Skip to content
Back to search

learn-skills.dev

Curated high-quality AI Agent Skills. Search, install, copy and share. Works with Claude Code, Cursor, OpenClaw, and other AI coding tools.

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. Its scripts were only partly scanned.

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

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/NeverSight/learn-skills.dev 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/NeverSight/learn-skills.dev'

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/neversight--learn-skills-dev/badge.svg)](/listings/neversight--learn-skills-dev)

HTML

<a href="/listings/neversight--learn-skills-dev"><img src="/api/listings/neversight--learn-skills-dev/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 · 221 lines

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

  1. <div align="center">
  2. <h1><a href="https://www.learn-skills.dev">learn-skills.dev</a></h1>
  3. <p>Curated high-quality AI Agent Skills. Search, install, copy and share.<br>
  4. Works with Claude Code, Cursor, OpenClaw, and other AI coding tools.</p>
  5. <p><strong>Web App:</strong> <a href="https://www.learn-skills.dev">https://www.learn-skills.dev</a> — Search, install, copy and share AI Agent Skills.</p>
  6. <p>
  7. English | <a href="./README.zh.md">简体中文</a> | <a href="./README.tw.md">繁體中文</a> |
  8. <a href="./README.ja.md">日本語</a> |
  9. <a href="./README.ko.md">한국어</a> |
  10. <a href="./README.fr.md">Français</a> |
  11. <a href="./README.de.md">Deutsch</a> |
  12. <a href="./README.es.md">Español</a> |
  13. <a href="./README.it.md">Italiano</a> |
  14. <a href="./README.ru.md">Русский</a> |
  15. <a href="./README.ar.md">العربية</a>
  16. </p>
  17. </div>
  18. ## Data Sources
  19. ### Current Providers
  20. - **[skills.sh](https://skills.sh)** - Community-curated skills leaderboard
  21. - All Time (`/`) - Total installs ranking
  22. - Trending (`/trending`) - Recent growth ranking
  23. - Hot (`/hot`) - Daily installs ranking
  24. ### Planned Providers
  25. - **GitHub Trending** - Popular skill repos on GitHub
  26. - **Awesome Lists** - Curated awesome-* lists for AI agent skills
  27. ### Manual Skills
  28. Skills not tracked by any provider can be manually added via `data/manual_skills.json`:
  29. ```json
  30. {
  31. "skills": [
  32. {
  33. "source": "owner/repo",
  34. "skillId": "skill-name",
  35. "name": "Skill Display Name",
  36. "installs": 1
  37. }
  38. ]
  39. }
  40. ```
  41. Manual skills will be:
  42. - Fetched for their `SKILL.md` from GitHub (using standard skill folder detection)
  43. - Included in `skills_index.json` with `providerId: "manual"`
  44. - **Not** overwritten by the crawler (they persist across runs)
  45. - **Deduplicated**: If skills.sh later tracks a manual skill, it will use skills.sh data instead
  46. Note: `installs` should be at least 1 (minimum value).
  47. ## Output Files
  48. The crawler generates files in the `data/` directory:
  49. ### `data/skills.json`
  50. Complete skill data containing all three leaderboards:
  51. ```json
  52. {
  53. "updatedAt": "2024-01-27T00:00:00.000Z",
  54. "allTime": [...],
  55. "trending": [...],
  56. "hot": [...]
  57. }
  58. ```
  59. ### `data/skills_index.json`
  60. Website-friendly index for *all* skills (built from `data/skills.json`):
  61. - Includes `description` as a **path** to `description_en.txt` (when a cached `SKILL.md` exists under `data/skills-md/`)
  62. - Includes `skillMdPath` so your website can fetch and render the full markdown
  63. - **Deduplicated** by `id` (`<source>/<skillId>`). If the upstream data contains duplicates, the index keeps the entry with the highest `installsAllTime`.
  64. ### `data/feed.json`
  65. Simplified feed format (top 50 from each leaderboard).
  66. It also tries to enrich each item with a `description` by fetching the corresponding GitHub `SKILL.md` (cached under `data/skills-md/`):
  67. ```json
  68. {
  69. "title": "Skills Feed",
  70. "description": "Aggregated AI agent skills from multiple sources",
  71. "link": "https://github.com/user/skills_feed",
  72. "updatedAt": "2024-01-27T00:00:00.000Z",
  73. "topAllTime": [...],
  74. "topTrending": [...],
  75. "topHot": [...]
  76. }
  77. ```
  78. ### `data/skills-md/`
  79. Cached `SKILL.md` files fetched from GitHub, using common skill folder locations such as:
  80. - `skills/<skillId>/SKILL.md` (most common)
  81. - `.claude/skills/<skillId>/SKILL.md`
  82. - `.cursor/skills/<skillId>/SKILL.md`
  83. - `.codex/skills/<skillId>/SKILL.md`
  84. - `plugins/<plugin-name>/skills/<skillId>/SKILL.md` (common in plugin-based repos, e.g. Expo)
  85. When a `SKILL.md` is present, the crawler also generates:
  86. - `description_en.txt` (extracted from the SKILL.md frontmatter `description` when available)
  87. By default, the crawler only fetches `SKILL.md` for skills included in the top lists (to keep the daily job fast).
  88. If you really want to sync *all* skills from `data/skills.json`, you can run:
  89. ```bash
  90. SYNC_ALL_SKILL_MDS=1 bun run crawl
  91. ```
  92. ### `data/feed.xml`
  93. RSS 2.0 feed (XML). This is meant for RSS readers / subscriptions.
  94. - It is generated from the current crawl + the previous `data/feed.json`
  95. - It only publishes meaningful changes (new entries / rank jumps) to avoid spamming
  96. ## Usage
  97. ### Local Development
  98. ```bash
  99. # Install dependencies
  100. bun install
  101. # Run crawler
  102. bun run crawl
  103. ```
  104. Tip: if you want more complete GitHub `SKILL.md` coverage (including plugin-style paths like `plugins/*/skills/...`),
  105. set `GITHUB_TOKEN` to avoid GitHub API rate limits:
  106. ```bash
  107. export GITHUB_TOKEN=ghp_xxx
  108. bun run crawl
  109. ```
  110. ### GitHub Actions
  111. After pushing to GitHub, the crawler will:
  112. 1. Run automatically daily at UTC 0:00
  113. 2. Support manual triggering (click "Run workflow" in Actions tab)
  114. 3. Run automatically on push to main branch
  115. ## Using in Your Website
  116. You can fetch data directly via GitHub Raw URL:
  117. ```
  118. https://raw.githubusercontent.com/<username>/<repo>/main/data/skills.json
  119. ```
  120. Or use jsDelivr CDN (faster):
  121. ```
  122. https://cdn.jsdelivr.net/gh/<username>/<repo>@main/data/skills.json
  123. ```
  124. ### RSS Subscription (Recommended)
  125. Subscribe to the RSS feed:
  126. ```
  127. https://raw.githubusercontent.com/<username>/<repo>/main/data/feed.xml
  128. ```
  129. Or via jsDelivr CDN:
  130. ```
  131. https://cdn.jsdelivr.net/gh/<username>/<repo>@main/data/feed.xml
  132. ```
  133. ### Example Code
  134. ```typescript
  135. // In Next.js
  136. const SKILLS_DATA_URL = 'https://cdn.jsdelivr.net/gh/your-username/skills-crawler@main/data/skills.json';
  137. export async function getSkillsData() {
  138. const res = await fetch(SKILLS_DATA_URL, {
  139. next: { revalidate: 3600 } // Revalidate every hour
  140. });
  141. return res.json();
  142. }
  143. ```
  144. ## Notes
  145. - Data is updated daily
  146. - Please comply with each provider's terms of service
  147. - For personal learning and research purposes only
  148. ## Recommended Tools
  149. Outputs from learn-skills (notes, summaries, data) pair well with AI presentation tools to quickly turn them into shareable slides.
  150. **Level up your workflow**
  151. Turn your learn-skills results into professional slides? Try PopAi for one-click AI-generated presentations:
  152. [https://www.popai.pro](https://www.popai.pro)
  153. ## Contributing
  154. Want to add a new skill source? PRs are welcome! Check out the existing provider implementations in the codebase.

Ratings and comments

Sign in to rate this skill.

Sign in

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