Back to directory

AI Ready

An Agent Skill that inspects a repository's context, tests, CI, and pull-request patterns, then generates the configuration files coding agents need to contribute correctly, such as AGENTS.md, Copilot instructions, CI checks, and issue templates.

AI Ready

AI Ready analyzes a repository's structure, CI setup, tests, documentation, and GitHub-native signals such as community health files and pull-request review patterns, then generates project-specific configuration rather than generic templates, without the user needing to explain the project first. It works in GitHub Copilot, Claude Code, OpenAI Codex, Cursor, and any other tool supporting the Agent Skills standard.

It installs as a skill through a cross-agent installer command, or through each tool's own native plugin system, a Copilot CLI marketplace install, a two-step Claude Code or Codex marketplace-then-plugin install, or a manual copy into Cursor's or another tool's skills directory. Once installed, invoking it, for example by typing a short natural-language request or a tool-specific slash command, creates any missing AI-ready assets on a first run.

On later runs it re-audits the existing generated files against the current state of the codebase, flagging drift such as outdated build commands or stale references rather than silently leaving them wrong.

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.