Back to directory

Learn Anything

Learn Anything generates skill and slash-command files for more than 30 AI coding tools, turning a coding assistant into an interactive tutor with Socratic explanations, TDD-style exercises, spaced repetition and a knowledge dashboard.

Learn Anything

Learn Anything generates skill and command files for AI coding tools such as Claude Code, Cursor, Codex and OpenCode, adding six slash commands to the assistant that guide a user through systematically learning a technical topic: generating a knowledge map to choose what to learn next, recursive explanations that go as deep as curiosity demands, TDD-style coding exercises with structured feedback, adaptive text quizzes graded and saved as reusable question decks, spaced-repetition review that resurfaces weak spots, and a heatmap visualization of mastery.

A web-based visual dashboard shows knowledge maps, session notes and exercises. Installation runs through an interactive or targeted CLI command that detects installed AI tools, and an optional integration with Context7 lets the assistant fetch official documentation to check its explanations against authoritative sources during a learning session.

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.