Building the whole retrieval-augmented answering loop as one system: the query transform stage before retrieval, multi-hop decomposition when one query cannot reach the answer, chunk-level citation so every claim traces to a source, grounding verification that catches unsupported answers, refusal behaviour when the corpus is silent, and the written RAG record. It explains how the loop components compose; it never recommends an embedding model and never promises an accuracy. Use when asking "RAG", "retrieval augmented generation", "query rewriting", "multi-hop retrieval", "citation extraction", "grounding check", "hallucination guard", "answer verification", "corpus is silent", "RAG evaluation", "RAG pipeline design". Not for vector index and hybrid search mechanics (ac-retrieval-and-vector-systems), not for the grounding prompt itself (ac-prompt-engineer), not for model evaluation suites (ac-model-evaluation).
cp -r cryptoskill/skills/exchanges/anoscranel-ac-rag-systems .claude/skills/clawhub install anoscranel-ac-rag-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.
analysis_only Phase 1 single-mode classification — multi-mode breakdown deferred to Phase 2.
External services this skill needs in order to work. The skill's behavior depends on these services being up, honest, and unchanged. Today we only show services we recognize from a curated list of ~50 well-known hosts (exchanges, RPC providers, data APIs); a complete dependency list — including every package, library, and binary the skill installs or imports — is on the roadmap.
anthropic.comNo 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