What problem does it solve?
This Skill refines PMO-platform skills by wrapping an Anthropic scaffolding skill with a PMO refinement layer, enhancing their capabilities and alignment with PMO requirements.
Core Features & Use Cases
- PMO Refinement: Injects PMO-platform fields into the produced SKILL.md, including delivery_approach, output-contract stub, dependency-graph node, evidence-quality protocol, failure-mode discipline, Principal Standard checklist, and reversibility declaration.
- Eval Harness: Runs the preserved eval harness from the skill-creator for variance analysis, description-trigger optimization, blind A/B comparison, and cross-skill false-positive detection.
- Existing Skill Refinement: Coordinates with pmo-skill-editor for modifying existing skills' SKILL.md structure and eval work.
- Use Case: When creating a new PMO skill or iterating on an existing skill's eval/description/trigger set, this Skill ensures it aligns with PMO standards and rigor.
Quick Start
Use the pmo-skill-refiner skill to refine an existing PMO skill's eval set, trigger description, or benchmark. For example, run "refine my-pmo-skill" to refine the skill's evaluation framework.