Provides work planning and tracking capabilities for AI agents through both a CLI and an MCP server interface. Features hierarchical task management (epic, task, subtask), dependency tracking with automatic readiness detection, hash-based IDs to prevent merge conflicts, and multi-tenant support with API keys. Built on PostgreSQL with a Go architecture following proven patterns.
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.