Skip to content
Back to search

https://github.com/anthropics/claude-plugins-community

MarketplaceWorks with Claude CodeOfficial: AnthropicGitHubIncomplete

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

It has changed since its scan on 11 Nov 2026.

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/anthropics/claude-plugins-community 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/anthropics/claude-plugins-community'

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/anthropics-claude-plugins-community/badge.svg)](/listings/anthropics-claude-plugins-community)

HTML

<a href="/listings/anthropics-claude-plugins-community"><img src="/api/listings/anthropics-claude-plugins-community/badge.svg" alt="findsafeskills safety rating" /></a>

Install

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 · 3,069 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "claude-community",
  3. "owner": {
  4. "name": "Anthropic"
  5. },
  6. "renames": {
  7. "qodo-skills": "qodo",
  8. "wordpress-com": "build-with-wordpress",
  9. "auth0-sdks": "auth0",
  10. "twilio": "twilio-developer-kit"
  11. },
  12. "plugins": [
  13. {
  14. "name": "0x",
  15. "description": "Guide developers through swapping ERC-20 tokens using the 0x API. Covers standard swaps via AllowanceHolder and Permit2 as well as gasless swaps across 20+ EVM chains — walking through price quotes, approvals, EIP-712 signing, and transaction submission. Also helps integrate 0x swaps directly into your app with code samples.",
  16. "source": {
  17. "source": "url",
  18. "url": "https://github.com/0xProject/0x-ai.git",
  19. "sha": "0167bbb411cc972b966127d23c23de801061fa99"
  20. },
  21. "homepage": "https://github.com/0xProject/0x-ai"
  22. },
  23. {
  24. "name": "10x-shopping",
  25. "description": "An AI-powered shopping assistant that connects Claude to Shopify's global product catalog. Browse products, manage carts, and complete purchases through natural conversation",
  26. "source": {
  27. "source": "url",
  28. "url": "https://github.com/qressy/10x-claude-plugin.git",
  29. "sha": "5cd3d90ec0cfa99773dd2c075e492bd280b3826a"
  30. },
  31. "homepage": "https://www.10xgeo.com/"
  32. },
  33. {
  34. "name": "10x-team",
  35. "description": "10x-Team gives you an entire engineering team as Claude Code skills. 12 specialized roles — CTO, Product Manager, Principal Architect,\nStaff Engineer, Engineering Manager, Senior Engineer, SDE, DBA, Security Engineer, QA Engineer, DevOps Engineer, and SRE — each with\nstructured decision processes and opinionated guidance.\n\nKey features:\n\n- 12 individual role skills (/cto, /architect, /sde, /security-engineer, etc.) for targeted expertise\n- 1 orchestrator skill (/10x-team) that runs all 12 roles end-to-end with hard gates at every phase\n- File-based project state (.10x/) so roles share decisions and track progress across conversations\n- Discovery protocol that reverse-engineers existing codebases before making changes\n- Every role follows a structured process — no generic advice, only actionable recommendations with trade-offs\n- Brainstorm-first approach — the orchestrator won't let you write code until the design is validated",
  36. "source": {
  37. "source": "url",
  38. "url": "https://github.com/Jaan-Mustafa/10x-Team.git",
  39. "sha": "ea01f8262495e99a66ca292739b0517314e6914e"
  40. },
  41. "homepage": "https://github.com/Jaan-Mustafa/10x-Team/blob/main/README.md"
  42. },
  43. {
  44. "name": "16minds",
  45. "description": "16-minds summons agents modeled on 16 distinct personality types — each with its own values, thinking patterns, and tone — to debate, review, or advise on any topic. Each personality is written directly into an independent prompt, so outputs carry visibly different voices instead of the averaged answer a single agent tends to produce.\n\nThree commands cover the range:\n - /mind <type> — a single type's opinion\n - /pair <a> <b> — a two-type debate (open → rebut → reply / synthesize)\n - /minds — fan out to all 16 in parallel, then synthesize\n\nThree modes (light / middle / heavy) trade depth for token cost.\n\nThe /minds synthesis follows a fixed 4-section rubric — score distribution, axes of disagreement, easily-overlooked perspectives, and landing-zone candidates with per-candidate \"types likely to agree / fit / risk\" — to keep 16-voice output structured rather than scattershot. The --save flag writes the full execution log to a file for use as article material or decision logs.\n\nBuilt for decisions where a single averaged answer would lose the edges: idea generation, design judgment, code review, and life/career questions.",
  46. "source": {
  47. "source": "url",
  48. "url": "https://github.com/yukurash/16minds-plugin.git",
  49. "sha": "00f3bd5f0f6d9d34a6df91e061afa5846f8d4bc6"
  50. },
  51. "homepage": "https://github.com/yukurash/16minds-plugin"
  52. },
  53. {
  54. "name": "42crunch-api-security-testing",
  55. "description": "Automate API security directly in Claude Code with 42Crunch. This plugin enables developers to audit OpenAPI specifications, detect OWASP API vulnerabilities including BOLA and BFLA, run live conformance and authorization tests, and apply AI-assisted fixes, all through natural language.\nDesigned for AI-assisted development workflows, the plugin provides continuous security guardrails across the full lifecycle of your API. It combines static analysis of OpenAPI definitions with dynamic runtime testing to ensure your APIs behave securely in real conditions.\nWith a simple audit to scan to remediate to validate loop, developers can identify issues early, fix them with confidence, and verify that security requirements are met before deployment. The plugin integrates seamlessly into Claude Code, allowing teams to embed API security directly into their development process without switching tools.\nKey capabilities include static security audit of OpenAPI specifications with scored findings, detection of OWASP API Security risks including authorization flaws like BOLA and BFLA, live API scanning for conformance and runtime behavior validation, AI-assisted remediation with user-controlled changes, an end to end security testing pipeline combining audit and scan, and automatic generation of OpenAPI specifications from source code.\nWhether you are working with existing APIs or generating new ones, 42Crunch helps ensure that security is built in from the start and continuously validated throughout development.",
  56. "source": {
  57. "source": "git-subdir",
  58. "url": "42Crunch-AI/claude-plugins",
  59. "path": "plugins/api-security-testing",
  60. "ref": "v1.0.1",
  61. "sha": "30287f5e3f122a646d1ac5ca3ab96e130c52a3ad"
  62. },
  63. "homepage": "https://docs.42crunch.com"
  64. },
  65. {
  66. "name": "8-habit-ai-dev",
  67. "description": "8-habit-ai-dev replaces ad-hoc AI prompting with a structured 7-step workflow: Research →\nRequirements → Design → Breakdown → Build Brief → Review → Deploy. Each step maps to one of\nStephen Covey's 8 Habits, providing both practical discipline and principled reasoning.\n\nKey features:\n- 17 hand-crafted skills with DAG-validated handoff chain\n- 472 automated assertions across 4 validator scripts (structure, skill-graph, content,\nverbosity)\n- Whole Person Model assessment (Body/Mind/Heart/Spirit scoring)\n- Maturity-adaptive verbosity via /calibrate (Dependence → Interdependence)\n- /reflect with dream-inspired lesson consolidation\n- /cross-verify 17-question checklist covering all 8 Habits\n- Composes cleanly with claude-governance plugin for compliance enforcement\n\nPure markdown plugin — no runtime dependencies, no MCP servers, no external services.",
  68. "source": {
  69. "source": "url",
  70. "url": "https://github.com/pitimon/8-habit-ai-dev.git",
  71. "sha": "42d03b42fcbc73f43652832973faa8a411e1dae6"
  72. },
  73. "homepage": "https://github.com/pitimon/8-habit-ai-dev"
  74. },
  75. {
  76. "name": "a11y-fixer",
  77. "description": "Scan HTML/JSX for accessibility issues",
  78. "source": {
  79. "source": "git-subdir",
  80. "url": "barnburner121/claude-plugin-marketplace",
  81. "path": "generated-plugins/a11y-fixer",
  82. "ref": "main",
  83. "sha": "5f6b5d32d9f457dc9c2c7c0fb1d67dffc9140f33"
  84. },
  85. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  86. },
  87. {
  88. "name": "ab-testing",
  89. "description": "Generate A/B testing infrastructure and analysis",
  90. "source": {
  91. "source": "git-subdir",
  92. "url": "barnburner121/claude-plugin-marketplace",
  93. "path": "generated-plugins/ab-testing",
  94. "ref": "main",
  95. "sha": "6470b3dbdf66767d531844b597ddff183f4eb146"
  96. },
  97. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  98. },
  99. {
  100. "name": "meticulous",
  101. "description": "Agent skills for Meticulous visual regression testing — review test runs, investigate replays, debug diffs. Also connects the hosted Meticulous MCP server.",
  102. "author": {
  103. "name": "Meticulous"
  104. },
  105. "category": "testing",
  106. "source": {
  107. "source": "url",
  108. "url": "https://github.com/alwaysmeticulous/skills.git",
  109. "sha": "59788561ed2b53f0fc56c54048c09f47f35b61af"
  110. },
  111. "homepage": "https://www.meticulous.ai/"
  112. },
  113. {
  114. "name": "sap-dev-core",
  115. "description": "Core SAP development utilities and ABAP Workbench automation: login, connection management, credential storage, BDC execution, add-on table maintenance, and SAP GUI Scripting for SE38, SE37, SE24, SE11, SE19, SE41, SE51, SE54, SE91, CMOD, and GUI inspection / recording. Also provides shared resources (shared/tables/, shared/scripts/) used by all other sap-dev plugins. Install this plugin first.",
  116. "source": {
  117. "source": "git-subdir",
  118. "url": "https://github.com/sapdev-ai/sap-dev.git",
  119. "path": "plugins/sap-dev-core",
  120. "ref": "main",
  121. "sha": "751882881caa1a1762a16a51f262525519a034d2"
  122. },
  123. "homepage": "https://sapdev.ai"
  124. },
  125. {
  126. "name": "sap-gen-code",
  127. "description": "ABAP code generation pipeline: convert design docs, extract structured data, validate process/DDIC, generate ABAP (incl. CDS views) and ABAP Unit tests, and run an AI semantic + security review. Companion to sap-dev-core (install that first — its shared scripts are required at runtime).",
  128. "source": {
  129. "source": "git-subdir",
  130. "url": "https://github.com/sapdev-ai/sap-dev.git",
  131. "path": "plugins/sap-gen-code",
  132. "ref": "main",
  133. "sha": "2283c60151fab9e4dbbb9c92d931ffabd2cda9f8"
  134. },
  135. "homepage": "https://sapdev.ai"
  136. },
  137. {
  138. "name": "sap-migrate",
  139. "description": "S/4HANA custom-code migration engine: run a brownfield conversion as a tracked campaign — inventory custom (Z/Y) objects, flag unused code for decommission, run the S/4HANA-readiness ATC, triage findings, and remediate mechanical changes at scale on a sandbox. Companion to sap-dev-core (install that first).",
  140. "source": {
  141. "source": "git-subdir",
  142. "url": "https://github.com/sapdev-ai/sap-dev.git",
  143. "path": "plugins/sap-migrate",
  144. "ref": "main",
  145. "sha": "f75aa49b592b1642a83b78a703a4f6378afb0146"
  146. },
  147. "homepage": "https://sapdev.ai"
  148. },
  149. {
  150. "name": "sap-tcd",
  151. "description": "SAP transaction automation for business processes: Business Partner (BP), Material Master (MM01), and Sales Order (VA01) management. Companion to sap-dev-core (install that first — its shared scripts are required at runtime).",
  152. "source": {
  153. "source": "git-subdir",
  154. "url": "https://github.com/sapdev-ai/sap-dev.git",
  155. "path": "plugins/sap-tcd",
  156. "ref": "main",
  157. "sha": "ed622a03402f7d5a53cc33a2a3aa336ddc17205f"
  158. },
  159. "homepage": "https://sapdev.ai"
  160. },
  161. {
  162. "name": "ac-artifact-workflow",
  163. "description": "Artifact-driven development workflow inspired by Google Antigravity. Produces task lists, implementation plans, and walkthroughs to keep you engaged during AI-assisted development.",
  164. "source": {
  165. "source": "git-subdir",
  166. "url": "AlteredCraft/claude-code-plugins",
  167. "path": "plugins/artifact-workflow",
  168. "ref": "main",
  169. "sha": "0fcb09e09172d657aa95de152403be61f80ff1e5"
  170. },
  171. "homepage": "https://github.com/AlteredCraft/claude-code-plugins/tree/main/plugins/artifact-workflow"
  172. },
  173. {
  174. "name": "accelbyte-ai-plugins",
  175. "description": "Public AI coding agents, skills, and MCP servers for AccelByte.",
  176. "source": {
  177. "source": "url",
  178. "url": "https://github.com/AccelByte/ai-plugins.git",
  179. "sha": "81c40c3edff1c292c60a100a7a15badb65eaf731"
  180. },
  181. "homepage": "https://accelbyte.io/"
  182. },
  183. {
  184. "name": "accelerate",
  185. "description": "Insights, experimentation and personalization for WordPress. Self-learning loops to automatically iterate on content.",
  186. "source": {
  187. "source": "url",
  188. "url": "https://github.com/humanmade/accelerate-ai-toolkit.git",
  189. "sha": "011700dfa59203e8786960315856369bbcb58901"
  190. },
  191. "homepage": "https://accelerateplugin.com/"
  192. },
  193. {
  194. "name": "access-review",
  195. "description": "Generate access review reports",
  196. "source": {
  197. "source": "git-subdir",
  198. "url": "barnburner121/claude-plugin-marketplace",
  199. "path": "generated-plugins/access-review",
  200. "ref": "main",
  201. "sha": "6470b3dbdf66767d531844b597ddff183f4eb146"
  202. },
  203. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  204. },
  205. {
  206. "name": "accessibility-audit",
  207. "description": "Generate WCAG compliance audit reports",
  208. "source": {
  209. "source": "git-subdir",
  210. "url": "barnburner121/claude-plugin-marketplace",
  211. "path": "generated-plugins/accessibility-audit",
  212. "ref": "main",
  213. "sha": "6470b3dbdf66767d531844b597ddff183f4eb146"
  214. },
  215. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  216. },
  217. {
  218. "name": "accessibility-test",
  219. "description": "Generate accessibility tests (WCAG)",
  220. "source": {
  221. "source": "git-subdir",
  222. "url": "barnburner121/claude-plugin-marketplace",
  223. "path": "generated-plugins/accessibility-test",
  224. "ref": "main",
  225. "sha": "5f6b5d32d9f457dc9c2c7c0fb1d67dffc9140f33"
  226. },
  227. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  228. },
  229. {
  230. "name": "accountsos",
  231. "description": "AI-native UK accounting for limited companies and sole traders. Track transactions, manage VAT, monitor HMRC deadlines, log expenses, and handle invoices through natural language. Auto-fires UK tax knowledge skills (Corporation Tax, VAT, MTD, BADR, capital allowances) verified for the 2026/27 tax year. Pairs with your AccountsOS account via API key — connects to your live books so Claude can read balances, create transactions, check deadlines and answer UK tax questions with gov.uk source citations.",
  232. "source": {
  233. "source": "url",
  234. "url": "https://github.com/paulgosnell/accountsos-cowork-plugin.git",
  235. "sha": "9021162ceb3489bd7603efe1ac515818dccb2c69"
  236. },
  237. "homepage": "https://accounts-os.com"
  238. },
  239. {
  240. "name": "achilles-ep-delphi",
  241. "description": "Agent safety infrastructure (RiskOracle, NoLeak, MemGuard, SecureExec, FlowCore) and real-time DELPHI Oracle intelligence signals. x402 USDC micropayments on Base Mainnet. 19 tools across 2 MCP servers.",
  242. "source": {
  243. "source": "git-subdir",
  244. "url": "https://github.com/achilliesbot/achilles-ep-delphi-plugin-marketplace.git",
  245. "path": "plugins/achilles-ep-delphi",
  246. "ref": "main",
  247. "sha": "db9b1a2628ab8393b1ec73a8ed1fe167126fee45"
  248. },
  249. "homepage": "https://achillesalpha.onrender.com/"
  250. },
  251. {
  252. "name": "acp-find",
  253. "description": "Semantic search and stack composition over the Virtuals Protocol ACP marketplace. Find on-chain agents and offerings without leaving Claude Code.",
  254. "source": {
  255. "source": "url",
  256. "url": "https://github.com/oliver-pringle/acp-find-plugin.git",
  257. "sha": "aea8931d972a46b8eba03abf68dd672a67607eb0"
  258. },
  259. "homepage": "https://github.com/oliver-pringle/acp-find-plugin"
  260. },
  261. {
  262. "name": "acumatica-plugin",
  263. "description": "What's included\nFinance — invoices, bills, payments, journal entries, cash accounts\nInventory & Purchasing — stock items, purchase orders, receipts, vendors\nCRM — customers, leads, opportunities, contacts\nReports — aged receivables, aged payables, trial balance, customer statements, ad-hoc analysis",
  264. "source": {
  265. "source": "url",
  266. "url": "https://github.com/allanwei/claude-acu-try.git",
  267. "sha": "658ce547fdb065a172e9ac35315b53efef94188d"
  268. },
  269. "homepage": "https://github.com/allanwei/claude-acu-try"
  270. },
  271. {
  272. "name": "acuris",
  273. "description": "Two model-invoked skills for the Acuris APIs. `acuris-address` teaches the Acuris Address Validation & Geocoding SDK (`@acuris-geo/av-sdk`) — validate, geocode,\n reverse, autocomplete — plus React component recipes for Next.js, Centra, commercetools, and SCAYLE storefronts, plus migration recipes from libAddressDoctor\n (Informatica), Loqate, Experian QAS, Melissa, and Smarty. `acuris-eudi` teaches relying-party integration with the Acuris EUDI Wallet Verifier (OID4VP / SD-JWT VC\n at eudi.acuris-geo.com), covering session lifecycle, polling, and trust validation across EU 27 member-state TSLs. Each skill auto-activates only when your task\n mentions its area, so installing both costs almost no context.",
  274. "source": {
  275. "source": "url",
  276. "url": "https://github.com/Acuris-GmbH/acuris-agent-context.git",
  277. "sha": "5fb6ebe15d2f4c5a7258b33eec885a42a8d8296a"
  278. },
  279. "homepage": "https://acuris-gmbh.github.io/acuris-agent-context/"
  280. },
  281. {
  282. "name": "ada-pdf-compliance",
  283. "description": "Audit and fix PDF accessibility for ADA/Section 508/PDF-UA compliance — auto-generates alt text, link descriptions, structure trees, bookmarks, and metadata.\n\nKey features:\n- 18-check accessibility audit across Critical/Important/Advisory tiers\nAI-generated alt text for every image (Claude reads pages visually — charts get data descriptions, screenshots get content summaries)\n- AI-generated link descriptions replacing raw URLs with meaningful text\nStructure tree generation for untagged PDFs — headings, paragraphs, lists, figures, tables, BDC/EMC marked content, tagged annotations\n- Metadata auto-population — title, language, author, subject, PDF/UA identifier, display-title flag\n- Bookmark generation from slide titles\nBatch processing — process a whole folder, ask for author once, fix everything\n- Two processing paths — Path A (Acrobat structure tree + plugin fixes) or Path B (fully automated, no Acrobat needed)\n- Export results as markdown checklists or spreadsheets",
  284. "source": {
  285. "source": "url",
  286. "url": "https://github.com/anitasrinivasan/ada-pdf-compliance.git",
  287. "sha": "698a26e2f018849f1d42484b799a95cecc0fe83f"
  288. },
  289. "homepage": "https://github.com/anitasrinivasan/ada-pdf-compliance"
  290. },
  291. {
  292. "name": "adaptive-agent",
  293. "description": "Make your AI agent get stronger with use. Includes two skills: /skill-review (periodic audit of all skills for staleness, missing gotchas, and improvements) and /build-user-profile (build user profile from workspace context so the agent knows who you are). Also includes CLAUDE.md behavioral rules for skill self-improvement on friction, memory-to-skill feedback loops, and automatic skill gap detection. Inspired by Hermes Agent's four-layer memory architecture.",
  294. "source": {
  295. "source": "url",
  296. "url": "https://github.com/truenorth-lj/adaptive-agent-skill.git",
  297. "sha": "01e8c036e31ab8d8025c768007e22e12ceae5ae7"
  298. },
  299. "homepage": "https://zengineer.blog"
  300. },
  301. {
  302. "name": "adaptlypost",
  303. "description": "Post and schedule social media content to 9 platforms — Instagram, TikTok, YouTube, X, LinkedIn, Facebook, Pinterest, Threads, and Bluesky — from Claude Code.\n\nKey features:\n- Cross-post to multiple platforms in a single command, with per-platform caption overrides for X length limits, LinkedIn formatting, etc.\n- Schedule posts to any future time, or bulk schedule up to 100 posts at once\n- Draft → review → publish workflow so Claude saves drafts you can approve before they go live\n- Per-platform results: see which platforms succeeded, which failed, and retry only the failed ones\n- Media upload for images and videos, with TikTok privacy controls",
  304. "source": {
  305. "source": "url",
  306. "url": "https://github.com/adaptlypost/claude-plugin.git",
  307. "sha": "d2ea0e76d31508e45ae4a9b5b7f088999c67b027"
  308. },
  309. "homepage": "https://adaptlypost.com/features/agents"
  310. },
  311. {
  312. "name": "adcp-client",
  313. "description": "Adds the /adcp skill for calling AdCP advertising agent tools over MCP or A2A, running protocol compliance scenarios, and querying the AdCP registry. Includes built-in test agents for zero-config use.",
  314. "source": {
  315. "source": "url",
  316. "url": "https://github.com/adcontextprotocol/adcp-client.git",
  317. "sha": "d7242bbf6c1e8ec6bbde33e87a65fbb2cbfbddf9"
  318. },
  319. "homepage": "https://github.com/adcontextprotocol/adcp-client"
  320. },
  321. {
  322. "name": "adobe-for-creativity",
  323. "description": "Brings together Adobe Creative Cloud tools for images, vectors, design, and video. Edit multiple assets at once, adapt for different platforms, and complete multi-step creative workflows for polished results.",
  324. "source": {
  325. "source": "git-subdir",
  326. "url": "https://github.com/adobe/skills.git",
  327. "path": "plugins/creative-cloud/adobe-for-creativity",
  328. "ref": "main",
  329. "sha": "cbaeec4138c6006fcdb499c94f545c2a4fa8f568"
  330. },
  331. "homepage": "https://github.com/adobe/skills"
  332. },
  333. {
  334. "name": "adr-creator",
  335. "description": "Create Architecture Decision Records",
  336. "source": {
  337. "source": "git-subdir",
  338. "url": "barnburner121/claude-plugin-marketplace",
  339. "path": "generated-plugins/adr-creator",
  340. "ref": "main",
  341. "sha": "5f6b5d32d9f457dc9c2c7c0fb1d67dffc9140f33"
  342. },
  343. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  344. },
  345. {
  346. "name": "adr-writer",
  347. "description": "Interactive ADR (Architecture Decision Record) writing tool with PRD traceability. Facilitates architectural decisions through guided Q&A sessions.",
  348. "source": {
  349. "source": "url",
  350. "url": "https://github.com/haandol/adr-writer.git",
  351. "sha": "54a0f5ff1d49782cb3e93cc83aa783a4eee70a7c"
  352. },
  353. "homepage": "https://github.com/haandol/adr-writer"
  354. },
  355. {
  356. "name": "ads-agent",
  357. "description": "AdsAgent turns Claude into your always-on Google Ads analyst. Audit account health, set up new campaigns from scratch, analyze Quality Score and Ad Rank, manage keywords and bids, mine search terms for negatives, generate A/B-tested ad copy, configure tracking, and run bulk operations across hundreds of keywords — all through conversation. No dashboards, no spreadsheets, no clicking through the Google Ads UI.\nUnder the hood: 40+ MCP tools with full read/write access to your Google Ads data, plus three built-in skills — /ads for campaign management, /ads-audit for account health scoring, and /ads-copy for ad copywriting.",
  358. "source": {
  359. "source": "url",
  360. "url": "https://github.com/nowork-studio/adsagent-plugin.git",
  361. "sha": "11c86e21bb3d39639a8ab16b1c0e3176f924b633"
  362. },
  363. "homepage": "https://www.adsagent.org/"
  364. },
  365. {
  366. "name": "adspirer-ads-agent",
  367. "description": "Cross-platform ad management for Google Ads, Meta Ads, TikTok Ads, and LinkedIn Ads. 91 tools for keyword research, campaign creation, performance analysis, and budget optimization.",
  368. "category": "productivity",
  369. "source": {
  370. "source": "url",
  371. "url": "https://github.com/amekala/adspirer-mcp-plugin.git",
  372. "sha": "e3067cec8803e28da91834d0f38e0405ad23429b"
  373. },
  374. "homepage": "https://www.adspirer.com"
  375. },
  376. {
  377. "name": "adup-ai-marketing-agent",
  378. "description": "AdUp for Claude\nConnect your entire marketing stack to Claude Code. Ask questions about your ad performance in plain English.\n\nWhat you can do:\n\nCross-platform overview — See total spend, ROAS, and performance across all channels at once\nFacebook/Instagram Ads — Campaign analysis, creative fatigue detection, audience breakdowns, learning phase diagnosis\nGoogle Ads — Search, Shopping, and Performance Max analysis, Quality Score diagnostics, impression share\nGoogle Analytics 4 — Sessions, revenue, acquisition channels, funnel drop-off, conversion events\nLinkedIn & TikTok Ads — Platform-specific performance and optimization recommendations\nAd fatigue detection — Spot rising frequency, falling CTR, and creative exhaustion before it hurts\nBudget optimization — Propose budget shifts based on performance data\nExecutive reports — Monday briefings, client-ready reports, anomaly alerts\n\nBuilt for agencies — Switch between clients instantly. Works with HubSpot, Intercom, and Google Search Console too.",
  379. "source": {
  380. "source": "url",
  381. "url": "https://github.com/Ad-Up-VC/adup-claude-plugin.git",
  382. "sha": "5ac4e325f14cb2446328ab89cba890411cfae3e0"
  383. },
  384. "homepage": "https://www.adup.io"
  385. },
  386. {
  387. "name": "adversarial-review",
  388. "description": "Adversarial planning and code review workflow between Claude Code and OpenAI Codex CLI. Enables iterative convergence loops where Claude creates plans/code and Codex provides critical review.",
  389. "source": {
  390. "source": "url",
  391. "url": "https://github.com/bobby-beckmann/adversarial-review.git",
  392. "sha": "45e0effc5fcf97544a192ead64afbc00a68fc114"
  393. },
  394. "homepage": "https://github.com/bobby-beckmann/adversarial-review"
  395. },
  396. {
  397. "name": "adversarial-spec",
  398. "description": "Iteratively refine product specs through multi-model debate until consensus. Claude actively participates alongside GPT, Gemini, Grok, and other models. Includes interview mode, early agreement verification, and optional Telegram integration.",
  399. "source": {
  400. "source": "url",
  401. "url": "https://github.com/zscole/adversarial-spec.git",
  402. "sha": "f90cf0c36c3999b8dc272c9c06dee9846076f369"
  403. },
  404. "homepage": "https://github.com/zscole/adversarial-spec"
  405. },
  406. {
  407. "name": "aeo-brand-scan",
  408. "description": "Free AEO / GEO / AI search visibility check. Scores how ChatGPT, Claude, and Perplexity describe your brand vs competitors. Runs inside Claude Code in 30 seconds.",
  409. "source": {
  410. "source": "url",
  411. "url": "https://github.com/WannabDad/aeo-brand-scan.git",
  412. "sha": "6df43ce936bff8e9ad757832c44b315f7242b63e"
  413. },
  414. "homepage": "https://github.com/WannabDad/aeo-brand-scan"
  415. },
  416. {
  417. "name": "aeon-flux",
  418. "description": "Bash Loop operating mode for Claude Code — action over explanation. Eliminates verbose preamble and apologies, replacing them with tight do-verify-fix feedback loops. Features intelligent context preservation with attention markers, reliable /abort command for subagent control, and checkpoint/resume for long tasks. Inspired by Geoffrey Huntley's Ralphy Loop with key improvements for reliability.",
  419. "source": {
  420. "source": "url",
  421. "url": "https://github.com/TheGlitchKing/aeon-flux.git",
  422. "sha": "41e0a1146c709dc4c8689794293c9cc35c441215"
  423. },
  424. "homepage": "https://github.com/TheGlitchKing/aeon-flux"
  425. },
  426. {
  427. "name": "ag2-claude-plugins",
  428. "description": "A Claude Code plugin marketplace for building AG2 (AutoGen) agents and multi-agent workflows. Includes 5 plugins: agent scaffolding (ConversableAgent + A2A server wiring), workflow patterns (two-agent chat, sequential, group chat, nested chat), tool building (function tools + API connectors), agent code review (prompt quality, security, tool contracts), and architecture guidance (pattern selection, system prompt engineering). Apache-2.0 licensed.",
  429. "source": {
  430. "source": "url",
  431. "url": "https://github.com/ag2ai/ag2-claude-plugins.git",
  432. "sha": "08f96234de88b2e914e52069a60eceb210339ced"
  433. },
  434. "homepage": "https://ag2ai.github.io/ag2-claude-plugins"
  435. },
  436. {
  437. "name": "agent-advisor",
  438. "description": "Real-time dashboard showing Claude Code subagent status and activity\nAnalyze their performances and offer improvements",
  439. "source": {
  440. "source": "url",
  441. "url": "https://github.com/cfirz/agent-advisor.git",
  442. "sha": "62e20857eb815b9cfb3301982ecb9c025c25fd2a"
  443. },
  444. "homepage": "https://github.com/cfirz/agent-advisor/blob/main/README.md"
  445. },
  446. {
  447. "name": "agent-archive",
  448. "description": "Agent Archive connects Claude to a community knowledge base of agent operational learnings — fixes, workarounds, environment quirks, API behaviors, and workflows contributed by agents and developers worldwide. When you hit an unfamiliar error or tool, Claude automatically searches the archive before starting work. When you solve something non-trivial, Claude drafts a post proposal in the background. Between sessions, a local wiki at ~/.claude/memory/problem-solving/ captures hard-won knowledge privately. Nothing is posted to the community without your explicit approval.",
  449. "source": {
  450. "source": "url",
  451. "url": "https://github.com/agent-archive/claude-code-agent-archive.git",
  452. "sha": "0ff87ead6ea9195b61b187fe97fda3be38a2df3b"
  453. },
  454. "homepage": "https://www.agentarchive.io/claude-code"
  455. },
  456. {
  457. "name": "agent-blueprint-skills",
  458. "description": "Open-source AI agent skills for enterprise deployment. Three skills: (1) ServiceNow AI Agent Studio reference with data model, entity mapping, tool types, prompting patterns, and browser navigation. (2) Vendor-agnostic agent deployment methodology with phased rollout, pilot-first approach, and test gates. (3) Multi-tool research agent with automatic depth routing from free to paid tools. Works with Claude Code, OpenAI Codex, and any coding agent via the Agent Skills open standard.",
  459. "source": {
  460. "source": "git-subdir",
  461. "url": "https://github.com/agent-blueprint/agent-blueprint-skills.git",
  462. "path": "plugins/agent-blueprint-skills",
  463. "ref": "main",
  464. "sha": "d755f380973227a88d9eb816f251ff66d1d99206"
  465. },
  466. "homepage": "https://agentblueprint.ai"
  467. },
  468. {
  469. "name": "agent-comm",
  470. "description": "Agent-agnostic intercommunication system. Lets AI coding agents — talk to each other, share state, and coordinate work in real time.",
  471. "source": {
  472. "source": "url",
  473. "url": "https://github.com/keshrath/agent-comm.git",
  474. "sha": "02b7fd00ef9636b9b581d316efb6c1e94e298d7d"
  475. },
  476. "homepage": "https://github.com/keshrath/agent-comm"
  477. },
  478. {
  479. "name": "agent-discover",
  480. "description": "MCP server registry and on-demand proxy for AI coding agents. Browse the official MCP Registry, install/activate/deactivate servers from a local dashboard, and proxy their tools with namespace prefixing. Per-server secrets, health probes with error-count tracking, tool-call metrics, and a real-time call log via WebSocket.",
  481. "source": {
  482. "source": "url",
  483. "url": "https://github.com/keshrath/agent-discover.git",
  484. "sha": "46b337711d108b03f4867a5c534adb10ea5aed7b"
  485. },
  486. "homepage": "https://github.com/keshrath/agent-discover"
  487. },
  488. {
  489. "name": "agent-discovery",
  490. "description": "Agent Discovery lets developers discover, review, install, and manage AI agent configurations from a curated catalog of 687+ entries — with zero setup. It ships a pre-built SQLite index of agents, skills, and instructions from awesome-copilot and GitHub's Agent Factory, so search is instant and requires no API keys or authentication. The interactive /recommend flow analyzes your project's tech stack, surfaces relevant agents with explanations, then guides you through reviewing content before installing, customizing in your editor, or assembling multiple agents into a coordinated team with an agentic lead. Additional /list and /edit commands let you manage everything you've installed without leaving Claude Code.",
  491. "source": {
  492. "source": "url",
  493. "url": "https://github.com/svmnikhil/agent-discovery.git",
  494. "sha": "ffb22d3d1d9ba830a485c8009b89cd90573ffc17"
  495. },
  496. "homepage": "https://github.com/svmnikhil/agent-discovery#agent-discovery"
  497. },
  498. {
  499. "name": "agent-discussion",
  500. "description": "Coordinate multi-agent debates across different AI platforms (Claude Code, Antigravity, Copilot, Gemini CLI, etc.) using a shared file protocol. Each agent reads one skill and handles everything autonomously — intros, turn-taking, and consensus.",
  501. "source": {
  502. "source": "url",
  503. "url": "https://github.com/cyrusxyl/agent-discussion.git",
  504. "sha": "67334880155400eff11c76b6e4cb3537240738f2"
  505. },
  506. "homepage": "https://github.com/cyrusxyl/agent-discussion"
  507. },
  508. {
  509. "name": "agent-estimate",
  510. "description": "Effort estimation for AI coding agents. PERT three-point estimation with METR reliability thresholds, modifier stacks (spec clarity, warm context, agent fit), and wave planning for multi-agent parallel execution. Supports single tasks, batch files, and GitHub issues.",
  511. "source": {
  512. "source": "url",
  513. "url": "https://github.com/haoranc/agent-estimate.git",
  514. "sha": "7b30943bac5648cf183f3d050baa6fea5485b8a9"
  515. },
  516. "homepage": "https://github.com/haoranc/agent-estimate"
  517. },
  518. {
  519. "name": "agent-guardrails-template",
  520. "description": "Core safety skills for AI-assisted development: Four Laws, Three Strikes, production-first, scope validation, and environment separation. 11 skills enforce guardrails on every operation so agents build at full velocity without breaking production.",
  521. "source": {
  522. "source": "url",
  523. "url": "https://github.com/TheArchitectit/agent-guardrails-template.git",
  524. "sha": "4af9ff36ba97c201e94838ff88a749cea5706be7"
  525. },
  526. "homepage": "https://github.com/TheArchitectit/agent-guardrails-template"
  527. },
  528. {
  529. "name": "agent-handoff",
  530. "description": "Strict 3-stage handoff workflow for coding agents — plan → execute → verify — with disk-backed state for cross-context handoff.",
  531. "source": {
  532. "source": "url",
  533. "url": "https://github.com/WillowRyu/agent-handoff.git",
  534. "sha": "6179248b0a644cc8695f9f9dedd883587c4d4378"
  535. },
  536. "homepage": "https://github.com/WillowRyu/agent-handoff"
  537. },
  538. {
  539. "name": "agent-knowledge",
  540. "description": "Cross-session memory for AI coding agents. A git-synced Markdown knowledge base with hybrid semantic + TF-IDF search, typed knowledge graph (11 edge types with directed BFS traversal), confidence/decay scoring, and automatic session distillation with secrets scrubbing. Reads session history from Claude Code, Cursor, and OpenCode.",
  541. "source": {
  542. "source": "url",
  543. "url": "https://github.com/keshrath/agent-knowledge.git",
  544. "sha": "f92dfaea3df6a8c5c34b14bc0b032b02f1acfb9b"
  545. },
  546. "homepage": "https://github.com/keshrath/agent-knowledge"
  547. },
  548. {
  549. "name": "agent-manager",
  550. "description": "Spawn and manage autonomous background agents with persistent state across sessions",
  551. "source": {
  552. "source": "url",
  553. "url": "https://github.com/devhimanshulohani/claude-agent-manager.git",
  554. "sha": "0ff9c3156fa120725d263aac647e07b4be28f64d"
  555. },
  556. "homepage": "https://github.com/devhimanshulohani/claude-agent-manager#readme"
  557. },
  558. {
  559. "name": "agent-memory",
  560. "description": "Save 60-90% on LLM token costs with intelligent memory compression. agent-memory automatically compresses tool output into structured observations, shares context across agents via a memory bus, and injects only relevant memory into each prompt — keeping your token budget under control. Features: auto-compression hooks (PostToolUse), token-budgeted context injection (SessionStart), semantic search via FTS5, cross-session persistence, and a token economics dashboard showing compression ratios and savings.",
  561. "source": {
  562. "source": "url",
  563. "url": "https://github.com/Keshab0310/agent-memory.git",
  564. "sha": "f92863ae94475f83007e58b02127d2c9788a2445"
  565. },
  566. "homepage": "https://github.com/Keshab0310/agent-memory#readme"
  567. },
  568. {
  569. "name": "agent-ping",
  570. "description": "Plays a sound when Claude finishes, asks a question, or needs permission — so you can step away and come back when needed. Configurable sounds, volume, and alert modes.",
  571. "source": {
  572. "source": "url",
  573. "url": "https://github.com/DavidWilsby/agent-ping.git",
  574. "sha": "2cc28dbe60a3c476ae3fb6b9cd24fc7f43f9da6e"
  575. },
  576. "homepage": "https://github.com/DavidWilsby/agent-ping"
  577. },
  578. {
  579. "name": "agent-protocols",
  580. "description": "Structured engineering protocols that make AI coding agents work like senior engineers.",
  581. "source": {
  582. "source": "url",
  583. "url": "https://github.com/arneesh/agent-protocols.git",
  584. "sha": "de768e04e410437e11b2f3a58b59f980cbc73159"
  585. },
  586. "homepage": "https://github.com/arneesh/agent-protocols"
  587. },
  588. {
  589. "name": "agent-recall",
  590. "description": "Persistent memory for AI coding agents. SQLite knowledge graph with scoped entities, MCP tools, and LLM-summarized briefings.",
  591. "source": {
  592. "source": "url",
  593. "url": "https://github.com/mnardit/agent-recall.git",
  594. "sha": "dcf21b5cc9691e1371299917e2e474fb82e07cab"
  595. },
  596. "homepage": "https://max.nardit.com/agent-recall"
  597. },
  598. {
  599. "name": "agent-runway",
  600. "description": "Prevents subagent tech debt by injecting project architectural context (module boundaries, CLAUDE.md rules, conventions) into every subagent's prompt. Validates code placement and conventions after writes with self-correction directives.",
  601. "source": {
  602. "source": "url",
  603. "url": "https://github.com/rennf93/agent-runway.git",
  604. "sha": "15c21c202492c6989791d2182be402b05e429139"
  605. },
  606. "homepage": "https://github.com/rennf93/agent-runway#readme"
  607. },
  608. {
  609. "name": "agent-smith",
  610. "description": "Agent Smith adds two slash commands to Claude Code: /analyze-agent performs a full configuration audit across 7 evaluation pillars (Security, Instruction Clarity, Configuration Quality, Context Efficiency, Command Design, Hook Safety, MCP Integration), scores each area, identifies issues by severity, and walks you through an interactive fix workflow. /create-agent scaffolds a new configuration with security deny rules and best practices. The tool is honest about its scope — it only measures user-configurable components and clearly states what's outside its reach.",
  611. "source": {
  612. "source": "url",
  613. "url": "https://github.com/maxencemeloni/claude-code-agent-smith.git",
  614. "sha": "88ee510da636afc8d92fd06d95b6d43f717afe0b"
  615. },
  616. "homepage": "https://agent-smith.mmapi.fr/"
  617. },
  618. {
  619. "name": "agent-synapse",
  620. "description": "Let multiple Claude Code sessions talk to each other across projects. Each session gets a name, sends messages, checks its inbox, and sees who's online.",
  621. "source": {
  622. "source": "url",
  623. "url": "https://github.com/DisposableByDefault/agent-synapse.git",
  624. "sha": "a135ca5387a9ed5cb3cb5b04ce68d3b041850f30"
  625. },
  626. "homepage": "https://github.com/DisposableByDefault/agent-synapse"
  627. },
  628. {
  629. "name": "agent-tasks",
  630. "description": "Pipeline-driven task management for AI coding agents. An MCP server with stage-gated pipelines, multi-agent collaboration, and a real-time kanban dashboard. Tasks flow through configurable stages — backlog, spec, plan, implement, test, review, done — with dependency tracking, approval workflows, artifact versioning, and threaded comments.",
  631. "source": {
  632. "source": "url",
  633. "url": "https://github.com/keshrath/agent-tasks.git",
  634. "sha": "2b421ca49141b82ad93723cabe21ed55b5270003"
  635. },
  636. "homepage": "https://github.com/keshrath/agent-tasks"
  637. },
  638. {
  639. "name": "agent-trace-triage",
  640. "description": "Agent Trace Triage is a Claude Code plugin for developers building agentic AI systems (LangGraph, CrewAI, custom tool loops, MCP agents).\n\nWhen an agent run fails, stuck in a loop, wrong tool, or burning tokens. the user runs /agent-trace-triage with a JSON/JSONL trace file. The plugin:\n\n• Parses traces (JSONL, OpenAI tool_calls, partial LangSmith/OTEL-style exports)\n• Detects loops deterministically (identical repeat, ping-pong, retry-without-progress) via bundled Node scripts\n• Classifies failures into five buckets: tool selection, arguments, execution, orchestration, recovery policy\n• Writes a markdown triage report with targeted fix recommendations\n• Scaffolds regression tests (pytest / vitest templates)\n\nNo MCP servers, no external API calls, no npm dependencies. \n\nRequires Node.js 18+ for local scripts only. MIT licensed.",
  641. "source": {
  642. "source": "url",
  643. "url": "https://github.com/WasayAbid/agent-trace-triage.git",
  644. "sha": "03285a0b6fa6a9338782fe631e1966d68f9a2aba"
  645. },
  646. "homepage": "https://github.com/WasayAbid/agent-trace-triage"
  647. },
  648. {
  649. "name": "agent4s",
  650. "description": "Scala code intelligence for AI coding agents. 35 commands — search,\njump-to-definition, find references, call-graph, dead code detection, semantic\nrename, bug-hunt with taint analysis, scaffolding — all without a build\nserver or compilation. Cold index 2.7s, warm 349ms on 18k files. Bug-hunt\nscans 45 vulnerability patterns (SQL injection, XSS, SSRF, hardcoded secrets, weak crypto, concurrency bugs) with cross-file taint analysis. SemanticDB integration for type-aware mode when compiled artifacts are available. Native binaries for macOS, Linux, and Windows. Works as a Claude Code plugin, MCP server (Cursor, Windsurf, Cline), or standalone CLI.",
  651. "source": {
  652. "source": "git-subdir",
  653. "url": "https://github.com/scala-digest/agent4s.git",
  654. "path": "plugins/agent4s",
  655. "ref": "main",
  656. "sha": "f1cfbc864692783694aa4a81784733864591a540"
  657. },
  658. "homepage": "https://github.com/scala-digest/agent4s/blob/main/README.md"
  659. },
  660. {
  661. "name": "agented",
  662. "description": "A text editor for LLMs, not humans. Optimized for the model's cost model: fewer round trips per task (no Read-before-Edit; conflict responses carry the new content, so you reconcile in one call instead of pre-reading every time), tighter token budget (lean tab output, not JSON envelopes; ~5x denser than the built-in Read/Edit shape), inline LSP diagnostics on every save (gopls, rust-analyzer-with-clippy, tsserver+eslint findings come back as diag lines instead of round-tripping through cargo / go build), reactive drift detection (external editor or formatter writes are folded into the undo tree as new edits, not silently clobbered or lost), and a branching undo tree that remembers the branches the agent abandoned — because that's often where the interesting work was. Three-way merge for concurrent agents, atomic multi-file refactors, cross-session memory via per-file annotations.",
  663. "source": {
  664. "source": "git-subdir",
  665. "url": "https://github.com/frane/agented.git",
  666. "path": "plugin",
  667. "ref": "master",
  668. "sha": "09d9429cd1f1c239164b16b672e9b359baef3610"
  669. },
  670. "homepage": "https://github.com/frane/agented"
  671. },
  672. {
  673. "name": "agentforce-adlc",
  674. "description": "Build, test, and optimize Salesforce Agentforce agents in Claude Code. Three skills cover the full agent development lifecycle: /developing-agentforce — author Agent Script .agent files, discover org targets, scaffold stubs, deploy, and run safety reviews; /testing-agentforce — smoke tests, batch execution, and action validation; /observing-agentforce — analyze production session traces and drive improvements. Safety guardrails enforced across every phase.",
  675. "source": {
  676. "source": "url",
  677. "url": "https://github.com/SalesforceAIResearch/agentforce-adlc.git",
  678. "sha": "d16d14ac7f817336e21bf9392cf51b6cac6194d8"
  679. },
  680. "homepage": "https://github.com/SalesforceAIResearch/agentforce-adlc/"
  681. },
  682. {
  683. "name": "agentic-beta-testers",
  684. "description": "AI-powered browser testing against any URL using personality-driven agents -- speedrunners, chaos gremlins, skeptical executives -- each surfacing different categories of usability and reliability issues.",
  685. "source": {
  686. "source": "url",
  687. "url": "https://github.com/rjspence3/claude-beta-tester.git",
  688. "sha": "2d609bef5a419d0f0d34d6107079929f61186922"
  689. },
  690. "homepage": "https://github.com/rjspence3/claude-beta-tester"
  691. },
  692. {
  693. "name": "agentic-commerce",
  694. "description": "13 commerce plugins covering Shopify, Magento, BigCommerce, WooCommerce, Salesforce, Stripe, and agentic commerce protocols.",
  695. "category": "development",
  696. "source": {
  697. "source": "url",
  698. "url": "https://github.com/OrcaQubits/agentic-commerce-claude-plugins.git",
  699. "sha": "7473b6a435a47813373baf70f802f2e47587e6d0"
  700. },
  701. "homepage": "https://github.com/OrcaQubits/agentic-commerce-claude-plugins"
  702. },
  703. {
  704. "name": "agentic-council",
  705. "description": "Convene a team of specialist agents out of a 20-agent roster in a 3-round deliberation council on your hardest engineering decisions. Walk away with a unified design and a phased build plan.",
  706. "source": {
  707. "source": "url",
  708. "url": "https://github.com/dtsong/agentic-council.git",
  709. "sha": "36cf1d3338993408d5de9b86dcbd61432ca23db8"
  710. },
  711. "homepage": "https://github.com/dtsong/agentic-council"
  712. },
  713. {
  714. "name": "agentic-guardrails",
  715. "description": "A set of strict, senior-level engineering guardrails and security standards for AI coding agents.",
  716. "source": {
  717. "source": "url",
  718. "url": "https://github.com/l-filice89/agentic-guardrails.git",
  719. "sha": "8313dcfa9cd58fd39161b36a7059af5ed2cf7e4a"
  720. },
  721. "homepage": "https://github.com/l-filice89/agentic-guardrails"
  722. },
  723. {
  724. "name": "agentic-security",
  725. "description": "Agentic-Security is a powerful Claude Code plugin that automatically performs Application Security Testing (SAST, SCA, secrets detection, and more). Think of it as the easy button for making your Claude-generated code safe and secure.",
  726. "source": {
  727. "source": "url",
  728. "url": "https://github.com/Clear-Capabilities/agentic-security.git",
  729. "sha": "cda40a57f09a442702503d26c2d3b6cb9802b873"
  730. },
  731. "homepage": "https://www.clearcapabilities.com/products/agentic-security"
  732. },
  733. {
  734. "name": "agentic-swe",
  735. "description": "agentic-swe is a Claude Code plugin that turns a normal repo session into a structured software-engineering pipeline—without a separate runtime.\nIt ships markdown policies, phase prompts, slash commands, templates, and 135+ specialist subagents. Work is organized with explicit states, human gates (e.g. ambiguity and approval), evidence-friendly artifacts under .worklogs/<id>/, and three pipeline tracks (lean, standard, rigorous) so you can match rigor to risk. Session hooks load policy early; /install helps merge CLAUDE.md into a target project safely.",
  736. "source": {
  737. "source": "url",
  738. "url": "https://github.com/surajSFDC/agentic-swe.git",
  739. "sha": "f1927500c3c738f1077c66042c41b6da11931e09"
  740. },
  741. "homepage": "https://surajsfdc.github.io/agentic-swe"
  742. },
  743. {
  744. "name": "agentic-teams",
  745. "description": "A modular plugin that packs specialised agents into teams and allows user to interact with them at the higher level of abstraction. Like with real-world company departments.",
  746. "source": {
  747. "source": "git-subdir",
  748. "url": "https://github.com/rustamfi/agentic-teams.git",
  749. "path": "plugins/dev-team",
  750. "ref": "main",
  751. "sha": "756319d0185c05108c51ee4d83e07ffe93da5004"
  752. },
  753. "homepage": "https://github.com/rustamfi/agentic-teams"
  754. },
  755. {
  756. "name": "agenticmail",
  757. "description": "Give every Claude Code subagent its own real email address and phone number, all self hosted on the user's machine. AgenticMail runs a local mail server (Stalwart in a Colima or Docker container) so each agent has a working `<name>@localhost` inbox, an identity, an API key, and a persona. When a teammate is CC'd on an email they wake up as a Claude Code subagent under your existing Claude OAuth, read the full thread, decide if it is their turn, and either reply to all or stay silent. The thread is the workspace and the audit trail. There is no central orchestrator, no separate Anthropic key per agent, no data leaving your machine, and no polling because everything is push based over SSE. The plugin exposes three skills (`install`, `create-agent`, `coordinate`) that handle the one time bootstrap and let the host session kick off multi agent work with a single email. Behind the plugin sit five npm packages doing the real work: an Express API, an MCP server with 62 tools across email, SMS, contacts, drafts, templates, rules, search, scheduling, and agent coordination, a dispatcher daemon, a core SDK, and the CLI. Reliability rails include a per agent per thread wake budget that stops reply loops, a 60 second recent reply check in every persona so two agents who both think it is their turn back off, and an outbound content guard that holds risky outbound mail for owner approval. Tested on Node 22 and Node 25 with 429 passing tests across the workspace.",
  758. "source": {
  759. "source": "git-subdir",
  760. "url": "https://github.com/agenticmail/agenticmail.git",
  761. "path": "plugin",
  762. "ref": "main",
  763. "sha": "b95f52ed97732e1bf7dbc6d82f5862a28f5f54a4"
  764. },
  765. "homepage": "https://github.com/agenticmail/agenticmail"
  766. },
  767. {
  768. "name": "agentiqa",
  769. "description": "AI-powered QA testing agent for web and mobile apps. Agentiqa explores your app visually - like a real user with fresh eyes - and reports bugs with severity, confidence scores, and step-by-step reproduction instructions. No selectors, no scripts, no test code to maintain. Just describe what to test in plain English.\n\nSupports web (any URL or localhost), Android (emulator/device), and iOS (simulator/device). Finds visual bugs, logical errors, UX issues, and accessibility problems that unit tests and linters miss.",
  770. "source": {
  771. "source": "url",
  772. "url": "https://github.com/Agentiqa/agentiqa-plugin.git",
  773. "sha": "0c9ccd26daad8f6ee83e5d82d7d564b16cf46cd9"
  774. },
  775. "homepage": "https://agentiqa.com/en"
  776. },
  777. {
  778. "name": "agentiqa-plugin",
  779. "description": "Repo not found",
  780. "source": {
  781. "source": "url",
  782. "url": "https://github.com/Agentiqa/agentiqa-plugin.git",
  783. "sha": "0c9ccd26daad8f6ee83e5d82d7d564b16cf46cd9"
  784. },
  785. "homepage": "https://github.com/Agentiqa/agentiqa-plugin"
  786. },
  787. {
  788. "name": "agentmancy",
  789. "description": "AI Agent & Skill Builder for Claude Code, OpenCode, and Gemini.\n\nA free alternative to summonaikit that leverages your already existing subscriptions to Claude.",
  790. "source": {
  791. "source": "url",
  792. "url": "https://github.com/vinngo/agentmancy.git",
  793. "sha": "210bb9b346e123c500037a790110c58bcfe23110"
  794. },
  795. "homepage": "https://github.com/vinngo/agentmancy"
  796. },
  797. {
  798. "name": "agentnews",
  799. "description": "Connect Claude to AgentNews — the frontpage of the agentic internet. Read the latest AI agent news, search posts, and submit content via MCP. Includes slash commands for quick access and a skill that automatically surfaces relevant agent news.",
  800. "source": {
  801. "source": "url",
  802. "url": "https://github.com/Kaizor7/agentnews-plugin.git",
  803. "sha": "01bca2a0b68e2acb11470029873ba4b83be597ca"
  804. },
  805. "homepage": "https://agentnews.xyz"
  806. },
  807. {
  808. "name": "agentops",
  809. "description": "Enterprise guardrails, delivery lifecycle, and self-evolution for Claude Code. Wraps every session in 7 security layers (path validation, command validation, injection scanning, credential redaction, exfiltration detection), structures work with the STAR methodology, and orchestrates full project builds from vision to merged PR through an 8.5-phase lifecycle with TDD enforcement, wave-based parallel execution, and two-stage code review. Includes 37 commands, 44 hooks, 12 specialist agents, 49 templates, and 32+ feature flags.",
  810. "source": {
  811. "source": "url",
  812. "url": "https://github.com/garethdaine/agentops.git",
  813. "sha": "d550b464e88bc3810eb47c466249516e8ca366d9"
  814. },
  815. "homepage": "https://github.com/garethdaine/agentops"
  816. },
  817. {
  818. "name": "agentpowers",
  819. "description": "AgentPowers is a marketplace plugin that lets you search, browse, purchase, install, and manage premium AI skills and agents directly inside Claude Code. It provides 26 MCP tools covering marketplace discovery (search, categories, reviews, security scans, seller profiles), full account management (login, logout, profile), Stripe-powered purchase workflows with auto-install, and multi-platform skill management across 12+ AI tools including Claude Code, Claude Desktop, Cursor, Codex, Windsurf, Gemini CLI, and more. Includes 4 MCP resources for proactive context and 2 guided prompts for skill discovery and purchase flows.",
  820. "source": {
  821. "source": "url",
  822. "url": "https://github.com/AgentPowers-AI/agentpowers-plugin.git",
  823. "sha": "19b9c78e6af52fa5279226fee057a35b3f367c83"
  824. },
  825. "homepage": "https://agentpowers.ai"
  826. },
  827. {
  828. "name": "agentsatlas",
  829. "description": "AgentsAtlas is a minimal, opinionated end-to-end workflow for Claude Code (also available as Codex skills). Eight slash commands take a project from setup through planning, execution, review, and milestone completion:\n\n/atlas:init, \n/atlas:plan, \n/atlas:execute,\n/atlas:status, \n/atlas:sync, \n/atlas:triage, \n/atlas:review, \n/atlas:complete. \n/atlas:execute \n\nRuns each 3–5-task plan in a fresh subagent (clean ~200k-token context) so quality doesn't degrade across a long run, while a small CLAUDE.md plus .planning/STATE.md and ROADMAP.md keep session continuity without context bloat. \n\nIt also ships 16 development \"discipline\" skills: debugging, testing,\nverifying, refactoring, security-audit, scaffolding, committing, creating-pr, and more enforcing root-cause-first investigation, evidence-before-claims verification, and test-first development. \n\n# Install globally (available in all projects)\nnpx agents-atlas --global\n\n# Or install locally (current project only)\nnpx agents-atlas --local\n\nMIT licensed; no telemetry, no network calls beyond Anthropic, and no bypass-permissions requirement.",
  830. "source": {
  831. "source": "url",
  832. "url": "https://github.com/AvinashP/AgentsAtlas.git",
  833. "sha": "72e52289e6c42e45dab5870a86d9c3b914f94fdd"
  834. },
  835. "homepage": "https://github.com/AvinashP/AgentsAtlas#readme"
  836. },
  837. {
  838. "name": "agnix",
  839. "description": "Lint agent configurations before they silently fail. 414 validation rules across Claude Code, Codex CLI, OpenCode, Cursor, GitHub Copilot, Gemini CLI, Cline, Windsurf, Roo Code, Amp, and Kiro - validates CLAUDE.md, AGENTS.md, SKILL.md, hooks.json, MCP server configs, and plugin manifests. Auto-fix included for safe issues; SARIF output for GitHub Code Scanning. Distributed as CLI (npm + Cargo), official GitHub Action (`agent-sh/agnix`), and IDE extensions for VS Code, JetBrains, Neovim, and Zed. Rules sourced from official specs, academic research on agent prompt design, and real-world failure patterns from production deployments. Mentioned in awesome-claude-code.",
  840. "source": {
  841. "source": "url",
  842. "url": "https://github.com/agent-sh/agnix.git",
  843. "sha": "c9e47613dc1d1eb63fb7f42ceced8f06df5b326e"
  844. },
  845. "homepage": "https://agent-sh.github.io/agnix/"
  846. },
  847. {
  848. "name": "ai-adoption-playbook",
  849. "description": "Structured AI adoption framework for leaders — diagnostic assessments, blocker analysis, rollout plans, and board-ready narratives",
  850. "source": {
  851. "source": "url",
  852. "url": "https://github.com/adimango/ai-adoption-playbook.git",
  853. "sha": "bf2fef49d48f6c89f7dbc95743c1f6f7e4d68fa4"
  854. },
  855. "homepage": "https://github.com/adimango/ai-adoption-playbook"
  856. },
  857. {
  858. "name": "ai-brainmap",
  859. "description": "Live Context Visualizer for Claude Code — watch Claude think in real time as an interactive 2D/3D mindmap. Every user prompt, tool call and response becomes a glowing node; the tree grows additively as Claude works.",
  860. "source": {
  861. "source": "git-subdir",
  862. "url": "https://github.com/Austro-Intelligence/ai-brainmap.git",
  863. "path": "plugins/ai-brainmap",
  864. "ref": "main",
  865. "sha": "5a87ec9dc08d266d8ff7dacc3b5210c79a45b962"
  866. },
  867. "homepage": "https://github.com/Austro-Intelligence/ai-brainmap"
  868. },
  869. {
  870. "name": "ai-coding-ok",
  871. "description": "PDCA memory loop for Claude Code — prevents \"AI fixed bug X and broke feature Y\" across iterations.\n\nInstalls a three-tier memory system in your project (project-memory, decisions-log, task-history) and enforces a closed PDCA loop on every task: Plan (read memory before coding), Do, Check, Act (write memory back after). The Act step is what most tools skip — without it, your context file rots after 10 iterations. With it, iteration 50 has the same context quality as iteration 1.\n\nComplements superpowers: superpowers brings per-session discipline, ai-coding-ok brings cross-session memory. Also works with Copilot, Cursor, and OpenCode via the same templates.",
  872. "source": {
  873. "source": "url",
  874. "url": "https://github.com/Mark7766/ai-coding-ok.git",
  875. "sha": "c96068cd4c604110dbcf6093abdd4b9f68b9a873"
  876. },
  877. "homepage": "https://github.com/Mark7766/ai-coding-ok"
  878. },
  879. {
  880. "name": "ai-craftsman-superpowers",
  881. "description": "Senior craftsman methodology for Claude Code. 22 commands, 12 specialized agents, and automated hooks that enforce DDD, Clean Architecture, and TDD practices. Includes 3-level code\nvalidation (regex + static analysis + architecture), semantic intelligence via agent hooks, bias protection, correction learning, Sentry channel integration, and framework-specific scaffolding for Symfony/PHP and React/TypeScript.",
  882. "source": {
  883. "source": "url",
  884. "url": "https://github.com/BULDEE/ai-craftsman-superpowers.git",
  885. "sha": "72c1069ff925864fc3cc6cf8ae9a24795b8a3934"
  886. },
  887. "homepage": "https://github.com/BULDEE/ai-craftsman-superpowers/tree/main/docs"
  888. },
  889. {
  890. "name": "ai-dev-kit",
  891. "description": "AI Dev Kit is a complete plugin-oriented developer workspace for AI coding assistants. It ships everything needed to run professional-grade engineering workflows — TDD, code review, security audit, CI/CD, ML pipelines, infrastructure-as-code, code quality analysis, and debt tracking across Claude Code, Codex, OpenCode, and Gemini CLI.\n\nThink of it as a system prompt that scales to 59 specialized skills and 33 domain agents, with lifecycle hooks and automated validation.",
  892. "source": {
  893. "source": "url",
  894. "url": "https://github.com/noah-sheldon/ai-dev-kit.git",
  895. "sha": "c5df01c6bdd89d5545b0fb1fb942c229e13e38fc"
  896. },
  897. "homepage": "https://github.com/noah-sheldon/ai-dev-kit/blob/main/README.md"
  898. },
  899. {
  900. "name": "ai-devkit",
  901. "description": "A structured software development toolkit that helps Claude Code follow senior-engineer workflows. AI DevKit provides phase-based development lifecycle (requirements, design review, planning, implementation, testing, code review), persistent memory for cross-session knowledge, test-driven development, structured debugging, code simplification, and technical writing review. It ensures consistent engineering standards across your projects with reusable skills and configurable workflows.",
  902. "source": {
  903. "source": "url",
  904. "url": "https://github.com/codeaholicguy/ai-devkit.git",
  905. "sha": "7b92c2bece27ae58bde46c1ecca04db3965671c3"
  906. },
  907. "homepage": "https://ai-devkit.com/docs/"
  908. },
  909. {
  910. "name": "ai-firstify",
  911. "description": "AI-first project auditor and re-engineer based on the 9 design principles and 7 design patterns from the TechWolf AI-First Bootcamp",
  912. "source": {
  913. "source": "git-subdir",
  914. "url": "techwolf-ai/ai-first-toolkit",
  915. "path": "plugins/ai-firstify",
  916. "ref": "main",
  917. "sha": "f6380c947b04ae0817c2723fbf589784d4501357"
  918. },
  919. "homepage": "https://ai-first.techwolf.ai"
  920. },
  921. {
  922. "name": "ai-instruct",
  923. "description": "Five practical skills covering the domains developers most often Google when shipping a website. Each skill auto-loads only when relevant to the task: Web Accessibility on UI work, SEO/LLMO before launch, Core Web Vitals on performance issues, AWS SPA deploy on Amplify/CDK work, and Google Analytics 4 on tracking setup. Originally distributed as standalone markdown guides for any AI tool (also available via npx ai-instruct init); now packaged as a single Claude Code plugin for one-command install.",
  924. "source": {
  925. "source": "url",
  926. "url": "https://github.com/ziniman/ai-instruct.git",
  927. "sha": "435aa7c5e8fd58c611b6f56e53daa41bd5a721a3"
  928. },
  929. "homepage": "https://github.com/ziniman/ai-instruct"
  930. },
  931. {
  932. "name": "ai-integration-architect",
  933. "description": "A Claude skill that helps teams plan, design, and scaffold AI integration into enterprise systems.\n46% of enterprises say integrating AI into existing systems is their #1 challenge. This skill acts as a senior integration architect — it assesses your system landscape, recommends architecture patterns, generates production-ready code scaffolds, and produces deployment plans with security baked in.",
  934. "source": {
  935. "source": "url",
  936. "url": "https://github.com/pfbarros2/ai-integration-architect-plugin.git",
  937. "sha": "899b1b8cfa035a7f8d571571edf64df995d7c33e"
  938. },
  939. "homepage": "https://github.com/pfbarros2/ai-integration-architect-plugin"
  940. },
  941. {
  942. "name": "ai-memory-reader",
  943. "description": "Adds /aimr slash command that opens CLAUDE.md and other AI agent memory files in AI Memory Reader — a free open-source native macOS & iOS app with markdown rendering, file tree, in-page find, and edit mode. Complements the internal claude-md-management plugin (which writes/improves CLAUDE.md) by providing a polished native viewer.",
  944. "source": {
  945. "source": "url",
  946. "url": "https://github.com/nvwalj/aimr-claude-plugin.git",
  947. "sha": "fbc3295bfc590e1a72a2a08b9b3d088ebf121737"
  948. },
  949. "homepage": "https://github.com/nvwalj/ai-memory-reader"
  950. },
  951. {
  952. "name": "ai-operations-consultant",
  953. "description": "Most AI readiness tools give you a questionnaire and a score. The DOI Method gives you a structured engagement — maturity scoring, role verification, outcome mapping, task classification, friction analysis, and a sequenced implementation roadmap. The same methodology behind 50+ client engagements, packaged as a Claude plugin.",
  954. "source": {
  955. "source": "url",
  956. "url": "https://github.com/3rd-Brain/AI-Operations-Consultant.git",
  957. "sha": "4d9496e434aaa678102084f528cdea9405ef5b2b"
  958. },
  959. "homepage": "https://github.com/3rd-Brain/AI-Operations-Consultant"
  960. },
  961. {
  962. "name": "ai-plugins",
  963. "description": "Set up endorctl and use Endor Labs to scan, prioritize, and fix security risks across your software supply chain",
  964. "source": {
  965. "source": "url",
  966. "url": "https://github.com/endorlabs/ai-plugins.git",
  967. "sha": "975f0ce422b1f2677681ffd085aef34ea1826b70"
  968. },
  969. "homepage": "https://www.endorlabs.com"
  970. },
  971. {
  972. "name": "ai-pm",
  973. "description": "An AI-driven Product Manager for Claude Code that transforms news, feedback, and research into actionable PRDs and guidelines through multi-agent stakeholder debates.",
  974. "source": {
  975. "source": "url",
  976. "url": "https://github.com/ATreep/ai-pm-frame.git",
  977. "sha": "4560d39f4c32dde93326a8d2103c0da62cb600de"
  978. },
  979. "homepage": "https://github.com/ATreep/ai-pm-frame"
  980. },
  981. {
  982. "name": "ai-skills-library",
  983. "description": "20 reusable AI skills for Claude Code covering engineering, career, thinking, and creative\nworkflows.",
  984. "source": {
  985. "source": "url",
  986. "url": "https://github.com/bob798/ai-skills.git",
  987. "sha": "f2b4bddfc898b70bc03648ac6d7087fd190d8acc"
  988. },
  989. "homepage": "https://github.com/bob798/ai-skills"
  990. },
  991. {
  992. "name": "ai-statusline",
  993. "description": "AI-powered status line customization - Interactive setup and edit wizards for configuring Claude Code's status line with progress bars and customizable display options",
  994. "source": {
  995. "source": "git-subdir",
  996. "url": "charlesjones-dev/claude-code-plugins-dev",
  997. "path": "plugins/ai-statusline",
  998. "ref": "main",
  999. "sha": "b6cd024993a1293b5a6f5d3ab4fc51490215c91f"
  1000. },
  1001. "homepage": "https://github.com/charlesjones-dev/claude-code-plugins-dev"
  1002. },
  1003. {
  1004. "name": "ai-sync",
  1005. "description": "Cross-platform AI agent synchronization. When you switch \n between AI coding tools (Claude Code, Cursor, Codex, \n Aider, Cline, Windsurf, Copilot), ai-sync maintains a \n shared .ai-sync/ directory so the next agent picks up \n exactly where the last one left off — with full context \n of what was done, what's next, blockers, and build \n status. Features conflict detection, auto-progress \n tracking, session audit trails, and adapter files for 9 \n tools.",
  1006. "source": {
  1007. "source": "url",
  1008. "url": "https://github.com/oreolion/ai-sync-plugin.git",
  1009. "sha": "7d59f37e3b59960352efdf22ebfb2e63bf048d05"
  1010. },
  1011. "homepage": "https://www.npmjs.com/package/@oreolion/ai-sync"
  1012. },
  1013. {
  1014. "name": "ai-team-os",
  1015. "description": "AI Agent Team Operating System for Claude Code. Provides persistent team management, meeting collaboration, task wall with pipeline workflows, company loop engine, and 79 MCP tools for orchestrating multi-agent development teams. Includes 25 agent templates, 8 slash commands, 9 lifecycle hooks, and a real-time React dashboard.",
  1016. "source": {
  1017. "source": "url",
  1018. "url": "https://github.com/CronusL-1141/AI-company.git",
  1019. "sha": "e1a9637ef5088dcad05267bcb8302588621dedc5"
  1020. },
  1021. "homepage": "https://github.com/CronusL-1141/AI-company"
  1022. },
  1023. {
  1024. "name": "aight",
  1025. "description": "Aight is a channel plugin that bridges Claude Code to an iOS\napp via a Cloudflare Workers relay. Users pair with a 6-digit\ncode — no port forwarding, no LAN requirement. The plugin exposes\nreply and react tools so Claude can send messages, markdown, and\nfile attachments to the phone. It also forwards tool events\n(Bash, Read, Edit, etc.) in real-time so users can monitor\nClaude's work from their phone. Built with Bun, TypeScript strict\nmode, 68 tests. Security: HMAC-SHA256 auth tokens,\nsession-isolated hook routing, rate limiting, input validation.",
  1026. "source": {
  1027. "source": "url",
  1028. "url": "https://github.com/aight-cool/aight-channel-plugin.git",
  1029. "sha": "09099471683cbdfe29777b8a4ad9a7f0715bd2b0"
  1030. },
  1031. "homepage": "https://github.com/aight-cool/aight-channel-plugin"
  1032. },
  1033. {
  1034. "name": "aikido",
  1035. "description": "Aikido Security scanning for Claude Code — SAST, secrets, and IaC vulnerability detection powered by the Aikido MCP server.",
  1036. "source": {
  1037. "source": "url",
  1038. "url": "https://github.com/AikidoSec/aikido-claude-plugin.git",
  1039. "sha": "1f40742cc1300986462e1160bfc2a8ef08e7cb54"
  1040. },
  1041. "homepage": "https://github.com/AikidoSec/aikido-claude-plugin"
  1042. },
  1043. {
  1044. "name": "aio-design-system",
  1045. "description": "All in one skills about software design, UI/UX",
  1046. "source": {
  1047. "source": "git-subdir",
  1048. "url": "https://github.com/aiocean/claude-plugins.git",
  1049. "path": "plugins/aio-design-system",
  1050. "ref": "main",
  1051. "sha": "a7033b9d6742e84c715c459c70f2d88fd79dd8a8"
  1052. },
  1053. "homepage": "https://aiocean.github.io/claude-plugins/"
  1054. },
  1055. {
  1056. "name": "aio-watermill-kit",
  1057. "description": "Skills and generators for working with the Go Watermill messaging library. Includes comprehensive reference guides for Routers, Pub/Sub implementations, CQRS, and middleware.",
  1058. "source": {
  1059. "source": "git-subdir",
  1060. "url": "aiocean/claude-plugins",
  1061. "path": "plugins/aio-watermill-kit",
  1062. "ref": "main",
  1063. "sha": "a7033b9d6742e84c715c459c70f2d88fd79dd8a8"
  1064. },
  1065. "homepage": "https://aiocean.github.io/claude-plugins/"
  1066. },
  1067. {
  1068. "name": "airport-pickups-london",
  1069. "description": "Book UK airport and cruise port transfers with fixed prices. Get instant quotes, validate flights, create real bookings, track drivers, and manage reservations for all London airports (Heathrow, Gatwick, Stansted, Luton, City), and UK cruise ports. Includes trip planner for round trips and group travel.",
  1070. "source": {
  1071. "source": "url",
  1072. "url": "https://github.com/mfy-apl/claude-plugin-airport-pickups-london.git",
  1073. "sha": "5d56132ca735e61cc3b69c3fc3d5a5ba78e67dda"
  1074. },
  1075. "homepage": "https://www.airport-pickups-london.com"
  1076. },
  1077. {
  1078. "name": "airship-agent-tools",
  1079. "description": "Work with the Airship platform through natural language - featuring live access to Airship APIs and documentation resources, plus structured workflows for implementation tasks that build on that access where supported.",
  1080. "source": {
  1081. "source": "url",
  1082. "url": "https://github.com/urbanairship/agent-tools.git",
  1083. "sha": "455aaed10861c323c1357f4dfe3ef5a18a94f97e"
  1084. },
  1085. "homepage": "https://www.airship.com/docs/developer/ai-tools/ai-tools/"
  1086. },
  1087. {
  1088. "name": "aiven",
  1089. "description": "Easily deploy managed PostgreSQL (pg), Kafka, OpenSearch, Clickhouse and other databases, streaming and apps. Free tier available, up and running in minutes.",
  1090. "source": {
  1091. "source": "url",
  1092. "url": "https://github.com/aiven/aiven-ai-plugins.git",
  1093. "sha": "634f41d6852957cb9280e9245f2ea6f74645b4f1"
  1094. },
  1095. "homepage": "https://github.com/aiven/aiven-ai-plugins"
  1096. },
  1097. {
  1098. "name": "aiwff",
  1099. "description": "AIWFF Claude Plugin Fleet-aware worker dispatch helpers for Claude Code.",
  1100. "source": {
  1101. "source": "url",
  1102. "url": "https://github.com/zaxardery8011-design/aiwff-claude-plugin.git",
  1103. "sha": "f9c9e5cdf55a59898c15d9f1758010f87a7c9841"
  1104. },
  1105. "homepage": "https://github.com/zaxardery8011-design/aiwff-claude-plugin"
  1106. },
  1107. {
  1108. "name": "akf",
  1109. "description": "The AI native file format. EXIF for AI — stamps every file with trust scores, source provenance, and compliance metadata. 20+ formats.",
  1110. "source": {
  1111. "source": "url",
  1112. "url": "https://github.com/HMAKT99/AKF.git",
  1113. "sha": "071eb1d6fa5b7b5287e84d5854cc6d3ec719f3d7"
  1114. },
  1115. "homepage": "https://akf.dev"
  1116. },
  1117. {
  1118. "name": "akii-seo-ai-search-optimizer",
  1119. "description": "Free SEO, AEO, and GEO toolkit by Akii. Audit websites, plan content strategy, optimize pages, generate schema markup, cluster keywords, and track AI visibility across ChatGPT, Claude, Gemini, Perplexity, Copilot, and Google AI Overviews — all from your terminal or IDE.\n\nShips 15 model-invoked skills (auto-trigger from natural language), 5 autonomous agents, and 8 slash commands. Encodes per-engine algorithm signal weights (ChatGPT 41% authoritative lists, Gemini 49% Google lists + 3.5★ review cutoff, Perplexity 64% top-5 lists, Claude 68% trusted business databases) and the Princeton/IIT-Delhi/Allen Institute GEO method (validated +40% AI visibility lift; +97–115% for pages ranked outside top 5).\n\nAuto-detects user's existing Ahrefs, Google Search Console, DataForSEO, and Apify MCPs for richer real-data outputs; falls back to WebFetch and WebSearch when not available. No login. No usage cap. No external dependencies — every skill works standalone via Claude Code's built-in tools.\n\nThe /ai-visibility-score command returns a real 0–100 score across four dimensions (Brand Recognition, Brand Understanding, Content Coverage, Brand Sentiment) via the same workflow that powers akii.com — no signup required.\n\nMIT licensed.",
  1120. "source": {
  1121. "source": "url",
  1122. "url": "https://github.com/akii-technologies-ltd/akii-seo-ai-search-optimizer.git",
  1123. "sha": "9cb04b83601f6b9be366334008f2ef2d28288fe8"
  1124. },
  1125. "homepage": "https://akii.com/claude-code"
  1126. },
  1127. {
  1128. "name": "al-development-collection-for-claude-code",
  1129. "description": "ALDC (AL Development Collection) is a comprehensive AI-assisted development\ntoolkit for Microsoft Dynamics 365 Business Central.\n\nIt provides 4 specialized agents (architect, conductor, developer, presales),\n11 domain knowledge skills (API, events, pages, performance, testing, etc.),\nand 6 development workflows (spec creation, build, PR preparation, etc.).\n\nKey features:\n• Extension-only development — never modifies base application objects\n• Human-in-the-Loop gates at critical decision points\n• TDD/spec-driven development cycle\n• Event-driven architecture patterns\n• Skills Evidencing — agents declare which skills and patterns they applied\n• 8 path-scoped AL rules (injected via /aldc:al-initialize)\n• 3 MCP servers for AL symbols, documentation, and Microsoft Learn\n\nFirst-time setup: run /aldc:al-initialize in your AL project directory.",
  1130. "source": {
  1131. "source": "git-subdir",
  1132. "url": "javiarmesto/ALDC-AL-Development-Collection-for-GitHub-Copilot",
  1133. "path": "claude-plugin",
  1134. "ref": "main",
  1135. "sha": "484038a294897f95b7f4649ed1da45e496900eef"
  1136. },
  1137. "homepage": "https://github.com/javiarmesto/ALDC-AL-Development-Collection"
  1138. },
  1139. {
  1140. "name": "alation",
  1141. "description": "Claude plugin for the Alation platform. Query data products, explore catalogs, automate workflows, curate metadata, and configure AI agents — all through natural language.",
  1142. "source": {
  1143. "source": "url",
  1144. "url": "https://github.com/Alation/alation-plugins.git",
  1145. "sha": "b450039495787ecd6bc16176cca6df6c4a1336c3"
  1146. },
  1147. "homepage": "https://github.com/Alation/alation-plugins"
  1148. },
  1149. {
  1150. "name": "aldc-al-development-plugin-for-business-central",
  1151. "description": "ALDC (AL Development Collection) transforms how you develop Business Central extensions with Claude Code.\nInstead of ad-hoc code generation, ALDC provides structured, contract-driven development with human-in-the-loop gates.ALDC (AL Development Collection) is a comprehensive AI-assisted development\ntoolkit for Microsoft Dynamics 365 Business Central.\n\nIt provides 4 specialized agents (architect, conductor, developer, presales),\n11 domain knowledge skills (API, events, pages, performance, testing, etc.),\nand 6 development workflows (spec creation, build, PR preparation, etc.).\n\nKey features:\n• Extension-only development — never modifies base application objects\n• Human-in-the-Loop gates at critical decision points\n• TDD/spec-driven development cycle\n• Event-driven architecture patterns\n• Skills Evidencing — agents declare which skills and patterns they applied\n• 8 path-scoped AL rules (injected via /aldc:al-initialize)\n• 3 MCP servers for AL symbols, documentation, and Microsoft Learn\n\nFirst-time setup: run /aldc:al-initialize in your AL project directory.",
  1152. "source": {
  1153. "source": "git-subdir",
  1154. "url": "javiarmesto/ALDC-AL-Development-Collection-for-GitHub-Copilot",
  1155. "path": "claude-plugin",
  1156. "ref": "main",
  1157. "sha": "484038a294897f95b7f4649ed1da45e496900eef"
  1158. },
  1159. "homepage": "https://github.com/javiarmesto/ALDC-AL-Development-Collection-for-GitHub-Copilot"
  1160. },
  1161. {
  1162. "name": "aldc-spec-tdd-development-framework-for-al",
  1163. "description": "ALDC (AL Development Collection) transforms how you develop Business Central extensions. Instead of ad-hoc code generation, ALDC provides structured, contract-driven development with human-in-the-loop gates.\n\nWorks with:\n\nGitHub Copilot — Agents, skills, prompts, and instructions in .github/ and agents/\nClaude Code — Agents, skills, rules, and hooks in .claude/ + official plugin in claude-plugin/",
  1164. "source": {
  1165. "source": "git-subdir",
  1166. "url": "javiarmesto/ALDC-AL-Development-Collection",
  1167. "path": "claude-plugin",
  1168. "ref": "main",
  1169. "sha": "484038a294897f95b7f4649ed1da45e496900eef"
  1170. },
  1171. "homepage": "https://github.com/javiarmesto/ALDC-AL-Development-Collection/tree/main/claude-plugin"
  1172. },
  1173. {
  1174. "name": "alert-rules",
  1175. "description": "Generate alerting rules for monitoring",
  1176. "source": {
  1177. "source": "git-subdir",
  1178. "url": "barnburner121/claude-plugin-marketplace",
  1179. "path": "generated-plugins/alert-rules",
  1180. "ref": "main",
  1181. "sha": "7a24c061dcc61685275c2b567a9480f43ef11772"
  1182. },
  1183. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  1184. },
  1185. {
  1186. "name": "alfred",
  1187. "description": "Alfred teaches 8 development habits using domain-specific language from 7 professional personas (ML/Data Science, Research, Business Analytics, Product Analytics, Data Platform, General, Writer/Editor). It explains concepts once using your domain's analogies, then goes silent as you learn. Your corrections automatically harden into permanent CLAUDE.md rules and then into automated hooks that enforce them. Install, run /alfred:bootstrap, answer 3 questions, and start working.",
  1188. "source": {
  1189. "source": "url",
  1190. "url": "https://github.com/DrakeCaraker/alfred.git",
  1191. "sha": "535a52b03f2033a6b292495d82391d2f2e83c69c"
  1192. },
  1193. "homepage": "https://github.com/DrakeCaraker/alfred"
  1194. },
  1195. {
  1196. "name": "algovault-skills",
  1197. "description": "The Brain Layer for AI Trading Agents. 20 Skills over the AlgoVault MCP — composite BUY/SELL/HOLD signals across 5 crypto exchanges, funding-rate arbitrage, and market regime classification. Track record: 90.5% PFE win rate across 90K+ signals, Merkle-anchored on Base L2.",
  1198. "source": {
  1199. "source": "url",
  1200. "url": "https://github.com/AlgoVaultLabs/algovault-skills.git",
  1201. "sha": "ae51b3035e15733e875eebfc912f21ae4c0cc0bc"
  1202. },
  1203. "homepage": "https://algovault.com"
  1204. },
  1205. {
  1206. "name": "alias-gen",
  1207. "description": "Generate shell aliases for project commands",
  1208. "source": {
  1209. "source": "git-subdir",
  1210. "url": "barnburner121/claude-plugin-marketplace",
  1211. "path": "generated-plugins/alias-gen",
  1212. "ref": "main",
  1213. "sha": "5f6b5d32d9f457dc9c2c7c0fb1d67dffc9140f33"
  1214. },
  1215. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  1216. },
  1217. {
  1218. "name": "alley-oop",
  1219. "description": "Alley Oop keeps your development momentum going across sessions without the cost of replaying full conversation history. When you're ready to hand off, /alley distills your current session into a compact cold-start prompt — capturing just what the next session needs to orient and act immediately. Start the new session with /oop and you're back in the game. For parallel workstreams, /alleyarchive and /ooparchive let you branch, archive, and resume multiple threads independently.",
  1220. "source": {
  1221. "source": "url",
  1222. "url": "https://github.com/1azarus/alley-oop.git",
  1223. "sha": "15c8d1094c4f74f4917a08c5663d9d5f834e991b"
  1224. },
  1225. "homepage": "https://github.com/1azarus/alley-oop"
  1226. },
  1227. {
  1228. "name": "alloydb-omni",
  1229. "description": "Create, connect, and interact with an AlloyDB Omni database and data.",
  1230. "source": {
  1231. "source": "url",
  1232. "url": "https://github.com/gemini-cli-extensions/alloydb-omni.git",
  1233. "sha": "60cd1c8d5659f2527c4f1b096ab73c490aca40a5"
  1234. },
  1235. "homepage": "https://cloud.google.com/alloydb/omni"
  1236. },
  1237. {
  1238. "name": "almanax-security",
  1239. "description": "Scan Git commits for security vulnerabilities using Almanax directly from Claude Code. The plugin connects to the Almanax MCP server to analyze commit diffs, surface findings by severity, and help you fix issues — all without leaving your terminal. Includes guided setup and support for scanning individual commits or commit ranges.",
  1240. "source": {
  1241. "source": "git-subdir",
  1242. "url": "https://github.com/almanax-ai/almanax-security-plugin.git",
  1243. "path": "plugins/almanax-security",
  1244. "ref": "main",
  1245. "sha": "cd91668e2ca6843f5ca767e4900b022f2e218756"
  1246. },
  1247. "homepage": "https://docs.almanax.ai/integration/mcp.html"
  1248. },
  1249. {
  1250. "name": "alps-writer",
  1251. "description": "MCP server for interactive ALPS (PRD) writing with AI. Guides you through 9 structured sections with templates, conversation guides, and document management.",
  1252. "source": {
  1253. "source": "url",
  1254. "url": "https://github.com/haandol/alps-writer-mcp.git",
  1255. "path": "plugins/alps-writer",
  1256. "sha": "b147816dd5e257d4a7d6d87428487d211286ddc7"
  1257. },
  1258. "homepage": "https://github.com/haandol/alps-writer-mcp"
  1259. },
  1260. {
  1261. "name": "altertable",
  1262. "description": "Altertable gives Claude governed access to your Altertable workspace so it can explore data, query the lakehouse, analyze product and business metrics, and help turn raw data into insights. The plugin bundles Altertable-specific Agent Skills with the Altertable MCP, allowing Claude to inspect schemas, write and run SQL, analyze funnels, build segments, interpret charts, forecast time series, configure monitoring agents, manage discoveries, and use memory for richer follow-up analysis. It is designed for teams using Altertable as an AI-native data platform where humans and agents work from the same governed data context.",
  1263. "source": {
  1264. "source": "url",
  1265. "url": "https://github.com/altertable-ai/skills.git",
  1266. "sha": "d143d96dbd099344ed2bbec8fd6449dde321c3cc"
  1267. },
  1268. "homepage": "https://altertable.ai/docs/agentic/claude-plugin"
  1269. },
  1270. {
  1271. "name": "amazon-location-service",
  1272. "description": "Guide developers through adding maps, places search, geocoding, routing, and other geospatial features with Amazon Location Service, including authentication setup, SDK integration, and best practices.",
  1273. "category": "location",
  1274. "source": {
  1275. "source": "git-subdir",
  1276. "url": "https://github.com/awslabs/agent-plugins.git",
  1277. "path": "plugins/amazon-location-service",
  1278. "ref": "main",
  1279. "sha": "7a17df718d26f07414b876e77a7480fa25089b08"
  1280. },
  1281. "homepage": "https://github.com/awslabs/agent-plugins"
  1282. },
  1283. {
  1284. "name": "amg-toolkit",
  1285. "description": "Agent plugin for Azure Managed Grafana — health checks, cost analysis, and diagnostics for Azure resources via the built-in AMG-MCP server.",
  1286. "source": {
  1287. "source": "url",
  1288. "url": "https://github.com/Azure/amg-skills.git",
  1289. "sha": "a32a5cdd6bd597f81e02e5e0fb95bcfd10d0b757"
  1290. },
  1291. "homepage": "https://github.com/Azure/amg-skills"
  1292. },
  1293. {
  1294. "name": "amni",
  1295. "description": "Your AI-based personal motherhood assistant. Helps mothers manage routines, family health, and track their child's development directly through Claude.",
  1296. "source": {
  1297. "source": "url",
  1298. "url": "https://github.com/amni-app/amni-claude-plugin.git",
  1299. "sha": "898270ee30a7e65e699fbc977223e593a812c5f9"
  1300. },
  1301. "homepage": "https://github.com/amni-app/amni-claude-plugin"
  1302. },
  1303. {
  1304. "name": "amplitude",
  1305. "description": "Use Amplitude as an expert analyst or product manager. Analyze charts, create dashboards, monitor experiments, discover opportunities, synthesize feedback, generate briefs, and improve your product and growth outcomes.",
  1306. "source": {
  1307. "source": "git-subdir",
  1308. "url": "https://github.com/amplitude/mcp-marketplace.git",
  1309. "path": "plugins/amplitude",
  1310. "ref": "main",
  1311. "sha": "90c0a8e658db547ab63a2210e84be07c23ce4cd0"
  1312. },
  1313. "homepage": "https://github.com/amplitude/mcp-marketplace/"
  1314. },
  1315. {
  1316. "name": "anakin-claude-plugin",
  1317. "description": "Anakin turns any website into clean, LLM-ready data directly from Claude Code. Scrape single pages or batch up to 10 URLs at once, returning markdown, JSON, or raw output. Run AI-powered web searches to find pages and sources instantly. Launch deep agentic research that autonomously explores the web and synthesizes comprehensive reports with cited sources. All output is saved to files to keep your context window clean. Supports headless browser rendering for JavaScript-heavy sites, geo...",
  1318. "source": {
  1319. "source": "url",
  1320. "url": "https://github.com/Anakin-Inc/anakin-claude-plugin.git",
  1321. "sha": "bd1cb3352a871576b077e717055eb56f940564ed"
  1322. },
  1323. "homepage": "https://github.com/Anakin-Inc/anakin-claude-plugin"
  1324. },
  1325. {
  1326. "name": "analyst-never-sleep",
  1327. "description": "Your personal analyst. Always on. Never sleeps. \n \nBuilt for fundamental investors who want an edge with hours of researched prepared when you wake up, in your own way.\n \n What it does for you: \n \n - Never miss a market move — wake up to a structured daily briefing covering macro shifts, sector moves, and news on your watchlist\n - Cut research time in half — run a full company deep dive in seconds, not hours. Financials, thesis, risks, all in one shot \n - Walk into earnings ready — get a pre-earnings framework before the call and a post-earnings breakdown after \n - Think in memos, not notes — turn your thesis into a clean, shareable investment memo with one command \n - Track what matters — manage your watchlist in plain English. Levels, catalysts, conviction — all in one place \n \n Who it's for: \n Retail investors, self-directed traders, and finance students who think like analysts but don't have a research team behind them.",
  1328. "source": {
  1329. "source": "git-subdir",
  1330. "url": "https://github.com/kmmz/analyst_never_sleep.git",
  1331. "path": "investment-analyst",
  1332. "ref": "main",
  1333. "sha": "4ffe0586bc3c83f491ccad295b56c281fc5791e2"
  1334. },
  1335. "homepage": "https://github.com/kmmz/analyst_never_sleep"
  1336. },
  1337. {
  1338. "name": "analytics-skills",
  1339. "description": "Agent skills that teach Claude, Cursor, and other AI agents to read web analytics like a senior analyst.\n\nFive model-invoked skills covering a diagnostic method (MECE hypothesis trees, signal vs noise, Simpson's paradox, Pyramid Principle output), traffic-change diagnosis with fingerprints for common causes, channel and funnel quality analysis, and metric benchmarking by business model.\n\nA one-time profile setup captures your business context (model, primary conversion, traffic range, ICP, data stack) so every answer is calibrated to your industry and scale instead of generic averages.\n\nWorks with any analytics source; first-class support for Clamp MCP with exact tool call-outs at each step of the method.",
  1340. "source": {
  1341. "source": "url",
  1342. "url": "https://github.com/clamp-sh/analytics-skills.git",
  1343. "sha": "b9e06c5131a6060114e68893bc34fc77b65a9552"
  1344. },
  1345. "homepage": "https://clamp.sh/docs/skills"
  1346. },
  1347. {
  1348. "name": "anamnese-core",
  1349. "description": "Secure, portable, cloud-persistent memory across every conversation. Store and retrieve your personal facts, decisions, tasks, goals, and notes. Accessible from any AI client. Export, View, Delete your data at any time.",
  1350. "source": {
  1351. "source": "git-subdir",
  1352. "url": "AnamneseAI/anamnese-plugin-marketplace",
  1353. "path": "anamnese-core",
  1354. "ref": "main",
  1355. "sha": "5c8449ca5762dd46941bc8fa3b354d8306386263"
  1356. },
  1357. "homepage": "https://anamneseai.app/"
  1358. },
  1359. {
  1360. "name": "andie",
  1361. "description": "Andie - the sharpest thinking partner inside Claude Code. \nAndie doesn't summarize — it debates, war-games, and dissects until the answer survives scrutiny. \nFour modes: \nDeep (world-class expert breaks it down Feynman-style), \nDrama (expert panel fights your decision to a conclusion), \nTriage (war strategy applied to your crisis in real time), \nKaizen (finds the waste, fixes one thing, locks it in). \nAutomatically picks up and loads specialist skills — AWS-GCP-Azure-OCI, multiple tools like Kafka, Postgres, security, ML, and more — so every answer comes from someone who's actually done the work.",
  1362. "source": {
  1363. "source": "url",
  1364. "url": "https://github.com/giggsoinc/andie.git",
  1365. "sha": "ad3221496f32e6df11b32212416f263f826a5bc5"
  1366. },
  1367. "homepage": "https://github.com/giggsoinc/andie/blob/main/README.md"
  1368. },
  1369. {
  1370. "name": "android-emulator-qa-plugin",
  1371. "description": "Claude Android QA Plugin helps Claude Code test Android apps in an emulator. It can launch apps, inspect UI trees, derive safe tap coordinates, capture screenshots, and collect logcat evidence for QA and bug reproduction.",
  1372. "source": {
  1373. "source": "url",
  1374. "url": "https://github.com/ceabarr/claude-android-plugin.git",
  1375. "sha": "18e69487874cc57acd8b4a10de2d401c8e9f1fc5"
  1376. },
  1377. "homepage": "https://github.com/ceabarr/claude-android-plugin"
  1378. },
  1379. {
  1380. "name": "android-kmp-playbook",
  1381. "description": "Comprehensive Claude Code toolkit for Android and Kotlin Multiplatform (KMP) many skills, sub-agents, and command enforcing Clean Architecture, Jetpack Compose best\npractices, KMP patterns, coroutines, TDD, Wear OS, TV, XR, and more.",
  1382. "source": {
  1383. "source": "url",
  1384. "url": "https://github.com/rezaiyan/android-kmp-claude-playbook.git",
  1385. "sha": "bc3496dc58e0a6d85ae731fea821091dc7cd8036"
  1386. },
  1387. "homepage": "https://github.com/rezaiyan/android-kmp-claude-playbook"
  1388. },
  1389. {
  1390. "name": "android-kotlin",
  1391. "description": "Generate Android/Kotlin project with Jetpack",
  1392. "source": {
  1393. "source": "git-subdir",
  1394. "url": "barnburner121/claude-plugin-marketplace",
  1395. "path": "generated-plugins/android-kotlin",
  1396. "ref": "main",
  1397. "sha": "6470b3dbdf66767d531844b597ddff183f4eb146"
  1398. },
  1399. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  1400. },
  1401. {
  1402. "name": "angel-ai",
  1403. "description": "This Plugin acts as a data analyst agent. The goal is to minimize costs as much as possible for early stage startups, so they can make informed decisions at a lower cost.",
  1404. "source": {
  1405. "source": "url",
  1406. "url": "https://github.com/ShayanShams8/AngelAI.git",
  1407. "sha": "eb857ea1406879cad672df474dc05105c3cc8405"
  1408. },
  1409. "homepage": "https://shayanshams8.github.io/Angweb/"
  1410. },
  1411. {
  1412. "name": "animation-helper",
  1413. "description": "Generate CSS/Framer Motion animations",
  1414. "source": {
  1415. "source": "git-subdir",
  1416. "url": "barnburner121/claude-plugin-marketplace",
  1417. "path": "generated-plugins/animation-helper",
  1418. "ref": "main",
  1419. "sha": "5f6b5d32d9f457dc9c2c7c0fb1d67dffc9140f33"
  1420. },
  1421. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  1422. },
  1423. {
  1424. "name": "ansible-playbook",
  1425. "description": "Generate Ansible playbooks",
  1426. "source": {
  1427. "source": "git-subdir",
  1428. "url": "barnburner121/claude-plugin-marketplace",
  1429. "path": "generated-plugins/ansible-playbook",
  1430. "ref": "main",
  1431. "sha": "5f6b5d32d9f457dc9c2c7c0fb1d67dffc9140f33"
  1432. },
  1433. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  1434. },
  1435. {
  1436. "name": "anson",
  1437. "description": "Battle-tested coworker setup for Claude Code · Slack · Notion · Gmail · Granola. Bootstrap a working AI coworker end-to-end by interview - identity, OAuth, scheduled automations, and custom workflows.",
  1438. "source": {
  1439. "source": "url",
  1440. "url": "https://github.com/superpositionhq/anson-v2.git",
  1441. "sha": "4dff2c84b2b25a35222e510155b662ab5dea2941"
  1442. },
  1443. "homepage": "https://github.com/superpositionhq/anson-v2"
  1444. },
  1445. {
  1446. "name": "anti-ai-writing",
  1447. "description": "Edits any draft to remove the words, phrases, and structures that mark writing as AI output. Strips banned words like delve, unlock, leverage, robust, harness, and showcase (plus 50 more). Strips banned phrases like \"in today's fast-paced world\" and \"unlock the potential of.\" Strips banned structures: em dashes, the default rule of three, bulleted lists with bold titles, formulaic transitions, weak verbs. Returns a clean rewrite plus a diagnosis of what was wrong. Works in English and Spanish.",
  1448. "source": {
  1449. "source": "url",
  1450. "url": "https://github.com/avectats7/anti-ai-writing.git",
  1451. "sha": "fd2459fc4b81a52bae557d4ac85f3b88e8d8968b"
  1452. },
  1453. "homepage": "https://github.com/avectats7/anti-ai-writing"
  1454. },
  1455. {
  1456. "name": "anti-slop-ui",
  1457. "description": "Eliminates the AI-generated look from any frontend. Identifies the specific patterns that make sites look AI-generated and provides concrete fixes for each one. Includes design tokens by impression level, a mobile adaptation pass, and a pre-ship checklist.",
  1458. "source": {
  1459. "source": "url",
  1460. "url": "https://github.com/awaken7050dev/anti-slop-ui.git",
  1461. "sha": "4d80235daefc593ccd72e3a58310b67b77090701"
  1462. },
  1463. "homepage": "https://github.com/awaken7050dev/anti-slop-ui"
  1464. },
  1465. {
  1466. "name": "anticipating-shadow-points",
  1467. "description": "Helps you ship complex engineering work without missing the obvious. Before any code is written, ASP runs an automated pre-mortem to surface failure modes that engineers (and LLMs) routinely miss on first pass — RLS policy gaps, replica lag during migrations, rate-limit issues in external APIs, deprecated callsites, monitoring blind spots, untested rollback paths. It then validates the plan with an independent agent, locks execution into a step-by-step contract with acceptance tests, and runs autonomously until done. Use before any non-trivial task: schema migrations, refactors across many files, deploys with external dependencies, RLS policy changes, or architecture decisions. Multilingual docs (English, Spanish, Portuguese, Italian, Hebrew). MIT licensed.",
  1468. "source": {
  1469. "source": "url",
  1470. "url": "https://github.com/ulissesflores/anticipating-shadow-points.git",
  1471. "sha": "99ec0f2bad103a75e3b80ad4b04a543bac9cd3eb"
  1472. },
  1473. "homepage": "https://ulissesflores.github.io/anticipating-shadow-points/"
  1474. },
  1475. {
  1476. "name": "aomi-build",
  1477. "description": "Use this to build agents hosted by Aomi Labs. An Aomi app is a platform-specific Rust API client compiled into an agentic application and loaded into the Aomi runtime to form a working crypto-trading agent. Apps are designed for crypto trading: the runtime supports native on-chain actions, so apps typically wrap complementary off-chain APIs from crypto platforms — CEXes, DEX aggregators, prediction markets, perp venues, oracles, social, on-chain analytics — to round out the agent's capabilities.\n\naomi-build scaffolds new Aomi apps from API docs, OpenAPI/Swagger specs, SDK docs, runtime interfaces, or product requirements. It generates production-ready Rust SDK crates (lib.rs, client.rs, tool.rs) with tool schemas, preambles, host-interop flows, and validation steps — turning a vendor's full API surface into AI-agent-callable tools.\nTrigger when the user wants to scaffold a new Aomi app from an OpenAPI/Swagger spec, wrap a REST API as agent-callable tools, port an existing SDK to Aomi, generate a tool surface from product requirements, or extend the Aomi runtime with a new crypto integration. Prefers real product integrations over docs-only helpers whenever a callable surface exists.\n\nOutput crates support sync HTTP, async tools (cancellation-safe via DynAsyncSink), proxy-unwrap (EIP-1967), and host-interop flows that route quote → approval → swap as multi-step transactions. Same runtime that aomi-transact drives — so an aomi-build-scaffolded app can be invoked alongside aomi-transact's on-chain primitives in the same agent session.\n\n---\nAbout Aomi: Aomi Labs builds the native harness for blockchains, functioning like Claude Code on-chain. We specialize in executions against arbitrary protocols with non-custodial workflow, account abstraction, and full security via fork-chain simulation. Aomi also hosts agentic applications deployed and owned by developers, companies, and the agents themselves. We ship end-to-end: chat UI, agent Skills, and SDKs in TypeScript and Rust.\n\nLinks: aomi.dev · x.com/aomi_labs · github.com/aomi-labs · npm: @aomi-labs/client, @aomi-labs/widget-lib · crates: aomi-sdk",
  1478. "source": {
  1479. "source": "git-subdir",
  1480. "url": "aomi-labs/skills",
  1481. "path": "aomi-build",
  1482. "ref": "main",
  1483. "sha": "d1dad35099825e3ee2d7e54b787111501e3ccd89"
  1484. },
  1485. "homepage": "https://aomi.dev"
  1486. },
  1487. {
  1488. "name": "aomi-transact",
  1489. "description": "Use this skill to build natural-language crypto agents, web3 assistants, trading bots, blockchain MCPs, or Claude/Cowork plugins that read and write EVM chain state. Aomi turns user prompts (\"swap 1 ETH for USDC\", \"open a 3x GMX long\", \"bet $100 yes on this Polymarket question\") into wallet-signed transactions on Ethereum, Base, Arbitrum, Optimism, Polygon, and Linea — generic, non-custodial, with fork-chain simulation before every signature.\n\nTrigger when the user wants to: scaffold a crypto/DeFi agent, build an AI trading or wallet assistant, wrap an EVM protocol as MCP tools, create natural-language interfaces to APIs from Across / 1inch / GMX / Hyperliquid / Polymarket / Binance / OKX, or add on-chain execution to universal protocols (e.g. Uniswap / Aave / Lido / Morpho) to an agent stack.\n\nAomi CLI connects to Aomi runtime reads and writes EVM chain state: stages calldata, simulates as a batch on a forked chain, and returns wallet requests for the user to sign. Works on any EVM contract via low-level primitives: ABI encoding (encode_and_call), fork-batch simulation (simulate_batch), staged-tx queueing (stage_tx), and wallet handoff with EIP-712 (commit_tx, commit_eip712) — including multi-step swap-approve-execute routing. Ships with 40+ tuned protocol apps and all on-chain smart contracts. Every action simulates first, batches when possible, and is signed by the end-user wallet — keys never leave.",
  1490. "source": {
  1491. "source": "git-subdir",
  1492. "url": "https://github.com/aomi-labs/skills.git",
  1493. "path": "aomi-transact",
  1494. "ref": "main",
  1495. "sha": "d1dad35099825e3ee2d7e54b787111501e3ccd89"
  1496. },
  1497. "homepage": "https://aomi.dev"
  1498. },
  1499. {
  1500. "name": "api-cache-client",
  1501. "description": "Generate API response caching",
  1502. "source": {
  1503. "source": "git-subdir",
  1504. "url": "barnburner121/claude-plugin-marketplace",
  1505. "path": "generated-plugins/api-cache-client",
  1506. "ref": "main",
  1507. "sha": "7a24c061dcc61685275c2b567a9480f43ef11772"
  1508. },
  1509. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  1510. },
  1511. {
  1512. "name": "api-contract-forge",
  1513. "description": ":\nBuild production-ready API endpoints with proper contracting for any tech stack, or analyze existing API responses to generate typed contracts. Supports Express, NestJS, FastAPI, Django, Go, Spring Boot, Laravel, and Rails. Auto-detects your project's framework, validation library, and ORM, then scaffolds CRUD endpoints with validation schemas, Swagger docs, RBAC permissions, and a compliance checklist (OWASP, RFC 9457). In analyze mode, paste any JSON response to infer types, detect inconsistencies, and generate contracts in TypeScript, Zod, Pydantic, Dart, Kotlin, Swift, OpenAPI 3.1, or JSON Schema.",
  1514. "source": {
  1515. "source": "url",
  1516. "url": "https://github.com/rumitdev/claude-api-contract-forge.git",
  1517. "sha": "b67be45bfa85bb95a83175279c72b466b39b4ba3"
  1518. },
  1519. "homepage": "https://github.com/rumitdev/claude-api-contract-forge.git"
  1520. },
  1521. {
  1522. "name": "api-forge",
  1523. "description": "Generate comprehensive API test suites from OpenAPI specs or route files, create mock servers with realistic fake data, run contract tests between services, and benchmark endpoint performance.",
  1524. "source": {
  1525. "source": "git-subdir",
  1526. "url": "barnburner121/claude-plugin-marketplace",
  1527. "path": "generated-plugins/api-forge",
  1528. "ref": "main",
  1529. "sha": "5b36995a83264b2c59d39137bdfcb721f4c5bb3b"
  1530. },
  1531. "homepage": "https://github.com/barnburner121/claude-plugin-marketplace"
  1532. },
  1533. {
  1534. "name": "apify-scraper",
  1535. "description": "Full Apify web scraping platform integration for Claude. Run Actors, manage datasets, key-value stores, schedules, webhooks, and tasks — all from within Claude. Includes 27 tools covering the full Apify platform.",
  1536. "source": {
  1537. "source": "git-subdir",
  1538. "url": "MSApps-Mobile/claude-plugins",
  1539. "path": "plugins/apify-scraper",
  1540. "ref": "main",
  1541. "sha": "578bd7dc2a26cbb5e0852f0b386a455b16372c7b"
  1542. },
  1543. "homepage": "https://github.com/MSApps-Mobile/claude-plugins/tree/main/plugins/apify-scraper"
  1544. },
  1545. {
  1546. "name": "apiiro",
  1547. "description": "The Apiiro plugin for Claude Code connects developers directly to Apiiro’s Software and Risk Graph along with organizational context, bringing repository intelligence, ownership, architecture, policies, and risk insights into the development workflow.\n\nWith Apiiro, developers can enrich prompts with relevant security and organizational context, get remediation guidance tailored to their codebase and internal policies, scan code changes for vulnerabilities before committing, generate threat models on demand, and ask natural-language questions about their application and security posture.\n\nThis helps teams build and ship code faster with security guidance that is specific to their repositories, applications, and organization.",
  1548. "source": {
  1549. "source": "git-subdir",
  1550. "url": "apiiro/mcp-server",
  1551. "path": ".cursor-plugin",
  1552. "ref": "main",
  1553. "sha": "dc5ea352bbd530a946793e36c8f7f5127481955e"
  1554. },
  1555. "homepage": "https://github.com/apiiro/mcp-server/tree/main/.cursor-plugin"
  1556. },
  1557. {
  1558. "name": "apollo",
  1559. "description": "Prospect, enrich leads, and bulk-load outreach sequences with Apollo.io. Includes 3 powerful skills: enrich-lead, prospect, and sequence-load for complete sales automation.",
  1560. "source": {
  1561. "source": "git-subdir",
  1562. "url": "MSApps-Mobile/claude-plugins",
  1563. "path": "plugins/apollo",
  1564. "ref": "main",
  1565. "sha": "578bd7dc2a26cbb5e0852f0b386a455b16372c7b"
  1566. },
  1567. "homepage": "https://github.com/MSApps-Mobile/claude-plugins/tree/main/plugins/apollo"
  1568. },
  1569. {
  1570. "name": "apollo-mcp",
  1571. "description": "FastMCP server for Apollo.io with 22 tools: sequences, campaign health, mailbox warmup, enrichment, CRM, credits.",
  1572. "source": {
  1573. "source": "url",
  1574. "url": "https://github.com/adelaidasofia/apollo-mcp.git",
  1575. "sha": "5bbc2b24ddd0ca51923d95b7494cdf313e6c489d"
  1576. },
  1577. "homepage": "https://myceliumai.co/plugins/apollo-mcp"
  1578. },
  1579. {
  1580. "name": "apollo-mcp-plugin",
  1581. "description": "The Apollo plugin offers 3 pre-built skills that chain multiple Apollo APIs into complete sales workflows — no manual steps, no tab switching. Enrich any contact from a name, email, or LinkedIn URL. Prospect by describing your ICP in plain English and get a ranked leads. Find, enrich, and load contacts into a sequence in one shot.",
  1582. "source": {
  1583. "source": "url",
  1584. "url": "https://github.com/apolloio/apollo-mcp-plugin.git",
  1585. "sha": "2adde980e45f421b7e9383d92870455627936bce"
  1586. },
  1587. "homepage": "https://github.com/apolloio/apollo-mcp-plugin"
  1588. },
  1589. {
  1590. "name": "apollo-skills",
  1591. "description": "A collection of skills for AI coding agents working with Apollo GraphQL tools and technologies. Includes guides for Apollo Client, Apollo Server, Apollo Connectors, Apollo Federation, Apollo Router, Apollo Kotlin, Apollo MCP Server, Rover CLI, GraphQL schema design, GraphQL operations, and Rust best practices. Skills activate automatically when relevant tasks are detected and provide up-to-date reference documentation so the agent produces correct, idiomatic code.",
  1592. "source": {
  1593. "source": "url",
  1594. "url": "https://github.com/apollographql/skills.git",
  1595. "sha": "c288eb80629dd2309eed81f23d693f66a452d043"
  1596. },
  1597. "homepage": "https://skills.sh/apollographql/skills"
  1598. },
  1599. {
  1600. "name": "aport-guardrails",
  1601. "description": "Security guardrails for Claude Code. Intercepts every tool call via PreToolUse hook and evaluates it against your Open Agent Passport (OAP) policy before execution. Blocks unauthorized commands, dangerous file operations, and policy violations. All evaluation runs locally by default - zero network calls, works offline. Open-source (Apache 2.0).\n\nIncludes three skills:\n- /aport-guardrails:claude-code — Set up guardrails and create a passport\n- /aport-guardrails:status — Check guardrail status and recent decisions\n- /aport-guardrails:openclaw — Set up guardrails for OpenClaw agents",
  1602. "source": {
  1603. "source": "url",
  1604. "url": "https://github.com/aporthq/aport-agent-guardrails.git",
  1605. "sha": "3a8a0b40e12b20e371ac9824190fa9d0fd6bfd4c"
  1606. },
  1607. "homepage": "https://aport.io/frameworks/claude-code/"
  1608. },
  1609. {
  1610. "name": "appstore-prep",
  1611. "description": "A 5-skill bundle that captures the gnarly pre-submission failure modes — Apple Distribution + 3rd Party Mac Developer Installer signing, SwiftPM nested-bundle 409 fix, AppIcon white-border detection, OAuth Guideline 4.5/4.8 review-rejection prevention, and offline ASO metadata audit (keywords / subtitle / screenshots). Complements Blitz — Blitz handles ASC operations, this handles the artifact preparation.",
  1612. "source": {
  1613. "source": "url",
  1614. "url": "https://github.com/Kevin-Wei-sudo/appstore-prep.git",
  1615. "sha": "02e686c701db0f83ec3c1de3436bece952488e2c"
  1616. },
  1617. "homepage": "https://github.com/Kevin-Wei-sudo/appstore-prep"
  1618. },
  1619. {
  1620. "name": "appstore-screenshots",
  1621. "description": "Automate App Store and Play Store screenshot creation for Expo/React Native apps. Full pipeline: capture via Maestro, add device frames with fastlane, composite marketing overlays with Pillow.",
  1622. "source": {
  1623. "source": "url",
  1624. "url": "https://github.com/ntgussoni/app-store-play-store-screenshots-skill.git",
  1625. "sha": "cc626ca89e1d2d990ef441aff6e8f251fa12dc10"
  1626. },
  1627. "homepage": "https://github.com/ntgussoni/app-store-play-store-screenshots-skill"
  1628. },
  1629. {
  1630. "name": "appwrite",
  1631. "description": "The Appwrite plugin for Claude code includes skills and MCP servers, allowing AI agents to access your projects and correctly integrate with your projects.",
  1632. "source": {
  1633. "source": "url",
  1634. "url": "https://github.com/appwrite/claude-plugin.git",
  1635. "sha": "a42b16918159183a0d556e305fea4d240a9e3823"
  1636. },
  1637. "homepage": "https://appwrite.io"
  1638. },
  1639. {
  1640. "name": "aptos-agent-skills",
  1641. "description": "AI skills for building fullstack Aptos dApps — Move smart contracts, TypeScript SDK, wallet integration, security auditing, and gas optimization.",
  1642. "category": "development",
  1643. "source": {
  1644. "source": "url",
  1645. "url": "https://github.com/aptos-labs/aptos-agent-skills.git",
  1646. "sha": "358a712b71d414566c32a89383f2d1a185522854"
  1647. },
  1648. "homepage": "https://github.com/aptos-labs/aptos-agent-skills"
  1649. },
  1650. {
  1651. "name": "arcanum",
  1652. "description": "Advanced debugging, code review, deep research, technical documentation, creative ideation, and semi-autonomous development workflows with parallel theory validation, team-based research, war room investigation, root cause analysis, PR review assistance, elite technical writing, and Maestro development pipeline",
  1653. "source": {
  1654. "source": "url",
  1655. "url": "https://github.com/burnsbert/claude-arcanum.git",
  1656. "sha": "57d56010d097169805e0d39e79a5bd4ec4ab011d"
  1657. },
  1658. "homepage": "https://github.com/burnsbert/claude-arcanum"
  1659. },
  1660. {
  1661. "name": "arcdeck",
  1662. "description": "Convert academic PDF papers into polished, narrative-driven PowerPoint presentations using 13 specialized AI agents. Based on discourse parsing with multi-agent critique-revise-judge refinement loops and aesthetic design principles.",
  1663. "source": {
  1664. "source": "url",
  1665. "url": "https://github.com/RehgLab/ArcDeck-Claude-Plugin.git",
  1666. "sha": "4bd03694531100611202a8751f578c6609a71c6c"
  1667. },
  1668. "homepage": "https://arcdeck.org"
  1669. },
  1670. {
  1671. "name": "archcore",
  1672. "description": "Git-native context for AI coding agents. Archcore turns your repository into structured, machine-readable context — so AI agents understand your architecture, rules, and decisions.",
  1673. "source": {
  1674. "source": "url",
  1675. "url": "https://github.com/archcore-ai/archcore-plugin.git",
  1676. "path": "plugins/archcore",
  1677. "sha": "5244f6c536c2b1d4ac857d67ebc6cdf7439f1e49"
  1678. },
  1679. "homepage": "https://archcore.ai/"
  1680. },
  1681. {
  1682. "name": "architecture-studio",
  1683. "description": "Description:\n\nArchitecture Studio is a Claude plugin system for architects, designers, and AEC professionals. It includes 7 autonomous agents, 36 skills, 6 rules, and 3 hooks organized into 9 installable plugins — covering site research, NYC property due diligence, zoning envelope analysis, workplace programming, CSI specifications, sustainability (EPD parsing and comparison), FF&E product research, and presentation generation.\n\nA single entry point (`/studio`) routes users to the right agent or skill based on natural language. Agents orchestrate multiple skills, exercise judgment, and hand off to each other across the project lifecycle. Skills ship with bundled reference data — NYC Zoning Resolution chapters, IBC occupancy load factors, workplace benchmarks, and Uruguay zoning regulations.\n\nKey features:\n\n- `/studio` smart router — describe your task, get routed automatically\n- 7 agents with handoff logic (site planner → zoning expert → workplace strategist → materials researcher → FF&E designer → sustainability specialist → brand manager)\n- Modular install — users pick the plugins they need\n- 6 always-on rules governing units, code citations, disclaimers, CSI formatting, terminology, and output structure\n- MIT licensed, open source",
  1684. "source": {
  1685. "source": "url",
  1686. "url": "https://github.com/AlpacaLabsLLC/skills-for-architects.git",
  1687. "sha": "44765760ae04c40d8db1e6af7882d83ae5ed5493"
  1688. },
  1689. "homepage": "https://www.alpa.llc/plugins"
  1690. },
  1691. {
  1692. "name": "aria",
  1693. "description": "Aria is a guided music-release workflow for artists, managers, and labels. It walks through a complete lifecycle — from raw idea or finished track to pitched, released, and live on a smart link — through nine progressive phase skills and the hosted aria MCP. Every artifact is grounded in your real catalog, streaming intelligence, and sonic analysis (BPM, key, genres, moods). No hallucinated playlists. No invented metrics. Plugin code is open source (MIT); the MCP backend is Patchline-hosted and authenticated via Cognito OAuth.",
  1694. "source": {
  1695. "source": "url",
  1696. "url": "https://github.com/Patchline-AI/aria.git",
  1697. "sha": "5d395214d9bc350a21d0436f572051dc407fb04b"
  1698. },
  1699. "homepage": "https://www.patchline.ai/claude"
  1700. },
  1701. {
  1702. "name": "aria-knowledge",
  1703. "description": "ARIA is automated knowledge capture, management, and application for Claude Code. It actively learns during AI-assisted development sessions — insights, decisions, patterns, gotchas — and promotes validated knowledge into an indexed markdown knowledge base that is proactively applied in sessions and on every edit to improve development and accuracy. It runs in Claude Code, fully local. Core feature sets are:\n\nKnowledge Lifecycle — automatic capture from conversations and pre-compaction transcripts, staging backlogs, review workflows, promotion to tagged files, staleness detection, and archival. A pipeline from raw signal to validated knowledge.\n\nDecision Discipline — hook-enforced impact assessment on every file edit, change framework with scope verification, pre/post edit checks, configurable critical paths, and abbreviated mode for planning docs. Not guidelines — active enforcement.\n\nContextual Retrieval — tag-based indexing with cross-references, on-demand knowledge loading by topic, project tag expansion, entity detection, and session-start surfacing. The right knowledge at the right time.\n\nARIA — Anchored Reasoning and Insight Architecture — is a human-in-the-loop knowledge kit focused on knowledge refinement and applied reasoning in Claude Code sessions.",
  1704. "source": {
  1705. "source": "git-subdir",
  1706. "url": "https://github.com/mikeprasad/aria-knowledge.git",
  1707. "path": "plugin",
  1708. "ref": "main",
  1709. "sha": "c8f1bb7ca0e1c488beebe17cf0e3fae842aabaac"
  1710. },
  1711. "homepage": "https://github.com/mikeprasad/aria-knowledge"
  1712. },
  1713. {
  1714. "name": "armo-ctrl",
  1715. "description": "Drive the ARMO Cloud and Kubernetes security platform from natural language: incidents, CVEs, posture, runtime, and policies, with dry-run safety on every mutation.",
  1716. "source": {
  1717. "source": "url",
  1718. "url": "https://github.com/armosec/armoctl.git",
  1719. "sha": "a87feb0babec89c5265fb765a3a611865668714b"
  1720. },
  1721. "homepage": "https://hub.armosec.io/docs/claude-code"
  1722. },
  1723. {
  1724. "name": "armorclaude",
  1725. "description": "Intent-based security enforcement for Claude Code. ArmorClaude makes Claude declare what it intends to do before doing it, then checks every tool call against that plan. Adds policy rules, intent drift detection, cryptographic proofs, and audit logging to the ArmorIQ platform. Works in both Claude Code CLI and Claude Desktop. Install with one curl command, optionally connect to ArmorIQ for signed JWT tokens and dashboard visibility.",
  1726. "source": {
  1727. "source": "url",
  1728. "url": "https://github.com/armoriq/armorClaude.git",
  1729. "sha": "d4cd8fd9cc5148064cf778937ba130df2532589e"
  1730. },
  1731. "homepage": "https://armorclaude-docs.armoriq.ai"
  1732. },
  1733. {
  1734. "name": "arn-code",
  1735. "description": "Structured, artifact-driven development pipeline for Claude Code — plan, implement, review, and ship features with three ceremony tiers. 25 pipeline skills, 14 specialist agents.",
  1736. "source": {
  1737. "source": "git-subdir",
  1738. "url": "AppsVortex/arness",
  1739. "path": "plugins/arn-code",
  1740. "ref": "main",
  1741. "sha": "598ff6dc1c7e1a7bc7298567adc688cb482e7fa6"
  1742. },
  1743. "homepage": "https://arness.appsvortex.com"
  1744. },
  1745. {
  1746. "name": "arn-infra",
  1747. "description": "Infrastructure and deployment for Claude Code — containerization, IaC generation (OpenTofu/Pulumi/CDK), CI/CD pipelines, environments, secrets, monitoring. 23 skills, 9 agents.",
  1748. "source": {
  1749. "source": "git-subdir",
  1750. "url": "AppsVortex/arness",
  1751. "path": "plugins/arn-infra",
  1752. "ref": "main",
  1753. "sha": "598ff6dc1c7e1a7bc7298567adc688cb482e7fa6"
  1754. },
  1755. "homepage": "https://arness.appsvortex.com"
  1756. },
  1757. {
  1758. "name": "arn-spark",
  1759. "description": "Guided greenfield pipeline from raw idea to working prototype — product discovery with AI-assisted persona generation, architecture vision, use case authoring, project scaffolding, and interactive prototype validation.",
  1760. "source": {
  1761. "source": "git-subdir",
  1762. "url": "AppsVortex/arness",
  1763. "path": "plugins/arn-spark",
  1764. "ref": "main",
  1765. "sha": "598ff6dc1c7e1a7bc7298567adc688cb482e7fa6"
  1766. },
  1767. "homepage": "https://arness.appsvortex.com"
  1768. },
  1769. {
  1770. "name": "arquestra",
  1771. "description": "Run and manage Arquestra workflows from Claude Code. Orchestrate computational chemistry (RDKit, ORCA, GROMACS, Vina, OpenMM) and HPC tasks — create runs, track status, list machines and packs.",
  1772. "source": {
  1773. "source": "url",
  1774. "url": "https://github.com/Apertura-AI/arquestra-claude-plugin.git",
  1775. "sha": "888060d458a12892fbb5af106fd796ec0f58a90f"
  1776. },
  1777. "homepage": "https://arquestra.ai"
  1778. },
  1779. {
  1780. "name": "artel",
  1781. "description": "Mesh infrastructure for AI teams. One self-hosted server gives a fleet of agents shared semantic memory, tasks, agent-to-agent messages, and session handoffs. Artel instances mesh together via RSS/JSON feed subscriptions — memory flows across machines, frameworks, and providers with no central coordinator — while a background archivist keeps the shared memory auto-organizing: merging conflicts, synthesizing cross-agent findings, and decaying stale knowledge.",
  1782. "source": {
  1783. "source": "url",
  1784. "url": "https://github.com/NicolasPrimeau/artel.git",
  1785. "sha": "542ea7022d6b8cc0de4ea38f8aef48d996e77a43"
  1786. },
  1787. "homepage": "https://github.com/NicolasPrimeau/artel"
  1788. },
  1789. {
  1790. "name": "artibot",
  1791. "description": "Artibot은 Claude Code를 위한 자율 에이전트 OS입니다. 듀얼 프로세스(System 1/2) 인지 라우팅, 평생 학습(GRPO+RLVR), 28개 전문가 에이전트의 병렬 팀 협업, 100여 개의 스킬과 56개 슬래시\n커맨드를 통해 코드 엔지니어링·마케팅·디자인 워크플로우를 자동으로 오케스트레이션합니다. Hook 기반 안전망, 자동 메모리 관리, MCP 통합, OTEL 옵저버빌리티, Git 자동 동기화, 5,000개\n이상의 테스트로 프로덕션 등급의 안정성을 제공합니다.",
  1792. "source": {
  1793. "source": "git-subdir",
  1794. "url": "https://github.com/Yoodaddy0311/artibot.git",
  1795. "path": "plugins/artibot",
  1796. "ref": "master",
  1797. "sha": "1be0246a6ea05e0d66123a727f1507a0e90bee69"
  1798. },
  1799. "homepage": "https://github.com/Yoodaddy0311/artibot"
  1800. },
  1801. {
  1802. "name": "artillery-mcp",
  1803. "description": "Artillery 2.x load-testing via MCP — one-command install for @kosiakmd/artillery-mcp. Ships a stdio MCP server with 18 tools (run_test_from_file, run_fargate, read_artillery_output, parse_results, run_report, compare_results, etc.) plus an agent SKILL.md with decision tree, call patterns, and gotchas. Config-driven: drop an .artillery-mcp.config.json at your project root and a 19th run_project_lt tool appears for one-liner flow×environment launches. Uses the published @kosiakmd/artillery-mcp npm package via npx caret-minor pin (patch fixes flow through automatically). MIT, open source, multi-arch Docker image also available. Prerequisites: Node 20+, artillery CLI on PATH.",
  1804. "source": {
  1805. "source": "git-subdir",
  1806. "url": "https://github.com/kosiakMD/artillery-mcp-plugin.git",
  1807. "path": "plugins/artillery-mcp",
  1808. "ref": "main",
  1809. "sha": "2dc3ce67b9672b35f30156ff5f21855f05352d12"
  1810. },
  1811. "homepage": "https://github.com/kosiakMD/artillery-mcp"
  1812. },
  1813. {
  1814. "name": "arxitect",
  1815. "description": "Enforces best-practice software design & architecture",
  1816. "source": {
  1817. "source": "url",
  1818. "url": "https://github.com/andonimichael/arxitect.git",
  1819. "sha": "473c4867e9be818033f654bacf82615bc8eed694"
  1820. },
  1821. "homepage": "https://github.com/andonimichael/arxitect"
  1822. },
  1823. {
  1824. "name": "asodev",
  1825. "description": "ASO.dev Skills is a Claude Code plugin for App Store Optimization and app growth work. It gives product, marketing, and growth teams 27 focused Agent Skills for ASO audits, App Store and Google Play metadata, keyword research, competitor analysis, localization, review analysis, screenshot briefs, In-App Events, featuring nominations, CPP/PPO planning, subscriptions, IAP, pricing, monetization, seasonal campaigns, ASO.dev local AI Companion MCP workflows, and ASO.dev public API guidance.",
  1826. "source": {
  1827. "source": "url",
  1828. "url": "https://github.com/asodevapp/skills.git",
  1829. "sha": "2ba6f60f7c9f04e0565ddabb2910086f42095e9e"
  1830. },
  1831. "homepage": "https://aso.dev/tools/ai-skills/"
  1832. },
  1833. {
  1834. "name": "asset-generator",
  1835. "description": "Generate production-ready visual assets without leaving your terminal. Describe what you need in plain English: icons, illustrations, placeholders, and Blueprint Studio generates them in your brand's style and saves them to your project. Manage brands, invite teammates, create custom styles, and automate with API keys. Browser-based auth, no keys to copy.",
  1836. "source": {
  1837. "source": "url",
  1838. "url": "https://github.com/Blueprint-Studio-AI/claude-code-asset-generator.git",
  1839. "sha": "ef3c1555ba0b8277ed60e86a3adb0614badc94ea"
  1840. },
  1841. "homepage": "https://tools.blueprintstudio.ai"
  1842. },
  1843. {
  1844. "name": "astravue",
  1845. "description": "Connect to Astravue project management. Manage spaces, projects, tasks, subtasks, checklists, comments, time tracking, and team collaboration through natural language.",
  1846. "source": {
  1847. "source": "url",
  1848. "url": "https://github.com/AstravueOrg/astravue-mcp-server.git",
  1849. "sha": "b98f7526569afca9d7bcf7bcaea879c93108aa65"
  1850. },
  1851. "homepage": "https://astravue.com"
  1852. },
  1853. {
  1854. "name": "astronomer",
  1855. "description": "Data engineering plugin for Apache Airflow and Astronomer. Author DAGs with best practices, debug pipeline failures, explore data warehouse schemas, trace data lineage, profile tables, migrate from Airflow 2 to 3, and manage local and cloud deployments all from your editor.",
  1856. "source": {
  1857. "source": "url",
  1858. "url": "https://github.com/astronomer/agents.git",
  1859. "sha": "dbd9bb79c4f7b7ac9c1cdd2b4b75213c81f423e5"
  1860. },
  1861. "homepage": "https://github.com/astronomer/agents"
  1862. },
  1863. {
  1864. "name": "astronomer-data-agents",
  1865. "description": "Data engineering for Apache Airflow and Astronomer. Author DAGs with best practices, debug pipeline failures, trace data lineage, profile tables, migrate Airflow 2 to 3, and manage local and cloud deployments.",
  1866. "category": "development",
  1867. "source": {
  1868. "source": "url",
  1869. "url": "https://github.com/astronomer/agents.git",
  1870. "sha": "dbd9bb79c4f7b7ac9c1cdd2b4b75213c81f423e5"
  1871. },
  1872. "homepage": "https://github.com/astronomer/agents"
  1873. },
  1874. {
  1875. "name": "atelier",
  1876. "description": "Universal multi-agent project harness for Claude Code — run any project through a structured AI team from discovery to release.",
  1877. "source": {
  1878. "source": "git-subdir",
  1879. "url": "https://github.com/dudgns0908/atelier.git",
  1880. "path": "atelier",
  1881. "ref": "main",
  1882. "sha": "c32662444d47b4e9e4b6f4c07d3fd32b29a252e2"
  1883. },
  1884. "homepage": "https://github.com/dudgns0908/atelier"
  1885. },
  1886. {
  1887. "name": "atelier-pipeline",
  1888. "description": "Atelier Pipeline has two core systems:\n\nMulti-Agent Orchestration. Eleven specialized agent personas with clear responsibilities, strict boundaries, and independent quality verification. Eva orchestrates, Robert handles product, Sable designs UX, Sarah architects, Colby builds, Poirot blind-reviews every wave, Agatha documents, Ellis commits, Distillator compresses cross-phase artifacts, Sherlock investigates user-reported bugs, and Sentinel audits security (opt-in). Custom agents can be added via agent discovery. Specs get written, designs get validated, every change passes Eva's mechanical test gate plus Poirot blind review, and nothing ships without review. Works with Claude Code and Cursor.\n\nAtelier Brain. A persistent memory layer backed by PostgreSQL and vector embeddings that gives your agents institutional memory across sessions. Without it, every time you close a terminal you lose the architectural decisions that shaped your implementation, the user corrections that steered scope, the rejected alternatives that explain why you didn't go a different way, and the QA lessons that prevent recurring bugs. The brain captures all of this during pipeline runs and surfaces it automatically when agents need context. It includes write-time conflict detection, TTL-based knowledge decay, and background consolidation that synthesizes raw observations into higher-level insights. The pipeline works without the brain -- but with it, session 12 of a feature build has the same context as session 1.",
  1889. "source": {
  1890. "source": "url",
  1891. "url": "https://github.com/robertsfeir/atelier-pipeline.git",
  1892. "sha": "56e46b938a0c818f9690c3ab480a4e3172748601"
  1893. },
  1894. "homepage": "https://github.com/robertsfeir/atelier-pipeline/blob/main/docs/guide/user-guide.md"
  1895. },
  1896. {
  1897. "name": "atlan",
  1898. "description": "Atlan data catalog plugin for Claude Code. Search, explore, govern, and manage your data assets through natural language. Powered by the Atlan MCP server with semantic search, lineage traversal, glossary management, data quality rules, and more.",
  1899. "source": {
  1900. "source": "url",
  1901. "url": "https://github.com/atlanhq/agent-toolkit.git",
  1902. "sha": "86bb1ad27f80e189b328333d2271b360ae579f2b"
  1903. },
  1904. "homepage": "https://docs.atlan.com/"
  1905. },
  1906. {
  1907. "name": "atlassian-forge-skills",
  1908. "description": "Forge-focused skills and MCP configuration for Atlassian Forge: scaffold and deploy apps (forge create, templates, dev spaces), pre-deploy review, systematic debugging, plus Forge docs and Atlassian Design System lookups via MCP.",
  1909. "source": {
  1910. "source": "url",
  1911. "url": "https://github.com/atlassian/forge-skills.git",
  1912. "sha": "a8eb109708de685dbad5b92eb25890d0a20addff"
  1913. },
  1914. "homepage": "https://developer.atlassian.com/platform/forge/"
  1915. },
  1916. {
  1917. "name": "atp",
  1918. "description": "Design, spec, and evaluate crypto exchange features — grounded in Vietnamese law, security incidents, and protocol analysis. From idea to actionable solutions in minutes.",
  1919. "source": {
  1920. "source": "url",
  1921. "url": "https://github.com/s27183/adi-atp-plugin.git",
  1922. "sha": "3fefdf0a703dd8a25006fc2dbaa3c72cd5742106"
  1923. },
  1924. "homepage": "https://atp.bigsmallai.com/"
  1925. },
  1926. {
  1927. "name": "attacca",
  1928. "description": "Attacca is a multi-agent coding orchestrator. Manager plans, Engineer builds, Security audits, you ship. Seven Specialists, one workplace.",
  1929. "source": {
  1930. "source": "url",
  1931. "url": "https://github.com/adihebbalae/Attacca.git",
  1932. "sha": "d5e18d65becc5fb646ff33e459e87e52a1500196"
  1933. },
  1934. "homepage": "https://github.com/adihebbalae/Attacca"
  1935. },
  1936. {
  1937. "name": "attention",
  1938. "description": "Connect Claude to Attention — search sales conversations, view calls transcripts, get AI-powered insights, and chat with the Attention super agent.",
  1939. "source": {
  1940. "source": "url",
  1941. "url": "https://github.com/attentiontech/attention.git",
  1942. "sha": "b8d644326977703b8efbea47c4fb66c32d16bb79"
  1943. },
  1944. "homepage": "https://docs.attention.com/attention-mcp-server"
  1945. },
  1946. {
  1947. "name": "attive",
  1948. "description": "Turn Claude into your GTM analyst. Query accounts, deals, calls, and pipeline data with natural language — powered by Attive's unified data graph.",
  1949. "source": {
  1950. "source": "url",
  1951. "url": "https://github.com/dpivot/attive-mcp-plugin.git",
  1952. "sha": "195ef86a06a8284d8d0f5bd3379dfd3f883ccc30"
  1953. },
  1954. "homepage": "https://attive.ai"
  1955. },
  1956. {
  1957. "name": "attune-lite",
  1958. "description": "Six developer workflow commands for Claude Code: code review, security audit, test generation, test fixing, bug prediction, and documentation generation.",
  1959. "source": {
  1960. "source": "url",
  1961. "url": "https://github.com/Smart-AI-Memory/attune-lite.git",
  1962. "sha": "07ae2ae91c1938ca1507b942da5f0371d7ae966e"
  1963. },
  1964. "homepage": "https://smartaimemory.com/attune-lite/"
  1965. },
  1966. {
  1967. "name": "audiorective",
  1968. "description": "Web Audio toolkit for coding agents - reactive primitives, sample-accurate scheduling, and React/three.js bindings. Build synths, sequencers, and spatial audio without re-inventing the plumbing.",
  1969. "source": {
  1970. "source": "url",
  1971. "url": "https://github.com/audiorective/audiorective.git",
  1972. "sha": "217a4bc343b5e8c50d665043cccc8383e88a6cde"
  1973. },
  1974. "homepage": "https://github.com/audiorective/audiorective"
  1975. },
  1976. {
  1977. "name": "audit-project",
  1978. "description": "Multi-agent iterative code review until zero issues remain. Spawns up to 10 specialist reviewers (code quality, security, performance, test coverage, architecture, database, API, frontend, backend, DevOps) chosen based on the project's signals. Each pass produces certainty-graded findings (HIGH / MEDIUM / LOW); HIGH findings auto-fix where safe. The orchestrator iterates passes until zero open issues remain or a max-iteration cap is reached. Specialists are role-based (defined inline via Task tool, not file-based agents) so they don't bloat the plugin's agent count. Designed to plug into /next-task and /prepare-delivery as the deep-review phase.",
  1979. "source": {
  1980. "source": "url",
  1981. "url": "https://github.com/agent-sh/audit-project.git",
  1982. "sha": "787d4043f6610601b2f72d04abed027670bf69cc"
  1983. },
  1984. "homepage": "https://github.com/agent-sh/audit-project"
  1985. },
  1986. {
  1987. "name": "audit-suite",
  1988. "description": "10 expert audit lenses + full-audit orchestrator + 5 bundled reference skills. Review plans and code through the eyes of\nDesign, UX, Frontend, Backend, Structural, Repo, Production, DX, Performance, and Accessibility engineers.",
  1989. "source": {
  1990. "source": "url",
  1991. "url": "https://github.com/Recusive/Orbit-plugin.git",
  1992. "sha": "db14d72bd58141f66157691ca5c69662123c51d6"
  1993. },
  1994. "homepage": "https://orbit.build/plugin"
  1995. },
  1996. {
  1997. "name": "aura-frog",
  1998. "description": "Structured AI development with 10 specialized agents, 5-phase TDD workflow, and performance-conscious design. Aura Frog turns Claude Code into a disciplined development team — agents auto-select per task, tests are written before code (RED→GREEN→REFACTOR), and 3-tier rule architecture loads only what's needed (74% less context overhead). Includes 27 lifecycle hooks, 6 bundled MCP servers, git worktree isolation, phase checkpoints with rollback, collaborative multi-perspective planning, and a self-learning system that improves with every session. Zero config required — install and start your first workflow in 30 seconds.",
  1999. "source": {
  2000. "source": "git-subdir",

Lines 2,001–3,069 are not shown. The link to the file on GitHub has every line.

README.md · README · 31 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Claude Plugins — Community
  2. Community-contributed plugins for [Claude Cowork](https://claude.com/product/cowork) and [Claude Code](https://claude.com/product/claude-code).
  3. ## What this repo is
  4. A **read-only mirror** of the community plugin marketplace. The `.claude-plugin/marketplace.json` file here is the list of community plugins available to install. It is synced nightly from Anthropic's internal review pipeline.
  5. Every plugin listed here has been submitted via [claude.ai](https://clau.de/plugin-directory-submission), passed automated security scanning, and been approved for distribution.
  6. ## Using this marketplace
  7. ### Claude Cowork
  8. Install plugins from [claude.com/plugins](https://claude.com/plugins/).
  9. ### Claude Code
  10. ```bash
  11. claude plugin marketplace add anthropics/claude-plugins-community
  12. claude plugin install <plugin-name>@claude-community
  13. ```
  14. ## Submitting a plugin
  15. Submit via **[clau.de/plugin-directory-submission](https://clau.de/plugin-directory-submission)**. Pull requests opened directly against this repo are closed automatically — all changes flow from the internal review pipeline.
  16. ## Related
  17. - [anthropics/claude-plugins-official](https://github.com/anthropics/claude-plugins-official) — Anthropic-maintained plugins
  18. - [anthropics/knowledge-work-plugins](https://github.com/anthropics/knowledge-work-plugins) — role-specific knowledge-work plugins

Ratings and comments

Sign in to rate this skill.

Sign in

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