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. Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI

    • 28.8K GitHub stars
  2. Connects Figma design components to code components using Code Connect mapping tools

    • 28.8K GitHub stars
    • Design and media
  3. Build or update a professional-grade design system in Figma from a codebase

    • 28.8K GitHub stars
    • Design and media
  4. **MANDATORY prerequisite** — you MUST invoke this skill BEFORE every `use_figma` tool call

    • 28.8K GitHub stars
    • Design and media
  5. Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to au

    • 28.8K GitHub stars
  6. Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize fai

    • 28.8K GitHub stars
  7. Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images,

    • 28.8K GitHub stars
  8. Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bun

    • 28.8K GitHub stars
    • Analytics and data
  9. Migrate supported instruction files, skills, agents, and MCP config into Codex project and global files.

    • 28.8K GitHub stars
  10. Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date offic

    • 28.8K GitHub stars
    • AI models and LLM tooling
  11. Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, U

    • 28.8K GitHub stars
    • Browser automation
  12. Use when the user explicitly asks for a desktop or system screenshot (full screen, specific app or window, or a pixel region), or when tool-

    • 28.8K GitHub stars
  13. Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and expor

    • 28.8K GitHub stars
    • Security
  14. Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the Ope

    • 28.8K GitHub stars
    • Design and media
  15. Transcribe audio files to text with optional diarization and known-speaker hints

    • 28.8K GitHub stars
    • Design and media
  16. Deploy applications and websites to Vercel

    • 28.8K GitHub stars
    • Cloud and infrastructure
  17. Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mocku

    • 28.8K GitHub stars
    • Design and media
  18. Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date offic

    • 28.8K GitHub stars
    • AI models and LLM tooling
  19. Guide for creating effective skills

    • 28.8K GitHub stars
  20. Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path

    • 28.8K GitHub stars
  21. Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3

    • Open source
    • 11.4K GitHub stars
  22. Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by defau

    • Open source
    • 11.4K GitHub stars
  23. Pick the right serving container for a SageMaker model deployment and find its current image URI

    • Open source
    • 11.4K GitHub stars
    • Design and media
  24. Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  25. Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructur

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  26. Publish and manage research papers on Hugging Face Hub

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  27. Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling
  28. Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3,

    • Open source
    • 11.4K GitHub stars
    • AI models and LLM tooling