Gives AI coding assistants structured access to a codebase's semantic graph through 12 tools covering symbol listing, caller/callee analysis, dependency tracking, test coverage mapping, semantic diffs, and impact analysis. Built on Kai's semantic engine that understands function signatures, call graphs, and behavioral changes across five programming languages. The graph initializes lazily on first use and supports selective CI optimization based on behavioral impact rather than file diffs.
Cognium trust score
65%
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.