菜单
Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Generate tests for a completed phase based on UAT criteria and implementation
Generate an AI-SPEC.md design contract for phases that involve building AI systems.
Autonomous audit-to-fix pipeline — find issues, classify, fix, test, commit
Audit milestone completion against original intent before archiving
Cross-phase audit of all outstanding UAT and verification items
Run all remaining phases autonomously — discuss→plan→execute per phase
| name | gsd-eval-review |
| description | Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan. |
| argument-hint | [phase number] |
| allowed-tools | Read, Write, Bash, Glob, Grep, Agent, AskUserQuestion |
<execution_context> @.github/get-shit-done/workflows/eval-review.md @.github/get-shit-done/references/ai-evals.md </execution_context>
Phase: $ARGUMENTS — optional, defaults to last completed phase. Execute end-to-end. Preserve all workflow gates.