Provides a gateway that exposes Agent Skills (agentskills.io) to any compatible agent through a standardized interface. Skills are declared in package.json and installed from GitHub repositories, local paths, or npm packages using a dedicated CLI. The server reads installed skills and serves them as tools, returning structured instructions and base paths that agents use to resolve scripts, references, and assets. Supports MCP server dependency declarations in skill frontmatter for automatic configuration across multiple agents including Claude Desktop, Cline, Cursor, and others.
Cognium trust score
30%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Last scanned 2026-09-02.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.