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.

Showing 1,321–1,350 of 3,419

  1. Manage hybrid Famou experiments via famou-ctl: run local evaluators, submit config.yaml tasks, inspect status, manifests, leaderboards, logs

    • Open source
    • 34 GitHub stars
  2. Generate interactive visualization pages for feasible solutions produced by Famou evolutionary algorithms

    • Open source
    • 34 GitHub stars
  3. 医疗票据整理助手,用于自动分类、OCR识别和信息抽取。当用户需要处理医疗票据时使用,支持文件夹或压缩包输入,自动分类存放到不同文件夹,抽取病历信息(住院日期、医院名称),生成发票汇总CSV表格。

    • Open source
    • 34 GitHub stars
    • Files and documents
  4. Analyze image files, image URLs, PDF files, and PDF URLs when the task requires recognizing, understanding, extracting, answering questions

    • Open source
    • 34 GitHub stars
    • Files and documents
  5. Score a PhD applicant's profile and rank candidate advisors using a connection-first 4.0-scale scoring system

    • Open source
    • 33 GitHub stars
    • Health and science
  6. AgentBnB adapter for Claude Code — request peer agent capabilities, manage credits with budget tiers, and join the P2P sharing network direc

    • Open source
    • 33 GitHub stars
    • AI models and LLM tooling
  7. Accepts task_decomposition requests from peer Conductors and returns a SubTask[] DAG using the AgentBnB Rule Engine

    • Open source
    • 33 GitHub stars
  8. Submits structured ADR-018 feedback after every rental (as requester), and collects + acts on incoming feedback (as provider)

    • Open source
    • 33 GitHub stars
  9. Monitors idle_rate and automatically publishes or unpublishes skills on AgentBnB Hub

    • Open source
    • 33 GitHub stars
  10. Combined gap detection + Hub search + rental decision engine

    • Open source
    • 33 GitHub stars
  11. P2P agent capability network

    • Open source
    • 33 GitHub stars
    • Design and media
  12. P2P capability sharing for AI agents — discover, rent, and share skills on the AgentBnB network

    • Open source
    • 33 GitHub stars
  13. Capture what this conversation worked out into DocBrain, so the whole organization can find it later and DocBrain can tell when it stops bei

    • Open source
    • 33 GitHub stars
  14. Fleet Deck doctrine — how to behave as one Claude Code session among many on this machine

    • Open source
    • 32 GitHub stars
  15. Interactively fix any type checking issues in Python code

    • Open source
    • 32 GitHub stars
  16. Upgrade JavaScript dependencies using npm-check-updates, then run post-upgrade checks to ensure nothing is broken.

    • Open source
    • 32 GitHub stars
  17. Upgrade Python dependencies using uv, then run post-upgrade checks to ensure nothing is broken.

    • Open source
    • 32 GitHub stars
  18. OCPP protocol reference for EV charging infrastructure development

    • Open source
    • 32 GitHub stars
  19. Quick URL bookmark capture : paste a link, AI generates name and description, suggests category, saves to Bookmarks.md in awesome-list forma

    • Open source
    • 31 GitHub stars
  20. Capture a stream of raw thoughts : classify them and file to inbox with action items extracted

    • Open source
    • 31 GitHub stars
  21. Forges weak Claude Code prompts into structured, credit-saving, framework-aware prompts

    • Open source
    • 30 GitHub stars
    • AI models and LLM tooling
  22. Creates and manages isolated cloud sandboxes (secure code execution environments with dedicated runtimes) on the Daytona platform, through t

    • Open source
    • 23 GitHub stars
  23. Run builds, tests, and other tooling inside a reproducible, containerized dev environment via the `ilo` CLI instead of on the host

    • Open source
    • 21 GitHub stars
  24. LOG-UFPB's internal quick reference (group conventions, recommended tools, solvers and caveats from the group's own experience)

    • Open source
    • 21 GitHub stars
  25. Use when items need categorical triage (critical/warning/ok), not numeric scoring

    • Open source
    • 14 GitHub stars
  26. Use when you want to stress-test a proposal, plan, or findings before acting on them

    • Open source
    • 14 GitHub stars
  27. Use when a goal is too large to tackle as one unit

    • Open source
    • 14 GitHub stars
  28. Use when deciding between two approaches and you need a structured tradeoff comparison

    • Open source
    • 14 GitHub stars
  29. Use when you want to browse available skills or find the right pipeline for a workflow

    • Open source
    • 14 GitHub stars