Provides a tiered, persistent memory architecture for Claude to automatically capture and retrieve user preferences, facts, and conversation history across sessions. It supports semantic search and seamless integration with the Claude desktop application using the Model Context Protocol.
Cognium trust score
47%
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 2026-09-28.
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.