Capture high-value items from a working session into Richard's Personal KMS at session-end. Triggers on session-end cues — "wrap up", "park this", "let's stop here", "call it", "we're done for today", "goodnight", "sign off", "checkpoint", "save state", "before I forget", or end-of-conversation signals where the user is clearly closing out. Distills the session into atomic claims and stores each via unified_store with metadata.subject. Always searches first to avoid duplicates and routes contradictions through kms_supersede instead of re-storing. Do NOT use for ad-hoc single-item storage (use kms-remember). Do NOT use for batch transcript ingestion (use kms-meeting-synthesis). Do NOT use to dump raw conversation history.
Synthesize a meeting transcript, Granola note, Slack huddle recap, call summary, or any conversation log into Richard's Personal KMS as one whole-meeting summary plus 2-5 typed atomic claims. Triggers on "summarize this meeting", "extract action items", "what did we decide", "draft the follow-up", "ingest this Granola", "process this huddle", "log this call", "store these meeting notes", or when handed a Granola URL / Slack canvas / transcript file in conversation. Each claim is self-contained with metadata.related_to pointing back to the whole-meeting entry. Routes through unified_store with subject facets and handles dedup_required responses with action=complement for related-meeting follow-ups. Do NOT use for live chat (use kms-auto-capture). Do NOT bypass the dedup gate.
Run a full-reconciliation pass over a topic cluster in Richard's Personal KMS — identify supersede candidates, contradictions, and near-duplicates, then PROPOSE corrective actions for human approval before dispatching. Triggers on "reconcile KMS", "clean up KMS", "audit KMS for <topic>", "weekly KMS pass", "find contradictions in KMS", "drain KMS dedup debt", "reconcile <topic>", or when Rich asks to clean up an over-written subject area. NEVER silently applies corrections — every supersede/update/delete needs explicit user approval first. Drains the "0 corrections vs N writes" debt the dedup gate spec was written to fix. Do NOT use for single-fact corrections (use kms_supersede directly). Do NOT use for hard-deleting flagged entries past the reversibility window — that is kms_reap, an admin tool.
Search Richard's Personal KMS BEFORE answering from training data or generating net-new content, whenever the user references prior conversation, prior decisions, prior facts, or prior preferences. Triggers on "remember when", "we discussed", "I previously said", "did I store", "what did I decide about", "didn't we talk about", "I think I told you", "have I mentioned", "we worked on this before", "what's my preference for", "did I already note", or any reference to prior context that would require KMS retrieval to answer accurately. Calls unified_search FIRST, surfaces results, THEN proceeds with whatever the user actually wanted (extending, retrieving, or storing). Behavioral inversion: search BEFORE generation, not as a fallback. Do NOT use as a replacement for kms-recall in pure-retrieval queries — kms-recall is search-and-present; kms-search-first is search-then-act.
Enforce corpus trust boundaries when reading, citing, or ingesting any document for Richard's projects — especially Lumen / libcp / L16 reverse-engineering work. Triggers when working with files under ~/Documents/Light_Work/ (UNTRUSTED), ~/Dev/L16_Lumen_ReverseEngineering/ (TRUSTED), or any L16/Lumen/libcp claim. Also triggers on "is this verified", "can I trust this source", "is this canonical", "should I cite this", "ingest this into KMS" when the source is Light_*, or any operation that risks promoting untrusted material into KMS as fact. Refuses to cite from UNTRUSTED paths without "[unverified]" prefix and refuses to ingest into KMS without explicit user override. Codifies the rule stored in KMS memory 54f04f28-259e-4c8c-9f6e-64cefc8fff52. Do NOT use as a generic file-trust skill — this is L16/Lumen-corpus-specific and applies Rich's verify-before-trust standard for that domain.
Saves structured session knowledge to the Personal KMS (unified_store) — decisions, technical facts, correction patterns, and working procedures discovered during the session. Use whenever the user says "save this session", "checkpoint the session", "save what we learned", "save to KMS before I stop", "dump session insights", "capture what we figured out", "session checkpoint", or "kms checkpoint". Also fires automatically when a PreCompact or periodic Stop hook blocks with a KMS CHECKPOINT reason. Do NOT use for searching or recalling from KMS (that is kms-recall). Do NOT use for storing a single ad-hoc fact — call unified_store directly. Do NOT use for silent per-turn extraction — kms-session-extract.py handles that automatically.