Skill Evaluation Iteration

Core Workflow

1. Define the target behavior and realistic user scenarios before editing the skill.
2. Run or simulate a baseline without the skill when practical.
3. Run or simulate the same scenario with the skill.
4. Compare outputs by decision quality, missing steps, correctness, concision, safety, tool use, validation, and deliverable usefulness.
5. Patch the skill to close observed gaps. Keep changes small and domain-specific.
6. Validate the skill folder with the official validator.
7. Repeat only when the new test reveals a material gap.

Output Contract

For skillset improvement work, return: