NeverSight / learn-skills.dev

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. Web App: https://www.learn-skills.dev — Search, install, copy and share AI Agent Skills. English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Français | Deutsch | Español | Italiano | Русский | العربية Data Sources Current Providers • **skills.sh** - Community-curated skills leaderboard • All Time ( ) - Total installs ranking • Trending ( ) - Recent growth ranking • Hot ( ) - Daily installs ranking Planned Providers • **GitHub Trending** - Popular skill repos on GitHub • **Awesome Lists** - Curated awesome-* lists for AI agent skills Manual Skills Skills not tracked by any provider can be manually added via : Manual skills will be: • Fetched for their from GitHub (using standard skill folder detection) • Included in with • **Not** overwritten by the crawler (they persist across runs) • **Deduplicated**: If skills.sh later tracks a manual skill, it will use skills.sh data instead Note: should be at least 1 (minimum value). Output Files The crawler generates files in the directory: Complete skill data containing all three leaderboards: Website-friendly index for *all* skills (built from ): • Includes as a **path** to (when a cached exists under ) • Includes so your website can fetch and render the full markdown • **Deduplicated** by ( ). If the upstream data contains duplicates, the index keeps the entry with the highest . Simplified feed format (top 50 from each leaderboard). It also tries to enrich each item with a by fetching the corresponding GitHub (cached under ): Cached files fetched from GitHub, using common skill folder locations such as: • (most common) • • • • (common in plugin-based repos, e.g. Expo) When a is present, the crawler also generates: • (extracted from the SKILL.md frontmatter when available) By default, the crawler only fetches for skills included in the top lists (to keep the daily job fast). If you really want to sync *all* skills from , you can run: RSS 2.0 feed (XML). This is meant for RSS readers / subscriptions. • It is generated from the current crawl + the previous • It only publishes meaningful changes (new entries / rank jumps) to avoid spamming Usage Local Development Tip: if you want more complete GitHub coverage (including plugin-style paths like ), set to avoid GitHub API rate limits: GitHub Actions After pushing to GitHub, the crawler will: • Run automatically daily at UTC 0:00 • Support manual triggering (click "Run workflow" in Actions tab) • Run automatically on push to main branch Using in Your Website You can fetch data directly via GitHub Raw URL: Or use jsDelivr CDN (faster): RSS Subscription (Recommended) Subscribe to the RSS feed: Or via jsDelivr CDN: Example Code Notes • Data is updated daily • Please comply with each provider's terms of service • For personal learning and research purposes only Recommended Tools Outputs from learn-skills (notes, summaries, data) pair well with AI presentation tools to quickly turn them into shareable slides. **Level up your workflow** Turn your learn-skills results into professional slides? Try PopAi for one-click AI-generated presentations: https://www.popai.pro Contributing Want to add a new skill source? PRs are welcome! Check out the existing provider implementations in the codebase.