A behavioral MCP that strengthens AI coding assistants by requiring explicit LLM evaluations. Combines task-centric workflow enforcement (plan, code, test, completion) with explicit LLM-based validations and human-in-the-loop elicitation. Acts as a validation layer to ensure safer and higher-quality code by enforcing evidence-based research, reuse over reinvention, and human approval for ambiguous decisions.
Cognium trust score
68%
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 2026-09-19.
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.