Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pingfanfan/hello-dsh --skill write-docs-cngit clone --depth 1 https://github.com/pingfanfan/hello-dshWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pingfanfan/hello-dsh/write-docs-cn)<a href="https://agentmods.dev/skills/pingfanfan/hello-dsh/write-docs-cn"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/write-docs-cn/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pingfanfan/hello-dsh/write-docs-cn"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/write-docs-cn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.01133 |
| Opus 5.5 | $0.00018 | $0.00453 |
| Sonnet 5.5 | $0.00009 | $0.00227 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
write-docs-cn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
写项目文档
先分类,再动笔。 教程和参考是两种东西,混在一起两边都不好用。
| 类型 | 目的 | 组织方式 | 判断标准 |
|---|---|---|---|
| 教程 | 带人走通一次 | 按顺序,有明确终点 | 必须能从头读到尾做出结果 |
| 参考 | 查东西 | 按主题,可随机访问 | 必须能不读上文直接查到 |
一份文档同时想做两件事,结果通常是:想学的人被参考细节淹没,想查的人要读一堆铺垫。
判断依据不是标题也不是路径,是读者的使用方式:他是从头读,还是搜进来看一段?
放在哪
规则:每份文档讲清楚自己的主题,子主题只给一句话概括加链接。
具体说:
- 根 README 讲这个项目是什么、怎么跑起来、去哪找别的
- 每个模块的 README 讲这个模块自己的事
- 深入的细节放在它归属的那一层,不要上浮
判断某段内容该放哪:它是谁的细节? 是某个子模块的实现细节,就放那个子模块的文档里,上层只留一个链接。
这条能挡住 README 无限膨胀。
README 的结构
# 名字
一句话说清这是什么。
## 安装 / 快速开始
最短的可执行路径。
## 用法
最常见的两三个场景。
## 更多
链接到详细文档。
第一屏必须能让人判断「这是不是我要找的东西」,第二屏必须能让人跑起来。
不要在开头放架构介绍、设计理念、技术选型说明。那些放后面或者单独一页。
教程怎么写
- 有明确的终点:读完能做出什么,开头就说
- 每一步可验证:这一步做完应该看到什么,写出来
- 不跳步:作者觉得显然的地方,读者可能卡住
- 前置条件写在最前面:需要装什么、需要什么账号、大概花多久
- 给完整可执行的命令,不给片段
一个检验方法:找个没做过的人照着走一遍。 他卡住的地方就是你跳步的地方。
参考怎么写
- 按可查找性组织,不按叙事顺序
- 每一项独立完整,不依赖上文
- 明确写出默认值、取值范围、错误情况
- 相关项之间给链接
注释和文档的分工
代码能表达的,不要写进文档;文档能表达的,不要写进注释。
注释应该写:
- 非显然的契约(前置条件、后置条件、不变量)
- 为什么这样做(尤其是「为什么不用那个更明显的办法」)
- 外部约束(这个魔数来自某个协议规范)
注释不应该写:
- 复述代码在做什么
- 变更历史(git 里有)
- 实现过程的心路历程
别写「思维链」
一类很常见的坏文字:视角站在「写这段代码的那次会话」,而不是站在「项目现在的状态」。
表现:
- 「以前是……后来改成了……」
- 「这里之前有个 bug,所以……」
- 「见方案 B」(读者不知道方案 B 是什么)
- 「评审时讨论过……」
判断标准:一个刚接触这个项目的人,能不能理解每一个引用、验证每一条说法? 不能就是这类问题。
改法不是直接删。如果那段话里有事实,先把事实改写成「现在是什么样」,再删掉叙述部分。
保持同步
改了行为就在同一个提交里改文档。 分开做的结果是文档永远落后。
文档里的命令和输出应该定期验证,最好能自动化。过期的文档比没有文档更糟,因为它会让人浪费时间在已经不存在的路径上。
不要做的事
- 不要写「本文档将介绍」这类元叙述
- 不要在 README 开头放大段背景
- 不要把教程和参考混在一页
- 不要写只有作者能看懂的缩写
- 不要留 TODO 而不写清什么条件下会补
- 不要复制粘贴同一段说明到多处(选一个家,其余给链接)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 116 lines · 46 tokens per session scan A f3bfcade9908
write-docs-cn is a skill published in the GitHub repository pingfanfan/hello-dsh (101 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,133 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
dsh-office-artifacts
Create, repair, transform, or verify XLSX, DOCX, PPTX, and PDF deliverables with format-aware tools and reopen or render checks.
office-pptx
Create, read, edit, and validate PowerPoint presentations (.pptx).
office-xlsx
Read, create, edit, and validate Excel workbooks, data, and formulas (.xlsx).
office-render
Render requested document images or inspect visual layout with LibreOffice Kit.
office-docx
Create, read, edit, and validate Word documents (.docx).