Catalog / Categories

Evals

Measuring whether a skill, prompt or agent actually works — and stays working.

Entries

• Anthropic skills

  Anthropic's own skills for documents, design, art, internal comms and building new skills and MCP servers.

  Plugin by Anthropic Claude apps, Claude Code

  Official Reviewed — install with care Runs on your machine

• MCP Inspector

  The MCP project's official tool for connecting to an MCP server and exercising its tools, resources and prompts, in a web UI, a terminal UI or a scriptable CLI.

  Tool by Model Context Protocol Any agent

  Official Reviewed — install with care Runs on your machine

Curated by Andrew Borden-Chisholm. Notes on building with these tools are on the blog.