Skill Eval Scaffolder
Create minimal, schema-valid eval manifests for repository skills.
Scope: Eval scaffolding only. Do not run live behavioral evals unless the maintainer explicitly approves.
Dispatch
| $ARGUMENTS | Action |
|---|---|
<name> |
Preview scaffold for skills/<name>/evals/evals.json |
<name> --apply |
Write scaffold when file is missing or user approved overwrite |
check <name> |
Validate an existing eval manifest |
| Empty | Show usage gallery and manifest schema summary |
Workflow
- Confirm
skills/<name>/SKILL.mdexists. - Run the bundled scaffold script:
uv run python skills/skill-eval-scaffolder/scripts/scaffold_evals.py <name>
- Add explicit, implicit, and negative-control cases before claiming adequate coverage.
- Validate with the bundled check script.
Manifest Shape
Each evals/evals.json uses:
skill_name— kebab-case directory nameevals— non-empty list of cases withid,prompt,expected_output, optionalfiles,assertions
Validation Contract
uv run python skills/skill-eval-scaffolder/scripts/check.py
Critical Rules
- Never overwrite an existing eval manifest without explicit user approval.
- Include at least one explicit-invocation case in new scaffolds.
- Run
validate_evals.pybefore declaring the scaffold complete. - Route live eval execution to skill-creator
evalmode or maintainer CI workflows. - Keep prompts grounded in the skill dispatch table and NOT-for boundaries.