Skill Claude CodeCodex
Design Registry-first Skill/Flow/Suite changes after mutation authorization, visibility-aware Registry Search, Candidate Skill Inspection, and Reuse Boundary Check; decide reuse, extension, creation, boundaries, contracts, dependent impact, representability, handoffs, and Flow-first architecture.
Skill Claude CodeCodex
Implement Agent Skill packages on non-main branches with correct registry paths, progressive disclosure, explicit contracts, appropriate references/scripts/assets/evals, validation, and minimal duplication.
Skill Claude CodeCodex
Route Agent Skill Factory requests across read-only behavior and explicit Registry mutation modes; enforce mutation authorization, visibility-aware Registry-first planning, Candidate Skill Inspection, Reuse Boundary Check, runtime discovery/composition, and progressive disclosure.
Skill Claude CodeCodex
Publish a sanitized public-safe variant of a private Agent Skill while preserving package structure, canonical registry paths, progressive disclosure, validation, and the private/public security boundary.
Skill Claude CodeCodex
Audit Agent Skill packages and Factory changes for correctness, Registry-first build semantics, mutation authorization, visibility-aware search, Candidate Skill Inspection, Reuse Boundary Check, Flow representability, placement, boundaries, contracts, eval coverage, security, validation, and regression risk.
Skill Claude CodeCodex
Describe concrete trigger situations and the single reusable job this Skill performs.
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: