review — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited review (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.
对 HEAD 和用户提供的固定点之间的 diff 做双轴 review:
两个轴都作为 parallel sub-agents 运行,避免彼此污染 context,然后此 skill 聚合它们的 findings。
Issue tracker 应该已经提供给你;如果缺少 docs/agents/issue-tracker.md,运行 /setup-matt-pocock-skills。
用户说的任何东西都是 fixed point:commit SHA、branch name、tag、main、HEAD~5 等。不要有自己的偏好,直接传递。如果他们没有指定,询问:"Review against what — a branch, a commit, or main?" 拿到 fixed point 前不要继续。
记录一次 diff command:git diff <fixed-point>...HEAD(three-dot,所以比较对象是 merge-base)。同时用 git log <fixed-point>..HEAD --oneline 记录 commits list。
按以下顺序寻找 originating spec:
#123、Closes #45、GitLab !67 等)— 通过 docs/agents/issue-tracker.md 中的 workflow 获取。docs/、specs/ 或 .scratch/ 下匹配 branch name 或 feature 的 PRD/spec file。Repo 中任何记录 code 应如何编写的东西。常见位置:
CLAUDE.md、AGENTS.mdCONTRIBUTING.mdCONTEXT.md、CONTEXT-MAP.md、per-context CONTEXT.md filesdocs/adr/(architectural decisions 也是 standards).editorconfig、eslint.config.*、biome.json、prettier.config.*、tsconfig.json(machine-enforced standards:记录它们,但不要重复检查 tooling 已检查的内容)docs/ 下任何 STYLE.md、STANDARDS.md、STYLEGUIDE.md 或类似文件收集 files list。Standards sub-agent 会读取它们。
发送一条包含两个 Agent tool calls 的 message。两者都使用 general-purpose subagent。
Standards sub-agent prompt — 包含:
Spec sub-agent prompt — 包含:
如果 spec 缺失,跳过 Spec sub-agent,并在 final report 中说明。
在 ## Standards 和 ## Spec headings 下展示两个 reports,逐字或轻微清理。不要 merge 或 rerank findings:两个轴刻意分开,方便用户独立查看。
以一句 summary 收尾:每个轴的 findings 总数,以及最严重的单个 issue(如有)。
一个 change 可能通过一个轴而失败在另一个轴:
分开报告能防止一个轴遮蔽另一个轴。
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.