Back to directory

OSS-Skills

A set of fifteen executable AI-assistant skills that walk a developer through finding, evaluating and submitting their first open-source contribution, across several coding assistants.

OSS-Skills

OSS-Skills packages the practical steps of making an open-source contribution as executable skills rather than a written guide: the skills search GitHub issues, read a project's contribution documentation, trace relevant code paths, check whether a repository accepts outside contributions, and ask the developer questions at each step, rather than just being a list of resources to read. They cover assessing a project's health and governance before investing time, finding an unclaimed issue that a maintainer will actually review, and the rest of the contribution pipeline.

It installs in about thirty seconds for Claude Code, Cursor, Cline, Copilot, Windsurf, Zed, Gemini CLI or Kiro through a setup script, or as an AGENTS.md file readable by Codex, Aider, Goose and other tools that follow that convention, and can also be installed as a project-local configuration.

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.