708san/agent-skill-factory
Skill Claude CodeCodex
Design Registry-first Skill/Flow/Suite changes after mutation authorization and visibility-aware Registry gap analysis; decide reuse, extension, creation, model/tool placement, boundaries, contracts, dependent impact, representability, handoffs, and Flow-first architecture.
708san/agent-skill-factory
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.
708san/agent-skill-factory
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, runtime discovery/composition, and progressive disclosure.
708san/agent-skill-factory
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.
708san/agent-skill-factory
Skill Claude CodeCodex
Audit Agent Skill packages and Factory changes for correctness, Registry-first build semantics, mutation authorization, visibility-aware search, Flow representability, placement, boundaries, contracts, eval coverage, security, validation, and regression risk.
708san/agent-skill-factory
Skill Claude CodeCodex
Describe concrete trigger situations and the single reusable job this Skill performs.