Reusable Claude Code skills — handoff queue, daily wrap-up, design interrogation, looklook
SaferSkills independently audited agent-skills (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.
Aggregate score unchanged between these scans.
The primary manifest — the file an agent reads to learn what this artifact does.
执行日终下班工作流。这是一个完整的日终盘点流程。
reports/daily-YYYY-MM-DD.md,汇总今天做了什么git log --since="today" 或类似),确认每个项目的实际变更reports/wrap-up-YYYY-MM-DD.md,包含:docs: wrap-up YYYY-MM-DD — update project cards and report<!-- adapt: if using self-drive module, include these steps -->
在生成收工报告之后、git commit 之前执行。
读取以下数据:
self-drive/experiences/ 中今天的经验文件执行日级反思,写入 self-drive/reflections/daily/YYYY-MM-DD.md:
基于今天的执行数据和反思结果,更新 self-drive/dashboard.md:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.