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. Searches and explores Burp Suite project files (.burp) from the command line

    • Open source
    • 8.2K GitHub stars
  2. Performs comprehensive C/C++ security review for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilitie

    • Open source
    • 8.2K GitHub stars
  3. Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user

    • Open source
    • 8.2K GitHub stars
  4. Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically

    • Open source
    • 8.2K GitHub stars
  5. Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings led

    • Open source
    • 8.2K GitHub stars
  6. Reviews the current branch's changes against its base branch as a pull request: correctness of new and modified code, test coverage for it,

    • Open source
    • 8.2K GitHub stars
  7. Reviews a code target by launching a panel of specialist auditor agents and merging their reports

    • Open source
    • 8.2K GitHub stars
  8. Detects timing side-channel vulnerabilities in cryptographic code

    • Open source
    • 8.2K GitHub stars
  9. Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data

    • Open source
    • 8.2K GitHub stars
  10. Produces CVSS v4.0 vector strings from plain-text vulnerability descriptions by systematically evaluating base metrics

    • Open source
    • 8.2K GitHub stars
  11. Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes

    • Open source
    • 8.2K GitHub stars
  12. Performs security-focused differential review of code changes

    • Open source
    • 8.2K GitHub stars
  13. Audits code for unit and decimal-scaling bugs and annotates it with dimensional comments recording the units of each value

    • Open source
    • 8.2K GitHub stars
  14. Analyzes DWARF debug information in compiled binaries

    • Open source
    • 8.2K GitHub stars
  15. Analyzes smart contract codebases to identify state-changing entry points for security auditing

    • Open source
    • 8.2K GitHub stars
    • Legal and government
  16. Scans Android APKs for Firebase security misconfigurations including open databases, storage buckets, authentication issues, and exposed clo

    • Open source
    • 8.2K GitHub stars
  17. Systematically verifies suspected security bugs to eliminate false positives, producing a TRUE POSITIVE or FALSE POSITIVE verdict with docum

    • Open source
    • 8.2K GitHub stars
    • Security
  18. Enforces authenticated gh CLI workflows over unauthenticated curl, WebFetch, and MCP fetch patterns

    • Open source
    • 8.2K GitHub stars
  19. Triages a repository's open GitHub issues and pull requests via the gh CLI

    • Open source
    • 8.2K GitHub stars
    • Developer tools
  20. Drafts copy-paste-ready /goal commands for goal mode in Claude Code and Codex

    • Open source
    • 8.2K GitHub stars
    • AI models and LLM tooling
  21. Draws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated

    • Open source
    • 8.2K GitHub stars
  22. Guides C++ code toward modern idioms (C++20/23/26)

    • Open source
    • 8.2K GitHub stars
  23. Configures Python projects with modern tooling (uv, ruff, ty)

    • Open source
    • 8.2K GitHub stars
  24. This skill should be used when the user asks to "open source this project", "prepare this repository for public release", "make this repo pu

    • Open source
    • 8.2K GitHub stars
  25. Use when a confirmed local bug needs an invariant-level fix, variant search, tests, and one local commit.

    • Open source
    • 8.2K GitHub stars
  26. Use when a known bug or falsifiable bug hypothesis in a local codebase needs a patch commit and reviewable proof report.

    • Open source
    • 8.2K GitHub stars
  27. Use when a local security patch commit needs independent scoped and three-arm proof.

    • Open source
    • 8.2K GitHub stars
  28. Use when a named runtime or compiler bug in a local repository needs independent reproduction.

    • Open source
    • 8.2K GitHub stars
  29. Use when a bug PoC package needs an independent rerun and judgment before patching.

    • Open source
    • 8.2K GitHub stars