Back to directory

Claude Code Templates

A CLI and web catalog of ready-to-use Claude Code configurations, including agents, slash commands, MCP integrations, settings, hooks and skills, plus tools for monitoring and diagnosing a Claude Code installation.

Claude Code Templates

The npx claude-code-templates command browses and installs from a catalog of more than 100 components, including domain-specialist agents such as a security auditor, a React performance optimizer or a database architect, custom slash commands, MCP integrations with services such as GitHub, PostgreSQL, Stripe and AWS, Claude Code settings, automation hooks, and reusable skills. A companion web interface lets a user browse and install the same catalog interactively.

Beyond the template catalog, the CLI adds an analytics mode that monitors Claude Code sessions in real time, a mobile-optimized conversation monitor for viewing responses remotely, optionally over a Cloudflare Tunnel, a health-check diagnostic for a Claude Code installation, and a plugin dashboard for viewing marketplaces and installed plugins. Its component catalog includes contributions from other projects, such as Anthropic's own official skills, a scientific-skills collection for biology, chemistry and medicine, and community workflow skills.

It is written in Python and licensed under the MIT license.

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.