Agent Skills
› davepoon/buildwithclaude
› gsd:eval-review
gsd:eval-review
GitHub对已完成的AI阶段进行回溯性评估覆盖率审计，检查评估策略是否落实，生成包含评分、结论、差距及补救计划的EVAL-REVIEW.md。
Trigger Scenarios
需要审查AI模型或功能的评估覆盖情况
完成AI开发阶段后需生成合规与质量审计报告
Install
npx skills add davepoon/buildwithclaude --skill gsd:eval-review -g -y
SKILL.md
Frontmatter
{
"name": "gsd:eval-review",
"description": "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",
"allowed-tools": [
"Read",
"Write",
"Bash",
"Glob",
"Grep",
"Task",
"AskUserQuestion"
],
"argument-hint": "[phase number]"
}
<execution_context> @${CLAUDE_PLUGIN_ROOT}/workflows/eval-review.md @${CLAUDE_PLUGIN_ROOT}/references/ai-evals.md </execution_context>
Version History
- 502fc01 Current 2026-07-05 15:12
