Skip to content

Agent skills

Agent skills are folders of instructions and scripts that teach Claude Code, Codex, Cursor and other agents a task. Each one lists what it can run and how to install it.
  1. Makes the agent list the files it needs to see before answering a question

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  2. Lets your agent find and inspect Windows desktop API types from a local WinMD cache

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  3. Guides an agent through migrating UWP code to WinUI 3 and Windows App SDK APIs

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  4. Sets up a workshop folder structure for agent desks, locally or as a private GitHub repo

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  5. Guides an agent through Xquik X API integrations for tweet search, lookups and exports

    • Open source
    • 41.3K GitHub stars
    • Web search and scraping
  6. Finds C# API changes that break or drift from TypeScript and JavaScript clients

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  7. Guides an agent to add Azure Application Insights telemetry to a hosted web app

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  8. Audits an iOS app's code and metadata for likely App Store rejection risks

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  9. Guides the agent through diagnosing and fixing Arch Linux problems with pacman and systemd

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  10. Generates a project architecture blueprint document by analyzing a codebase's structure

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  11. Lets an agent create, list, update and delete Arize AI LLM provider integrations

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling
  12. Lets your agent manage Arize annotation configs, review queues and span labels

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling
  13. Turns raw work history into evidence-backed impact statements for reviews and updates

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  14. Turns an epic PRD into a high-level technical architecture specification

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  15. Guides the agent to write an epic-level product requirements document for a SaaS feature

    • Open source
    • 41.3K GitHub stars
    • Productivity
  16. Drafts detailed feature implementation plans with architecture, schema and API design

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  17. Guides the agent to write a feature PRD from a parent Epic, saved as Markdown

    • Open source
    • 41.3K GitHub stars
    • Productivity
  18. Turns feature docs into a GitHub project plan with linked epic, feature and story issues

    • Open source
    • 41.3K GitHub stars
    • Productivity
  19. Closes bug fixes with a structured receipt stating VERIFIED, PARTIAL or BLOCKED status

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  20. Turns a vague or intermittent bug report into a minimal, verified reproduction

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  21. Builds auditable evidence maps that separate supporting, contrary and missing sources

    • Open source
    • 41.3K GitHub stars
    • Knowledge and memory
  22. Checks SRT and WebVTT captions against Netflix, BBC and DCMP timing and line limits

    • Open source
    • 41.3K GitHub stars
    • Files and documents
  23. Guides the agent through diagnosing and fixing CentOS Linux issues with RHEL-compatible

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  24. Lets an agent drive and inspect a live Chrome browser through the DevTools MCP server

    • Open source
    • 41.3K GitHub stars
    • Browser automation
  25. Reference guidance on 42 cloud design patterns for designing distributed systems

    • Open source
    • 41.3K GitHub stars
    • Design and media
  26. Generates a prompt that makes the agent find representative code exemplars in a codebase

    • Open source
    • 41.3K GitHub stars
    • AI models and LLM tooling
  27. Lets an agent create persona-targeted CodeTour walkthroughs that link to real code lines

    • Open source
    • 41.3K GitHub stars
    • Developer tools
  28. Guides an agent to explore code through a Codebase Memory graph with verification steps

    • Open source
    • 41.3K GitHub stars
    • Knowledge and memory