task-evaluation
Evaluate completed objectives using actual artifacts, constraints, verification evidence, time and available usage. Use for a bounded acceptance review, investigating regressions or comparing execution approaches; plan repeated trials without launching paid model calls automatically.
Pinned to revision 8d4b32271e69, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/task-evaluation/SKILL.md
- skills/task-evaluation/references/protocol.json
- skills/task-evaluation/references/run-template.json
- skills/task-evaluation/references/scenarios.json
Every link opens the file at its source, pinned to the revision this page describes.