Scientific debugging and defect analysis: reproduce and minimise a failure, hypothesis-driven experiments, sanitizers and race detection, git bisect and delta debugging, fixing the defect class instead of the instance, and triaging a red build or broken pipeline back to green. Use when asking "why does this fail", "fix this bug", "it crashes when", "race condition", "find the root cause", "git bisect this", "why do we keep getting this bug", "CI is red", "the build is broken". Not for designing the test suite that catches the next defect, nor the pipeline's wiring once it is green; those sit outside this skill.
cp -r cryptoskill/skills/exchanges/anoscranel-ac-debugging .claude/skills/clawhub install anoscranel-ac-debuggingCapabilities 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