code-review-b7be66 — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited code-review-b7be66 (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.
!gh pr view $0 --json title,body,labels,changedFiles
!gh pr diff $0 --stat
!gh pr diff $0
基于以上 PR 信息，进行代码审查。
始终加载 rules/base.md。
根据代码内容，额外加载相关规则：
.tsx/.jsx 或 React 导入 → rules/react.md不要把所有问题都标 Critical——只有真正阻塞合并的才算。
根据技术栈，按需读取：
严格按以下格式输出：
#### 问题列表
| # | 文件 | 行号 | 严重度 | 问题描述 | 修复建议 |
|---|
#### 总结
审查完成后，对本次审查质量进行评分（诚实评估，不要虚高）：
以 JSON 格式输出 selfScore。
审查完成后：
/tmp/review-output.mdnpx tsx ${CLAUDE_SKILL_DIR}/scripts/collect-metrics.ts /tmp/review-output.md 生成统计npx tsx ${CLAUDE_SKILL_DIR}/scripts/append-log.ts data/review-metrics.jsonl '<统计JSON>' 记录日志~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.