hygiene-gate
Inspect, reconcile, minimize, and route outputs from AI agents, tools, documents, or parallel workstreams before they reach a human or a closure gate. Use when outputs may be duplicated, contradictory, unsupported, stale, incomplete, privacy-sensitive, outside permission boundaries, or inconsistent with prior decisions; when material deltas must be quantified; or when agent-resolvable corrections should be returned without consuming human attention.
Pinned to revision cba1796fb7d7, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/hygiene-gate/SKILL.md
- skills/hygiene-gate/agents/openai.yaml
- skills/hygiene-gate/assets/icon.svg
- skills/hygiene-gate/references/verification-checks.md
Every link opens the file at its source, pinned to the revision this page describes.