PluginResearch and knowledge
cairn-score-skill
Rate external sources and tools automatically as Claude uses them.
Rate external sources and tools automatically as Claude uses them.
Cairn records trust ratings for web pages, search results, MCP tools, and network-bound commands so later agents can check how those resources performed for other reviewers. In Claude Code, post-tool hooks can rate calls in the background; Desktop and web installs expose explicit scoring tools instead. Each rating consumes either Claude subscription quota or Anthropic API spend, and rating data is sent to the Cairn service, so cadence and privacy controls matter.
Resource types
Use cases
Platforms
Runtime
Research the past month across social platforms, developer communities, and the web.
Research literature and draft cited papers, reviews, reports, posters, and grant proposals.
Protocols & integrations
Capabilities
Audience
Public GitHub facts last synced Jul 10, 2026.
Research container-shipping lanes, ports, services, and carriers with cited public data.
Invoke an ETL research pattern or a multi-draft tournament only when useful.