Submit a resource

Navigation

Back to directory

Agent Skills

A now-deprecated catalog of Agent Skills, folders of instructions, scripts and resources, for use and distribution with OpenAI's Codex.

Visit website (opens in a new tab)github.com
Agent Skills

This repository catalogs Agent Skills for OpenAI's Codex: folders of instructions, scripts and resources that an AI agent can discover and use to perform a specific task, written once and reused across projects.

Skills placed in a system folder install automatically in the latest Codex; curated or experimental skills install by name or by GitHub directory URL through Codex's built-in skill-installer, and Codex needs a restart to pick up a newly installed skill. Each skill's license is stated separately inside its own directory.

The repository is deprecated; current Codex skill and plugin examples now live in a separate OpenAI Plugins repository.

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.

  • Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents

    github.com

    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.

Cookies

We use necessary cookies to run the site. Measurement and marketing are optional; neither is used today. Privacy policy