Runs a full deep-research study end to end. Reframes the question into falsifiable hypotheses, decomposes it into a query plan, triages sources on a trust ladder, pulls evidence through the keyless-first retrieval cascade, verifies every load-bearing claim against two or more independent source lineages with verbatim quotes archived, attacks the draft conclusions with an adversarial pass, stops on declared criteria with the reason stated, keeps a claim-to-source evidence ledger, and delivers the answer-first evidence report. Use for "research this question", "map the literature", "verify this claim properly", "write the evidence report", "investigate before we decide", or any question where a wrong answer costs more than the research. Not for one-hop factual lookups (what, who, when, price), single-page fetches, multi-day autonomous desk operations, or formal systematic-review protocol compliance.
cp -r cryptoskill/skills/exchanges/anoscranel-ac-deep-researcher .claude/skills/clawhub install anoscranel-ac-deep-researcherCapabilities 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