Skip to content
Back to search

SKILL

This repository stores personal AI Agent skills in a scalable directory layout.

Safety scan

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

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/innei--skill/badge.svg)](/listings/innei--skill)

HTML

<a href="/listings/innei--skill"><img src="/api/listings/innei--skill/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

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.

README.md · README · 146 lines

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

This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.

  1. # Personal Skills Repository
  2. This repository stores personal Codex / Claude Code skills in a scalable directory layout.
  3. ## Layout
  4. ```text
  5. SKILL/
  6. ├── README.md
  7. ├── skills/
  8. │ ├── automation/
  9. │ ├── content/
  10. │ ├── infrastructure/
  11. │ ├── research/
  12. │ └── writing/
  13. │ └── <skill-name>/
  14. │ ├── SKILL.md
  15. │ ├── references/ (optional)
  16. │ ├── scripts/ (optional)
  17. │ └── assets/ (optional)
  18. └── templates/
  19. ├── SKILL.template.md
  20. └── SKILL.with-references.template.md
  21. ```
  22. ## Conventions
  23. - Place real skills only under `skills/`.
  24. - Group skills by a stable domain: `automation`, `content`, `infrastructure`, `research`, or `writing`.
  25. - Each skill lives in its own directory with a required `SKILL.md` plus optional `agents/`, `references/`, `scripts/`, or `assets/`.
  26. - Keep `templates/` for reusable skeletons only — they are not active skills.
  27. - Avoid credentials, tokens, or machine-specific secrets in skill files.
  28. - One skill per directory, even when the first version is only a single `SKILL.md`.
  29. - Domain folders are stable classification buckets; do not encode transient project names at the domain level.
  30. ## Skills
  31. ### Automation
  32. > Repeated shell workflows, CLI procedures, scripting playbooks.
  33. | Skill | Purpose |
  34. | ----- | ------- |
  35. | [`iphone-duo-dual-pane`](skills/automation/iphone-duo-dual-pane/SKILL.md) | Build, lay out, and verify an iOS app on the iPhone Duo foldable — measured inner/outer displays, right status safe area, dual-pane UIArrangementViewController, hinge postures, and simctl/axe verification |
  36. | [`profiling-electron-startup`](skills/automation/profiling-electron-startup/SKILL.md) | Segment an Electron app's launch (native / main bundle / window / renderer) with instrumented entry, CPU profile and startup trace, then apply only the levers whose segment is big |
  37. | [`react-rerender-audit`](skills/automation/react-rerender-audit/SKILL.md) | Measure React re-render counts over CDP, name the exact hook causing them, fix by lowering state, lock with a Profiler test |
  38. | [`session-handoff`](skills/automation/session-handoff/SKILL.md) | Produce a self-contained handoff prompt for another agent when delegating continued work |
  39. | [`session-to-skill-and-blog`](skills/automation/session-to-skill-and-blog/SKILL.md) | Classify a completed engineering session into a narrative blog, zero or more reusable skills, and project-local documentation |
  40. | [`working-summary`](skills/automation/working-summary/SKILL.md) | Work summary / 周报 from GitHub PRs/commits and optional Linear trackers; markdown for notes (e.g. Obsidian) |
  41. ### Content
  42. > Media generation, character assets, site SEO imagery.
  43. | Skill | Purpose |
  44. | ----- | ------- |
  45. | [`acg-character-settei`](skills/content/acg-character-settei/SKILL.md) | Generate ACG character settei sheet (multi-view + expression + callouts) from a reference image via Gemini |
  46. | [`app-store-listing`](skills/content/app-store-listing/SKILL.md) | One-shot App Store listing: copy, official-bezel screenshots, and Connect questionnaires |
  47. | [`chibi-sticker-sheet`](skills/content/chibi-sticker-sheet/SKILL.md) | Generate a 4×8 chibi sticker sheet via Codex CLI (default) or Gemini, with alpha keying, 1:1 cell slicing, and matching banners |
  48. | [`gemini-image-generation`](skills/content/gemini-image-generation/SKILL.md) | Gemini text-to-image and image-to-image — style transfer, character consistency, watermark removal |
  49. | [`gemini-seo-image-assets`](skills/content/gemini-seo-image-assets/SKILL.md) | Generate favicon/OG artwork via Gemini, export icon variants, and wire SEO metadata |
  50. | [`product-visuals`](skills/content/product-visuals/SKILL.md) | Compose product marketing visuals from real macOS/iOS screenshots in official device bezels |
  51. ### Infrastructure
  52. > Deployment, servers, databases, containers, networking, observability.
  53. | Skill | Purpose |
  54. | ----- | ------- |
  55. | [`capture-output-via-sidechannel`](skills/infrastructure/capture-output-via-sidechannel/SKILL.md) | Capture stdout/stderr from runners/CI/containers when log retrieval is unavailable, by persisting output to a readable store |
  56. | [`ci-smoke-needs-real-deps`](skills/infrastructure/ci-smoke-needs-real-deps/SKILL.md) | Fix CI release smoke tests that fail after a stack migration by aligning service containers and env vars with `ci.yml` |
  57. | [`cloudflare-r2-upload`](skills/infrastructure/cloudflare-r2-upload/SKILL.md) | Upload files/batches to Cloudflare R2 via `wrangler`, resolve multi-account context, set MIME, and verify public URLs |
  58. | [`dokploy-api-cli`](skills/infrastructure/dokploy-api-cli/SKILL.md) | Operate Dokploy deployments via REST API — create/update/deploy services, switch sources, script redeploys |
  59. | [`dokploy-internal-oneshot`](skills/infrastructure/dokploy-internal-oneshot/SKILL.md) | Run ephemeral one-shot tasks inside a Dokploy project's internal network without exposing services publicly |
  60. | [`dokploy-traefik-traffic-split`](skills/infrastructure/dokploy-traefik-traffic-split/SKILL.md) | Canary two backends on one Dokploy domain with path-aware weighted+sticky Traefik routing; covers SPA asset trap and rollback |
  61. | [`edge-canary-split`](skills/infrastructure/edge-canary-split/SKILL.md) | Cookie-sticky canary rollout between two Vercel apps via a Cloudflare Worker, with hashed assets offloaded to R2 so they never traverse the worker |
  62. | [`electron-native-lib-extraction`](skills/infrastructure/electron-native-lib-extraction/SKILL.md) | Extract an in-app Electron native-module integration into a standalone source-distributed npm library with its release toolchain |
  63. | [`mx-space-remote-db-access`](skills/infrastructure/mx-space-remote-db-access/SKILL.md) | Remote `mx-space` PostgreSQL inspection and guarded updates via `ssh → docker exec → psql` |
  64. | [`mx-space-remote-translation-audit`](skills/infrastructure/mx-space-remote-translation-audit/SKILL.md) | Remote translation auditing — coverage checks, hash freshness, and route-level verification |
  65. | [`nextjs-rsc-to-react-router-v8-migration`](skills/infrastructure/nextjs-rsc-to-react-router-v8-migration/SKILL.md) | Migrate a Next.js App-Router / RSC site to React Router v8 for CDN-cacheable SSR under multi-locale cost pressure |
  66. | [`vless-reality-aws-lightsail`](skills/infrastructure/vless-reality-aws-lightsail/SKILL.md) | End-to-end VLESS+Reality+Vision on AWS Lightsail, with Alpine LXC SOCKS5 bridge for LAN and Surge wiring |
  67. ### Research
  68. > Data analysis, report generation, conversation mining.
  69. | Skill | Purpose |
  70. | ----- | ------- |
  71. | [`chat-export-report`](skills/research/chat-export-report/SKILL.md) | Analyze exported chat logs (WeChat / Telegram / iMessage / QQ) into layered, drill-down reports grounded in original quotes |
  72. | [`codebase-value-audit`](skills/research/codebase-value-audit/SKILL.md) | Audit whether a codebase's size is justified: strict LOC accounting, product-surface inventory, per-sub-product line attribution and worth verdicts |
  73. ### Writing
  74. > Structured writing, design docs, editorial judgment.
  75. | Skill | Purpose |
  76. | ----- | ------- |
  77. | [`co-write-blog-post`](skills/writing/co-write-blog-post/SKILL.md) | Co-write a blog post with the agent in the online Mix Space editor; agent edits land live via `mxs draft cat` / `patch` |
  78. | [`generate-design-md`](skills/writing/generate-design-md/SKILL.md) | Produce `DESIGN.md` for a brand/site from live CSS and tokens (awesome-design-md format) |
  79. | [`holding-analytical-judgment`](skills/writing/holding-analytical-judgment/SKILL.md) | Keep analysis grounded in evidence; do not flip conclusions for mood alone (code review, diagnosis, post-mortems) |
  80. ## Agent Integration
  81. Skills are loaded by Copilot CLI (`.agent/`) and Claude Code (`.claude/`) via **flat symlinks** under their respective `skills/` directories. Each agent expects skills exactly one level deep: `.agent/skills/<skill-name>/SKILL.md`.
  82. ```text
  83. .agent/skills/
  84. └── <skill-name> -> ../../skills/<domain>/<skill-name>
  85. .claude/skills/
  86. └── <skill-name> -> ../../skills/<domain>/<skill-name>
  87. ```
  88. > [!WARNING]
  89. > Do **not** symlink the entire `skills/` directory — agents will not discover nested domain subdirectories.
  90. ## Adding a New Skill
  91. 1. Create a directory under `skills/<domain>/<skill-name>/`.
  92. 2. Copy `templates/SKILL.template.md` into that directory as `SKILL.md`.
  93. 3. Fill in the frontmatter and keep the body concise.
  94. 4. Add optional `references/`, `scripts/`, or `assets/` only when they improve reuse.
  95. 5. Add a row to the matching domain table in this README.
  96. 6. Create flat symlinks in both agent skill roots:
  97. ```bash
  98. ln -sf ../../skills/<domain>/<skill-name> .agent/skills/<skill-name>
  99. ln -sf ../../skills/<domain>/<skill-name> .claude/skills/<skill-name>
  100. ```
  101. ## Naming Guidance
  102. - Directory names: lowercase kebab-case.
  103. - Skill `name` values: stable and descriptive.
  104. - Prefer names that state both target and action, e.g. `mx-space-remote-db-access` or `article-publish-checklist`.
  105. ## Repository Hooks
  106. A pre-commit hook in `.githooks/pre-commit` enforces the rules above: every skill under `skills/<domain>/<name>/SKILL.md` must have a README entry and matching flat symlinks under `.agent/skills/` and `.claude/skills/`. Orphan symlinks fail the hook too.
  107. Enable it once per clone:
  108. ```bash
  109. git config core.hooksPath .githooks
  110. ```
  111. If you must bypass it for a non-skill commit, use `git commit --no-verify`.

Ratings and comments

Sign in to rate this skill.

Sign in

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