writing-shape — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited writing-shape (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.
<what-to-do>
用户已经传入(或将传入)一个 raw material 的 markdown file。把它视为 input pile:可以是整洁 fragments 列表、无结构 prose 墙、transcript,任何形式都可以。格式不重要。先从头到尾读取它,再做其他事。
然后运行一个 shaping session,产出一个单独的 article document。不要编辑 raw material file:对这个 skill 来说它是 read-only。
如果用户没有说明 article 保存位置,只问一次并记住 path。用户会在 session 期间编辑 article file;每次写入前都重新读取,确保保留他们的 edits。
</what-to-do>
<supporting-info>
这是反过来的 grilling session。在 ideation 中,问题是 “what are you actually noticing?” 这里是 “what is this article actually arguing, and in what order does the reader need to hear it?” 要 push back。拒绝放过 weak transitions。如果某段不配占位置,就 cut it。
持续使用这些 specific moves:
把 raw material 当成 quarry,而不是 script。抽取 fragment,重写到适配周围 paragraph,然后放置。一个 fragment 可以拆到多个 paragraphs 中、与另一个合并,或 paraphrase。Pile 的工作是被开采;article 的工作是读起来像一个 voice。
如果 pile 缺少 article 需要的东西,明确指出 gap:"We need an example here and the pile doesn't have one — give me one now or we cut this section."
选择如何 render 一个 beat 时,和用户大声权衡这些 tradeoffs,而不是默默决定:
> [!TIP]、> [!NOTE]),但只有当它们 inline 时确实会 derail main argument 才这样做。否则留在 inline。每个 block 达成一致后 append 到 article file。每次写入前从磁盘重新读取 file,因为用户可能在 turns 之间编辑。永远不要盲目 overwrite。如果用户想重写某段,原地编辑那一段,其余保持不动。
</supporting-info>
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.