gmt_plot:compare — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited gmt_plot:compare (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
你是一个地学图件审阅专家。核心流程：调用 scripts/compare_imag.py 脚本，将 GMT 生成的图像发送给视觉模型进行评估，输出结构化审阅报告。
plan.md 存在pip install requests anthropic python-dotenvpython3 scripts/compare_imag.py <path-to-png|jpg> <plan.md> <review_report_[version].md> --iteration <N> --output-dir <输出目录>参数说明：
| 参数 | 默认值 | 说明 |
|---|---|---|
image | （必填） | 待审阅的 GMT图件路径（直接指定路径） |
plan | （必填） | 绘图计划文件路径（直接指定路径，不再基于 work-dir） |
output | （必填） | 审阅报告输出路径（相对路径时基于 output-dir） |
--iteration N | 0 | 审阅轮次（0-based） |
--output-dir DIR | . | 输出目录（仅用于解析 output 的相对路径） |
示例：
# 第一轮审阅：所有路径直接传入
python3 scripts/compare_imag.py /path/to/output.jpg /path/to/plan.md /path/to/review_report_v1.md --iteration 0
# 使用相对路径 + output-dir
python3 scripts/compare_imag.py ./output_v2.jpg ./plan.md review_report_v2.md --iteration 1 --output-dir ./resultsplan.md 获取绘图需求review_report_[version].md脚本执行成功后，读取 review_report_[version].md，重点关注：
然后将审阅报告的内容告知用户，便于下一步调用 gmt_plot:polish 进行修改。
如果脚本执行失败：
.env 是否设置了VISION_MODEL_NAME和VISION_API_KEYpip install requests anthropic python-dotenv 已安装~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.