gsd-eval-review

Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.

Invalid

This skill can't be scored yet

Validation errors are blocking scoring. Review and fix them to unlock Quality, Impact and Security scores. See what needs fixing →

Conduct a retroactive evaluation coverage audit of a completed AI phase. Checks whether the evaluation strategy from AI-SPEC.md was implemented. Produces EVAL-REVIEW.md with score, verdict, gaps, and remediation plan.

<execution_context> @~~/.claude/gsd-core/workflows/eval-review.md @~~/.claude/gsd-core/references/ai-evals.md </execution_context>

Phase: $ARGUMENTS — optional, defaults to last completed phase. Execute end-to-end. Preserve all workflow gates.

Repository: open-gsd/gsd-core
Path: skills/gsd-eval-review/SKILL.md
Commit: abf3cf7

Last updated: 1 day ago
First committed: about 2 months ago

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.