Skip to content

Agent skills for Claude Code

3,385 agent skills for Claude Code, out of 3,419 agent skills listed. Popular ones include Skill creator, Rea analysis optimization and Rea changelog update. Claude Code reads the SKILL.md folder format, so each skill here can be copied into ~/.claude/skills. Each one lists what it can run and the steps to install it.

Showing 2,011–2,040 of 3,385

  1. Automatically discover networking and connectivity skills when working with TCP, UDP, DNS, mTLS, NAT traversal, SSH, Mosh, Tailscale, or net

    • Open source
    • 191 GitHub stars
  2. Automatically discover product management skills when working with product management, roadmap, user stories, prioritization, metrics, or pr

    • Open source
    • 191 GitHub stars
  3. Automatically discover research methodology skills when working with research methodology, literature review, systematic review, evidence sy

    • Open source
    • 191 GitHub stars
  4. Automatically discover security skills when working with authentication, authorization, input validation, security headers, vulnerability as

    • Open source
    • 191 GitHub stars
    • Security
  5. Automatically discover eBPF, compiler, programming language theory, information retrieval, and formal verification skills when working with

    • Open source
    • 191 GitHub stars
  6. Automatically discover WebAssembly skills when working with WebAssembly, WASM, WASI, wasm-bindgen, Rust to WASM, wasm-pack, or browser runti

    • Open source
    • 191 GitHub stars
  7. Automatically discover Zig programming skills when working with Zig, comptime, allocators, build.zig, safety, C interop, memory management,

    • Open source
    • 191 GitHub stars
  8. Create world-class, accessible, responsive interfaces with sophisticated interactive elements including chat, terminals, code display, and s

    • Open source
    • 191 GitHub stars
    • Design and media
  9. Refactor codebases using Design by Typed Holes methodology - iterative, test-driven refactoring with formal hole resolution, constraint prop

    • Open source
    • 191 GitHub stars
  10. Use when the user wants to evolve an ML model/program through population-based search rather than a single sequential refine loop — a genera

    • Open source
    • 183 GitHub stars
  11. Use when the user has a known, already-observed anomaly in their data — a metric spike or drop, an outlier, an unexpected number — and wants

    • Open source
    • 183 GitHub stars
  12. Use when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR

    • Open source
    • 183 GitHub stars
    • Developer tools
  13. Use when the user has a results draft or a set of data-backed claims and wants each one adversarially verified against the underlying datase

    • Open source
    • 183 GitHub stars
  14. Use when the user wants an iterative, self-checking exploratory analysis of a dataset — surfacing findings that are each verified by re-runn

    • Open source
    • 183 GitHub stars
    • Analytics and data
  15. Use when the user wants two approaches raced head-to-head on a single shared metric — e.g

    • Open source
    • 183 GitHub stars
  16. Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach

    • Open source
    • 183 GitHub stars
  17. Use when the user wants to generate and literature-vet a pool of novel, testable research hypotheses for a question or domain

    • Open source
    • 183 GitHub stars
  18. Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes

    • Open source
    • 183 GitHub stars
  19. Use when a loop needs scholarly literature — paper discovery, novelty checks, full-text snippet search, citation-graph traversal, single-pap

    • Open source
    • 183 GitHub stars
  20. Use when the user wants a structured, saturating literature survey on a question — not a one-shot summary, but an evidence/contradiction mat

    • Open source
    • 183 GitHub stars
  21. Use when the user wants an autonomous ML research loop that does more than blindly try changes

    • Open source
    • 183 GitHub stars
  22. Use when the user wants to iteratively improve an artifact under a hard correctness bound while minimizing a measured cost — refactoring a c

    • Open source
    • 183 GitHub stars
  23. Use when the user has a coding or engineering prompt and wants it refined into a detailed, executable plan before any code is written — the

    • Open source
    • 183 GitHub stars
  24. Use when the user is planning a two-arm comparison (an A/B test, a simple RCT, a behavioral study, or a two-model/two-config evaluation) and

    • Open source
    • 183 GitHub stars
  25. Use when the user has a prompt that feeds a system they can already score, and wants that prompt automatically improved to raise the score a

    • Open source
    • 183 GitHub stars
    • AI models and LLM tooling
  26. Use when the user wants to automatically harden a guardrail, classifier, content filter, prompt, or API they own by running attack and defen

    • Open source
    • 183 GitHub stars
  27. Use when the user wants to adversarially stress-test a guardrail, classifier, prompt, or API they own or are authorized to test, to surface

    • Open source
    • 183 GitHub stars
  28. Use when the user has a research proposal (problem + proposed methodology + planned experiments) and wants it iteratively strengthened until

    • Open source
    • 183 GitHub stars
  29. Use when the user has a vague topic or area of interest and wants it sharpened into a few strong, novel, feasible research questions

    • Open source
    • 183 GitHub stars
  30. Use when the user has scientific data (or a prompt alluding to scientific data) and wants a publication-quality figure made from it

    • Open source
    • 183 GitHub stars
    • Health and science