. reused = isinstance(proof, dict) and proof.get("identity") == identity and sha256(cached) == proof.get("clip_sha256")
  171. except (OSError, ValueError):
  172. reused = False
  173. if not reused:
  174. wire = run_worker(self.spec, {"action": "extract", "fingerprint": self.spec["fingerprint"],
  175. "start": start, "end": end})
  176. header, data = wire.split(b"\n", 1)
  177. info = json.loads(header)
  178. if (len(data) != info["size"] or hashlib.sha256(data).hexdigest() != info["sha256"]
  179. or abs(info["duration"] - (end-start)) > 0.05):
  180. raise ValueError("clip transfer/duration mismatch")
  181. proof = {"identity": identity, "clip_sha256": info["sha256"],
  182. "clip_size": info["size"], "duration": info["duration"]}
  183. atomic_write(cached, data)
  184. atomic_write(metadata, (json.dumps(proof, ensure_ascii=False, indent=2)+"\n").encode())
  185. self.check()
  186. data = cached.read_bytes()
  187. if hashlib.sha256(data).hexdigest() != proof["clip_sha256"]:
  188. raise ValueError("cache changed before output publication")
  189. atomic_write(target, data)
  190. receipt = {**proof, "cache_reused": reused, "output": str(target),
  191. "source_sha256": self.spec["sha256"], "source_start": start,
  192. "source_end": end, "speed": 1}
  193. atomic_write(sidecar, (json.dumps(receipt, ensure_ascii=False, indent=2)+"\n").encode())
  194. return receipt
  195. finally:
  196. lock.unlink()
  197. def main() -> int:
  198. parser = argparse.ArgumentParser(description=__doc__)
  199. commands = parser.add_subparsers(dest="command", required=True)
  200. p = commands.add_parser("prepare", help="Full-hash an existing local/authorized SSH source once")
  201. p.add_argument("--path", required=True)
  202. p.add_argument("--sha256", required=True)
  203. p.add_argument("--ssh-host")
  204. p.add_argument("--expected-hostname")
  205. p.add_argument("--expected-user")
  206. p.add_argument("--ffmpeg", help="Verified absolute ffmpeg path on source host, if absent from SSH PATH")
  207. p.add_argument("--ffprobe", help="Verified absolute ffprobe path on source host, if absent from SSH PATH")
  208. p.add_argument("--output", required=True)
  209. p = commands.add_parser("fetch", help="Fetch a verified source-clock window, with bounded cache reuse")
  210. p.add_argument("--source-spec", required=True)
  211. p.add_argument("--cache-dir", required=True)
  212. p.add_argument("--start", type=float, required=True)
  213. p.add_argument("--end", type=float, required=True)
  214. p.add_argument("--output", required=True)
  215. args = parser.parse_args()
  216. try:
  217. if args.command == "prepare":
  218. spec = {"kind": "ssh" if args.ssh_host else "local", "path": args.path, "sha256": args.sha256}
  219. if args.ssh_host:
  220. spec["ssh"] = {"host": args.ssh_host, "hostname": args.expected_hostname, "user": args.expected_user}
  221. for tool in ("ffmpeg", "ffprobe"):
  222. if getattr(args, tool):
  223. spec[tool] = getattr(args, tool)
  224. result = prepare(spec)
  225. atomic_write(Path(args.output), (json.dumps(result, ensure_ascii=False, indent=2)+"\n").encode(), replace=False)
  226. else:
  227. result = SourceClips(args.source_spec, args.cache_dir).fetch(args.start, args.end, args.output)
  228. print(json.dumps(result, ensure_ascii=False))
  229. return 0
  230. except (OSError, ValueError, KeyError, TypeError, subprocess.SubprocessError) as exc:
  231. print(json.dumps({"error": str(exc)}, ensure_ascii=False), file=sys.stderr)
  232. return 2
  233. if __name__ == "__main__":
  234. raise SystemExit(main())

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.