feature-doc-splitter-cn — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited feature-doc-splitter-cn (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
A bulleted imperative like {match} tells the agent to never reveal, disclose, or mention something to the user. Used adversarially it can instruct the agent to hide its tool calls or lie about what it did — stripping the transparency a user relies on to trust the agent.
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.
使用这个技能,将早期功能需求初稿整理成一组三份可落地文档:总览文档、前端实现文档和后端实现文档。
输出必须结合真实代码结构,明确拆分前端和后端职责,定义共享契约,补充必要 Mermaid 图,并把不确定点显式写入假设或待确认事项。涉及新增 UI 表面时,还要判断是否需要预留可选 Pencil 设计稿占位。
当用户提出以下需求时使用本技能:
以下场景不要使用本技能:
按照以下流程执行,并始终按责任归属拆分三份输出文档。
创建或更新三份文档:
总览文档必须用项目相对路径引用前端和后端实现文档,并且必须包含 Mermaid 代码块。
AGENTS.md。rg 和定向文件阅读查找现有页面、路由、组件、Hook、生成 API 客户端、模型、Schema、服务、测试、通知代码、统计或排行逻辑。.pen 文件,并在文档中简要记录该决策。.pen 文件。.pen 文件。.pen 文件。docs/features/<feature>/pencil/<surface>.pen。.pen JSON 文件,空占位可以只包含:{"version":"2.13","children":[]}.pen 占位,校验 JSON 格式。git diff --check。当 Mermaid 节点文案包含标点时,使用引号包裹节点标签。
最少图示:
简要说明创建或更新的文档,列出创建或明确删除的 Pencil 占位,并报告验证结果。
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.