Hermes Loop Engineering skills for self-improving AI delivery governance.
Gesondian/ai-collab-governance-skills
Skill Claude CodeCodex
Use when an AI is about to report accepted, passed, closed, ready, done, or equivalent handoff, receipt, or completion wording.
Gesondian/ai-collab-governance-skills
Skill Claude CodeCodex
Use when an AI delivery conclusion depends on partial, indirect, inherited, mock, local, visual, or otherwise limited evidence.
Gesondian/ai-collab-governance-skills
Skill Claude CodeCodex
Use when repeated delivery failures, disputed acceptance, weak evidence patterns, owner-routing mistakes, or trial observations may need reusable governance improvement.
Gesondian/ai-collab-governance-skills
Skill Claude CodeCodex
Use when an AI must decide whether a failure belongs to a feature owner, shared capability owner, data owner, environment owner, or verifier.
Gesondian/ai-collab-governance-skills
Skill Claude CodeCodex
Use when a user rejects, challenges, or reopens a previously accepted UAT, acceptance, or review result in an AI-assisted delivery workflow.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: