Provides iterative, progressive-disclosure search across a filesystem-backed mnemonic memory store. Use it to run fast regex or semantic searches, filter by namespace/tag/type/date, and synthesize findings into a concise answer with source citations. It supports both simple frontmatter lookups and more advanced semantic queries when qmd tooling is available.
Use this skill when a user asks to "search memories", "find in memories", "grep mnemonic" or requests a deep synthesis of stored notes (e.g., "what do we know about X"). Start with title-only scans, escalate to frontmatter previews, and only read full files when necessary. It also supports iterative refinement for complex queries.
rg, find, and qmd for BM25/vector search if available.Best with agents that can run shell tools and read repo files (Claude Code, Copilot-like assistants, local CLI agents). Supports semantic tooling (qmd) when available for enhanced vector search.
This skill has not been reviewed by our automated audit pipeline yet.
