Generaldavepoon

gsd:eval-review

Retroactively audit an executed AI phase's evaluation coverage — scores each eval dimension as COVERED/PARTIAL/MISSING and produces an actionable EVAL-REVIEW.md with remediation plan

Stars: 2,987
Source: davepoon/buildwithclaude
Updated: 2026-05-26
Slug: davepoon--buildwithclaude--eval-review

View on GitHub Raw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/davepoon/buildwithclaude/HEAD/plugins/gsd/skills/eval-review/SKILL.md -o .claude/skills/eval-review.md

Drops the SKILL.md into .claude/skills/eval-review.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

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. @${CLAUDE_PLUGIN_ROOT}/workflows/eval-review.md @${CLAUDE_PLUGIN_ROOT}/references/ai-evals.md Phase: $ARGUMENTS — optional, defaults to last completed phase. Execute @${CLAUDE_PLUGIN_ROOT}/workflows/eval-review.md end-to-end. Preserve all workflow gates.