Building the retrieval layer behind search and grounded answers: chunking strategy and what it costs, embedding models and their dimensional and multilingual trade-offs, vector index types and the recall-latency curve, hybrid search and reranking, freshness and the stale index problem, relevance evaluation with golden sets, and the written retrieval record. It explains how the index is built and measured; it never recommends a vendor and never promises an accuracy. Use when asking "vector database", "embedding model", "chunking strategy", "reranking", "hybrid search", "recall versus latency", "stale index", "retrieval quality", "why does search return nothing useful", "grounded answers". Not for prompt design and RAG prompting (ac-prompt-engineer), not for evaluating a dataset's provenance (ac-alternative-data), not for batch pipeline scheduling (ac-market-data-collection).
cp -r cryptoskill/skills/exchanges/anoscranel-ac-retrieval-and-vector-systems .claude/skills/clawhub install anoscranel-ac-retrieval-and-vector-systemsCapabilities below are detected automatically by an open-source scanner that reads the skill's text and scripts (see how this is computed). Not measured means the scanner couldn't make a confident call — it is NOT a green check, and you should treat it as a possible red flag until a human or a stronger scanner has measured it.
read_only Phase 1 single-mode classification — multi-mode breakdown deferred to Phase 2.
We did not find any well-known hosted services in this skill's text or scripts. This does NOT mean the skill is local-only — it might use services we don't yet recognize, or talk to them through code paths our scanner can't reach. A complete dependency list (every package, library, and binary, with integrity hashes) is on the roadmap; today we only show recognized hosts.
No one has audited this skill yet. That is different from “audited and clean” — it just means no professional reviewer (a security firm, the CryptoSkill team, or a verified independent researcher) has signed off on it. There are no audit reports to read. How reviewer levels work →
SKILL.md → SOURCE.md → TRUST.auto.yaml → Browse directory →
Auto-generated by cryptoskill/extract-capabilities/0.3.1 · hosted-service list version 2026-09-06 · how this is computed