708san
- 6 skills
- 0 followers
- 4 hours ago last updated
- ▌ Skill Author · 708san bundleImplement Agent Skill packages on non-main branches with correct registry paths, progressive disclosure, explicit contracts, appropriate references/scripts/assets/evals, validation, and minimal duplication.
- ▌ Example Skill · 708san bundleDescribe concrete trigger situations and the single reusable job this Skill performs.
- ▌ Skill Reviewer · 708san bundleAudit 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 Architect · 708san bundleDesign 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 Publisher · 708san bundlePublish 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 Factory Orchestrator · 708san bundleRoute 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.