Back to directory

explainmyrepo

A Claude Code skill that reads a GitHub repository and produces a live explainer web page with architecture and data-flow diagrams, along with a downloadable vector knowledge base, a search command-line tool and an MCP server built from the repository's own source.

Visit website (opens in a new tab)repo-explainer-six.vercel.app
explainmyrepo

explainmyrepo turns an opaque repository into an explainer aimed at getting a newcomer, human or AI, from never having seen the project to understanding why it was built, what problem it solves and how it works. It runs as a single Claude Code skill, rather than a template filler or a documentation scraper, and produces three outputs from one command.

The outputs are a live, art-directed web page with an architecture diagram and a data-flow diagram drawn from the actual source code, a GitHub repository the user is invited to as a collaborator so they can edit the result, and a downloadable knowledge pack containing a vector knowledge base of the repository, a search command-line tool and an MCP server, so that Claude Code or Cursor can answer questions about the repository from its real source instead of guessing.

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.