6 skills · sorted by relevance
Run the retrieval recall gate with dead-gold triage and the binary A/B regression test. Required before release tags; use after any retrieval-adjacent merge.
The English summary is being prepared. Showing the original description.
Persistent vector memory for Claude Code via LanceDB. Use when: remembering across sessions, storing lessons, recalling past decisions, maintaining context continuity. Tools: memory_store, memory_recall, memory_update, memory_forget, memory_merge.
The English summary is being prepared. Showing the original description.
Combine vector search, which finds similar meanings, with keyword search for exact terms. Design retrieval for search engines and RAG systems that supply reference material to AI, using methods to merge and rerank results.
Recommend runtime and V2 scene management: run recommendation requests, manage recommend scenes and rules, and verify the deployed recommendation path.
The English summary is being prepared. Showing the original description.
Efficiently accumulate and retrieve competition knowledge in the knowledge/ stock layer (atomic pages + INDEX). Distill reusable insights from the daily-report flow and promote them, deduplicating and keeping things current. Use when an insight emerges, for weekly cleanup, or to recall past knowledge.
The English summary is being prepared. Showing the original description.
Audit whether an enforced-coordination MCP has actually shrunk its ~19 legacy etiquette verbs into the 5 enforced tools — work/act/ask/recall/status — each carrying one denial shape and one transcript event, migrated through a real retirement path (intake-metadata, alias, or doc-history — never a parallel runtime), with zero legacy-verb calls once a body reaches compliance mode C4+. Use when reviewing a broker-collapse migration plan, gating a body's move from advisory (C0-C3) to enforced (C4+) coordination, or verifying IT-018 Broker Collapse compliance. NOT for the inbound trigger→spawn boundary that decides whether an event may spawn an agent at all (use fleet-event-spawn-trust), the capability-token cryptographic mechanism behind a denial (use agentic-zero-trust-security), designing how a swarm of agents invokes and shards work (use swarm-invocation-designer), or auditing an individual PR's mergeability (use agent-pr-authoring).
The English summary is being prepared. Showing the original description.