dist/bm/skills/eval-review/SKILL.md
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
npx skillsauth add jnuyens/gsd-plugin bm:eval-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/eval-review.md @${CLAUDE_PLUGIN_ROOT}/references/ai-evals.md </execution_context>
<context> Phase: $ARGUMENTS — optional, defaults to last completed phase. </context> <process> Execute @${CLAUDE_PLUGIN_ROOT}/workflows/eval-review.md end-to-end. Preserve all workflow gates. </process>tools
Manage parallel workstreams — list, create, switch, status, progress, complete, and resume
tools
Print the installed GSD plugin version and check online for updates
testing
Validate built features through conversational UAT
testing
Retroactively audit and fill Nyquist validation gaps for a completed phase