Back to directory

Lazy Skills

A terminal UI for managing agent skills across a project, showing every installed skill in one place, which coding agents such as Claude Code, OpenCode or Cursor can actually see it, and why a skill's visibility might be broken.

Lazy Skills

LazySkills groups project, global, universal and agent-specific skills in a single terminal interface, and lets a user switch between agents to check which skills are actually visible to Claude Code, OpenCode, Codex, Cursor, Gemini CLI and many others. It highlights broken installs, such as a missing SKILL.md file, invalid frontmatter, a broken symlink, a missing lock entry, or a ghost skill an agent references but that is not actually installed.

Before acting it previews a skill's metadata, its rendered content, and the exact command it is about to run, and its actions, opening, reinstalling, updating, removing, pruning orphaned locks, or running a bulk update or removal, all require confirmation for anything destructive. A separate discovery view scans local checkouts or GitHub sources, or searches the skills.sh directory, to find and install skills not yet present, to either project or global scope.

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.