Indexes a project codebase into a local SQLite database and assembles precisely targeted context using a 4-layer system: project tree overview, current files, search results with dependency chain traversal, and frequently accessed files. Supports BM25 keyword search with optional semantic vector search via Ollama embeddings, and follows import chains across JavaScript, TypeScript, Python, Rust, Go, and Java. Achieves significant token reduction while maintaining accuracy through intelligent file selection.
Cognium trust score
61%
Tier
Scanned
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.