Running the systems that judge user-generated content: the policy hierarchy from principles to line-level rules, taxonomy design that makes reviewer disagreement measurable, classifiers and thresholds as precision-recall decisions, the moderation queue and reviewer calibration, graduated enforcement actions, appeals as error correction, boundaries with adjacent security surfaces, and the written moderation record. It explains how moderation systems are engineered; it never decides what content is allowed. Use when asking "content moderation", "trust and safety engineering", "moderation queue", "reviewer guidelines", "policy taxonomy", "appeal process", "graduated enforcement", "classifier threshold", "false positive rate". Not for endpoint rate limiting and bot defence (ac-security-engineer), not for detection engineering of security telemetry (ac-security-operations), not for LLM-judge evaluation of model outputs (ac-model-evaluation).
cp -r cryptoskill/skills/exchanges/anoscranel-ac-content-moderation .claude/skills/clawhub install anoscranel-ac-content-moderationCapabilities 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