Back to directory

Agent Skill Index

A community-curated directory of real-world Agent Skills, text files that teach AI assistants such as Claude, Copilot, or Codex new abilities without retraining, compatible with many coding-agent hosts.

Agent Skill Index

Agent Skill Index is a community-curated list of Agent Skills, focusing on real-world skills created and used by actual engineering teams rather than bulk-generated collections. It is aimed at people who have not heard of agent skills before, and is compatible with Claude Code, Codex, Antigravity, Gemini CLI, Cursor, GitHub Copilot, Windsurf, and other hosts.

A skill is a folder containing a required SKILL.md file plus optional scripts, references, and assets, whose YAML frontmatter declares a name and description so an agent can find it before loading its full instructions. Using a skill means picking one from the directory, loading it into an agent through a per-host method such as a slash command, and then describing the task in plain English; no installation or coding is required.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.