product-architecture — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited product-architecture (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.
把任意产品(微信、豆包、某 AI App、ToB 工具…)逆向拆解成产品经理视角的架构图:
不是技术架构(微服务、数据库选型),不是信息架构(页面结构),是产品架构 — 业务模块怎么切、模块之间什么关系、数据怎么流转。
如果用户没说清是哪个产品,先问:
如果产品比较小众或用户没给信息,主动用 WebFetch / WebSearch 查官网了解。
必读 references/methodology.md,这是整个 SKILL 的方法论核心。里面有:
读完再继续。
读 references/examples.md,里面有四个范例:
挑一个跟目标产品最相似的形态重点看,理解"该层应该写什么粒度的东西"。
按顺序执行,不能跳步:
templates/architecture-template.html 生成可视化。四层骨架只是静态结构,箭头才是产品的"活"。至少标 1-2 条:
复制 templates/architecture-template.html → 当前工作目录,文件名 <产品名拼音或英文>-architecture.html。
按 assets/color-tokens.md 的配色规范替换内容。不要改变四层颜色对应(黄=触达/绿=场景/蓝=能力/紫=数据),保持视觉一致性。
完成后告诉用户:
| 现象 | 误判 | 纠正 |
|---|---|---|
| 把"语音输入"放在场景层 | ❌ | 它是能力层,场景层是"语音对话/语音笔记"这种业务 |
| 把"用户画像"放在数据层 | ⚠️ 看情况 | 如果是用于推荐的特征工程产物,属于数据层;如果是 ToB 客户管理界面,属于场景层 |
| 触达层只写"App" | ❌ 太粗 | 应该写"iOS App / Android App / Web 端 / 小程序 / 公众号" |
| 数据层写"MySQL" | ❌ 技术细节 | 写"用户对话记录 / 企业存量文档 / 互联网爬取" |
引导用户做两件事:
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.