Agent Skills
› AjayIrkal23/agentic-mercy-10x
› gsd-eval-review
gsd-eval-review
GitHub对已完成的AI阶段进行回溯性评估覆盖审计，检查是否落实了AI-SPEC.md中的评估策略，并生成包含评分、结论、差距分析及补救计划的EVAL-REVIEW.md文件。
Trigger Scenarios
需要审计已完成AI阶段的评估覆盖率
生成评估审查报告及修复计划
Install
npx skills add AjayIrkal23/agentic-mercy-10x --skill gsd-eval-review -g -y
SKILL.md
Frontmatter
{
"name": "gsd-eval-review",
"description": "Audit an executed AI phase's evaluation coverage and produce an EVAL-REVIEW.md remediation plan.",
"allowed-tools": [
"Read",
"Write",
"Bash",
"Glob",
"Grep",
"Agent",
"AskUserQuestion"
],
"argument-hint": "[phase number]"
}
<execution_context> @$HOME/.claude/get-shit-done/workflows/eval-review.md @$HOME/.claude/get-shit-done/references/ai-evals.md </execution_context>
Version History
- 581d130 Current 2026-07-19 09:09
