Oracle v2 is a knowledge management and memory layer that combines semantic vector search with full-text search to create an intelligent consultation system. The implementation indexes markdown documents (principles, learnings, retrospectives) from filesystem sources, stores them in SQLite with FTS5 and ChromaDB for hybrid search capabilities, and provides both MCP tools and a React dashboard for querying organizational knowledge. It features automatic project context detection via ghq paths, decision tracking with GitHub issue integration, and a forum system for collaborative knowledge building.
Cognium trust score
50%
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.
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.