Provides an auto-evolving intelligence layer for Claude Code development workflows. Scans GitHub repositories to extract coding patterns, compares against local project conventions, and proposes improvements to CLAUDE.md configuration files. Features 7 tools with SQLite-backed storage for persistent pattern learning across sessions.
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.