evaluate-skill
Use when evaluating or comparing agent-skill behavior.
Pinned to revision 881fb153f36d, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/evaluate-skill/SKILL.md
- skills/evaluate-skill/references/evaluation-definition-schema.md
- skills/evaluate-skill/references/evaluation-design.md
- skills/evaluate-skill/references/execution-and-evidence.md
- skills/evaluate-skill/references/review-and-revision.md
- skills/evaluate-skill/scripts/lib/definitions.mjs
- skills/evaluate-skill/scripts/lib/evidence.mjs
- skills/evaluate-skill/scripts/lib/grade-comparison.mjs
- skills/evaluate-skill/scripts/lib/grade-interaction.mjs
- skills/evaluate-skill/scripts/lib/grade-support.mjs
- skills/evaluate-skill/scripts/lib/grade-workspace.mjs
- skills/evaluate-skill/scripts/lib/grade.mjs
- skills/evaluate-skill/scripts/lib/pi.mjs
- skills/evaluate-skill/scripts/lib/process.mjs
- skills/evaluate-skill/scripts/lib/rpc.mjs
- skills/evaluate-skill/scripts/lib/runner.mjs
- skills/evaluate-skill/scripts/lib/sandbox.mjs
- skills/evaluate-skill/scripts/lib/view.mjs
- skills/evaluate-skill/scripts/pi-guard.mjs
- skills/evaluate-skill/scripts/pi-observer.mjs
- skills/evaluate-skill/scripts/skill-eval.mjs
Every link opens the file at its source, pinned to the revision this page describes.