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-tech-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-tech-cn)<a href="https://agentmods.dev/skills/pingfanfan/hello-dsh/write-tech-cn"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/write-tech-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-tech-cn"><img src="https://agentmods.dev/badge/skills/pingfanfan/hello-dsh/write-tech-cn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 84 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00055 | $0.01114 |
| Opus 5.5 | $0.00022 | $0.00446 |
| Sonnet 5.5 | $0.00011 | $0.00223 |
| Haiku 4.5 | $0.00006 | $0.00111 |
Grade A, and why
write-tech-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
中文技术写作
读者是来解决问题的，不是来欣赏文笔的。 第一段就要给出他能用的东西。
先给结论
技术文章不是悬疑小说。把结论、可执行的动作放在最前面，论证放后面。
✗ 随着 AI 技术的快速发展，越来越多的开发者开始关注 agent 框架。
本文将介绍……
✓ DSH 的技能是纯 Markdown，丢进 ~/.dsh/skills/ 就生效，不用重启。
第一段写不出具体信息，说明你还没想清楚要说什么。
禁用的开头
- 「随着……的发展」
- 「众所周知」
- 「在当今……时代」
- 「本文将介绍」
- 「首先我们来看」
这些句子的共同点是：删掉之后文章更好。
AI 味从哪来
几个典型特征，写完自查：
排比轰炸：「它不仅……而且……更重要的是……」。一段里出现两次以上的排比就该改。
万能形容词：强大、优雅、健壮、全面、深入、丰富。这些词不携带信息。「强大的错误处理」不如「错误会带上失败的具体字段名」。
空转的总结句：「总而言之，这是一个值得关注的方向」。删掉，或者换成具体判断。
过度对仗：每段都是「是什么 + 为什么 + 怎么做」的三段式。真实的技术写作节奏是不均匀的，重要的地方多说，次要的地方一句带过。
假设读者的感受：「相信你一定很好奇」「是不是很神奇」。不要替读者表达情绪。
术语处理
中文技术写作里英文术语是正常的，不要硬翻。
- 通行的英文术语直接用：commit、merge、fiber、context、plugin
- 有稳定中文译法的用中文：进程、线程、缓存、依赖
- 第一次出现时给注解：用括号或「就是」，
Coeffect（组件对环境的依赖声明） - 不要混用译名：一篇里 fiber 就一直叫 fiber，不要一会儿叫「纤程」
判断标准：你在工位上跟同事口头说这个词时用中文还是英文？ 口头怎么说就怎么写。
句子
中文技术写作的问题通常是「翻译腔」：
✗ 这个函数被设计用来处理那些可能会失败的情况
✓ 这个函数处理失败情况
✗ 我们可以通过使用这个方法来实现对配置的加载
✓ 用这个方法加载配置
✗ 在大多数情况下，这样的做法是被推荐的
✓ 一般这样写
规律：删掉「被」「通过」「进行」「的话」「一个」，句子通常更准。
代码和命令
- 给完整可执行的命令，不要片段
- 说明预期输出，让读者知道成功长什么样
- 标注环境：什么系统、什么版本、什么前置条件
- 代码块前一句话说清它干什么，不要让读者自己猜
# 检查配置有没有静默失效的问题
npx dsh-doctor
# 干净时输出「未发现问题」，有问题时退出码为 1
诚实
- 不确定就说不确定，不要用模糊措辞掩盖
- 没测过就不要写「实测」
- 有局限就写出来，这增加可信度而不是减少
- 数字必须准确，记不清就不写具体数
读者能分辨出你是真跑过还是在复述文档。 真跑过的文章里会有具体的报错、具体的版本号、具体的坑。
排版
- 段落短，两到四句
- 少用加粗，全篇加粗等于没有加粗
- 列表用来并列，不要用列表写连贯的论述
- 表格用来对比，不要用表格装普通句子
不要做的事
- 不要写「本文将介绍」这类元叙述
- 不要在结尾写「以上就是全部内容，希望对你有帮助」
- 不要用感叹号强调
- 不要为了凑长度加背景介绍
- 不要把免责声明写在开头（要写就放最后）
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 · 112 lines · 55 tokens per session scan A ae155dd1f5bf
write-tech-cn is a skill published in the GitHub repository pingfanfan/hello-dsh (101 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,114 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).