recall-knowledgelisted

# Recall Knowledge ## Goal Surface the most relevant knowledge entries for a query by meaning — bridging synonyms and cross-language wording (e.g. Japanese ↔ English identifiers) that literal keyword search misses. ## When to Use - Searching the knowledge base for prior art, decisions, pitfalls, or related context - The query may be worded differently than the entries (synonyms, JA query vs EN identifiers) - Before starting work on a topic, to pull related accumulated knowledge - NOT for per-prompt automatic injection — that stays ripgrep via the existing `userpromptsubmit_knowledge_search.sh` hook (instant, no model load) ## Structure First for Multi-Hop Questions When the recall looks like it needs several hops — tracing how a decision evolved, asking how two topics connect, or mapping everything around an entry — do NOT chain search → read → follow links → read again. Query the link graph first (`kb_graph.py neighborhood` / `path`), pick the endpoints from the structure (IDs + titles only), and Read just those entries. Details in the procedure file. ## Execution (run directly — do NOT delegate to a subagent) IMPORTANT: hybrid search executes code (`uv run` a Python script). Subagents run in a sandbox that blocks code execution, networking, and out-of-cwd writes, so this skill runs from the MAIN agent's Bash — do NOT spawn an Agent for the search itself. 1. Read the procedure file at: {plugin_root}/skills/recall-knowledge/procedure.md 2. Follow it: resolve paths, de