Declauding
oaustegard/claude-skills
Rewrites model-sounding prose into plain technical writing and checks that every claim survives, for PR text, docs, commit messages and similar drafts.
Sets writing rules for Chinese technical docs: short plain sentences, consistent typography and a checklist for removing AI-sounding filler.
SKILL.md written in Chinese; this summary is our English description.
Install Chinese Technical Writing
$ npx skills add leter/zh-tech-writing --skill zh-tech-writing -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install leter/zh-tech-writing zh-tech-writing --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/leter/zh-tech-writing.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/zh-tech-writing .claude/skills/zh-tech-writing && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "zh-tech-writing" agent skill from https://github.com/leter/zh-tech-writing/tree/main/skills/zh-tech-writing into .claude/skills/zh-tech-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zh-tech-writing", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/leter/zh-tech-writing/tree/main/skills/zh-tech-writingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add leter/zh-tech-writing --skill zh-tech-writing -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install leter/zh-tech-writing zh-tech-writing --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leter/zh-tech-writing.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/zh-tech-writing .agents/skills/zh-tech-writing && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "zh-tech-writing" agent skill from https://github.com/leter/zh-tech-writing/tree/main/skills/zh-tech-writing into .agents/skills/zh-tech-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zh-tech-writing", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add leter/zh-tech-writing --skill zh-tech-writing -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install leter/zh-tech-writing zh-tech-writing --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leter/zh-tech-writing.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/zh-tech-writing .cursor/skills/zh-tech-writing && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "zh-tech-writing" agent skill from https://github.com/leter/zh-tech-writing/tree/main/skills/zh-tech-writing into .cursor/skills/zh-tech-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zh-tech-writing", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/leter/zh-tech-writing.git --path skills/zh-tech-writing--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add leter/zh-tech-writing --skill zh-tech-writing -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install leter/zh-tech-writing zh-tech-writing --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leter/zh-tech-writing.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/zh-tech-writing .gemini/skills/zh-tech-writing && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "zh-tech-writing" agent skill from https://github.com/leter/zh-tech-writing/tree/main/skills/zh-tech-writing into .gemini/skills/zh-tech-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zh-tech-writing", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install leter/zh-tech-writing zh-tech-writingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add leter/zh-tech-writing --skill zh-tech-writing -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/leter/zh-tech-writing.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/zh-tech-writing .github/skills/zh-tech-writing && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "zh-tech-writing" agent skill from https://github.com/leter/zh-tech-writing/tree/main/skills/zh-tech-writing into .github/skills/zh-tech-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zh-tech-writing", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add leter/zh-tech-writing --skill zh-tech-writing -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install leter/zh-tech-writing zh-tech-writing --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leter/zh-tech-writing.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/zh-tech-writing .opencode/skills/zh-tech-writing && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "zh-tech-writing" agent skill from https://github.com/leter/zh-tech-writing/tree/main/skills/zh-tech-writing into .opencode/skills/zh-tech-writing/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "zh-tech-writing", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
zh-tech-writing- GitHub stars
- 338
- Token cost
- ~656 tokens
- SKILL.md length
- 159 words
- Files
- 3 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Sets writing rules for Chinese technical docs: short plain sentences, consistent typography and a checklist for removing AI-sounding filler.
- Works in 5 steps: 先想清楚读者是谁，读完要能做成什么事。一句话说不清，先问用户。 → 按下面的“句子”“语气”“段落与结构”“排版”写。 → 自检：拿“AI 腔清单”逐条对照全文，命中的全部改掉。 → …
- Writing a README, design document, API description or tutorial in Chinese
- SKILL.md covers 流程, 句子, 语气 and 段落与结构, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill sets a style standard for Chinese technical documents such as READMEs, design documents, API descriptions and tutorials, aiming for text that reads as if an experienced engineer wrote it: plain, specific and in short sentences. For a new document the agent first pins down the reader and what they should be able to do afterward, drafts against the rules, then checks the draft against an AI-tone list. For an existing one it reads the whole text first, and lists problems as original, revision and reason when you only want feedback. The skill text is in Chinese.
Rules cover sentence length (clauses of about 20 characters, splitting past 30, whole sentences under 100), active voice, affirmative statements, a conversational but not slangy tone, facts in place of adjectives, paragraph and heading structure, and typography such as spaces between Chinese and Latin text, full-width punctuation and proper ellipses. The AI-tone list flags filler openings and closings, contrast and escalation patterns, forced triples, promotional adjectives, jargon, em dashes and emoji. The agent runs autocorrect --fix for spacing and punctuation when it is installed, with references for typography and manual structure.
When your agent uses it
- Writing a README, design document, API description or tutorial in Chinese
- Editing existing Chinese documentation for clarity and tone
- Reviewing a Chinese document and listing problems as original, revision and reason
- Checking spacing and punctuation between Chinese and English text
Example prompts
- “Write a Chinese README for this CLI tool in plain, short sentences.”
- “Review docs/design.md and list the problems as original sentence, revision and reason, without editing the file.”
- “把这篇教程里的 AI 腔都改掉，并修正中英文之间的空格。”
Requirements
- The autocorrect CLI for spacing and punctuation fixes (optional)
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- 先想清楚读者是谁，读完要能做成什么事。一句话说不清，先问用户。
- 按下面的“句子”“语气”“段落与结构”“排版”写。
- 自检：拿“AI 腔清单”逐条对照全文，命中的全部改掉。
- 跑 autocorrect --fix <文件>，修空格和标点。命令不存在就跳过，改为按“排版”手动检查。
- 手动检查 autocorrect 管不到的：引号、省略号、破折号。
What it can do on your machine
Read from SKILL.md and the folder at commit ffda935. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Chinese Technical Writing loads about 656 tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 17 tokens; SKILL.md has 159 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from leter/zh-tech-writing at commit ffda935, republished under its MIT licence (© leter). 159 words, ~656 tokens.
Download SKILL.mdSave it as
.claude/skills/zh-tech-writing/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- zh-tech-writing
- description
- 中文技术文档写作规范。写或修改中文技术文档、开发文档（README、设计文档、接口说明、教程）时使用。
中文技术文档写作
目标：写出像资深工程师写的中文技术文档。平实、具体、短句。
流程
写新文档：
- 先想清楚读者是谁，读完要能做成什么事。一句话说不清，先问用户。
- 按下面的“句子”“语气”“段落与结构”“排版”写。
- 自检：拿“AI 腔清单”逐条对照全文，命中的全部改掉。
- 跑
autocorrect --fix <文件>，修空格和标点。命令不存在就跳过，改为按“排版”手动检查。 - 手动检查 autocorrect 管不到的：引号、省略号、破折号。
修改已有文档：
- 通读全文，再动手。
- 用户只要意见：按“原句 → 改后 → 原因”列出问题，不改文件。
- 否则直接改，然后做上面的第 3～5 步。最后用两三句话说明改了哪几类问题。
每一步都做完才算完成。第 3 步的标准是：清单每一条都对照过，全文没有命中。
句子
- 用逗号隔开的每一截，尽量在 20 字以内。超过 30 字就拆开。整句不超过 100 字。
- 一句只说一个意思。多用简单句和并列句，把长定语拆出去。
- 差：那个昨天生病的人没有参加会议。
- 好：他昨天生病了，没有参加会议。
- 用肯定句，不用双重否定。
- 差：请确认没有接通装置的电源。 → 好：请确认装置的电源已关闭。
- 差：没有删除权限的用户，不能删除此文件。 → 好：用户必须有删除权限，才能删除此文件。
- 用主动语态，少用“被”。
- 差：假如此软件尚未被安装 → 好：假如还没安装这个软件
- 动词直接用，不套“进行”“做出”。
- 差：对配置文件进行修改 → 好：修改配置文件
- “这”“其”“该”只指一个明确的对象。可能有歧义就把名词重复一遍。
- 名词前的修饰语不超过两层，多了就拆成两句。
- 用现代汉语常用词，不用文言、生造词。
- 差：这是唯二的方法。 → 好：只有这两种方法。
- 分清“的、地、得”：开心的笑容、开心地笑、笑得开心。
语气
- 像给同事讲清楚一件事：口语化可以，网络流行语不用。
- 称呼读者用“你”，称呼项目方用“我们”。
- 用陈述语气，句末用句号。
- 用事实代替形容词：给出数字、命令、文件名、报错原文。
- 差：性能得到了大幅提升。
- 好：p99 延迟从 120 ms 降到 40 ms。
- 确定的事直接说。不确定就说清楚哪里不确定、怎么验证。
段落与结构
- 每段第一句说这段的重点，后面的句子为它服务。一段一个主题。
- 一段最好不超过 4 行，最多 7 行。
- 标题用二级、三级为主：
- 一级标题下直接接二级，不跳级。
- 同级标题只有一个时，去掉这层标题。
- 下级标题不重复上级标题的名字。
- 需要四级标题时，改用
**（1）xxx**或列表。 - 标题末尾不加句号、逗号、冒号。
- 列表只放真正并列、可以单独扫读的条目。有因果、转折关系的内容，写成段落。
- 加粗只给读者必须注意的警告或关键词，一屏最多一两处。
- 引用别人的内容或图片，注明出处。
排版
每篇都要守的规则：
- 中文与英文、数字之间加一个半角空格：
在 Linux 上安装 5 个包。 - 中文句子用全角标点：
，。：；？（）。整句是英文时用半角标点。 - 英文、数字后面紧跟全角标点时，中间不加空格：
他用的是 MacBook Air。 - 引号用全角
“ ”，引号里再套引号用‘ ’。 - 并列的词用顿号
、隔开，最后一项用“和”连接：Google、腾讯和百度。 - 省略号写成
……，不写...或。。。，也不和“等”连用。 - 数字一律用半角。
数字（千分位、单位、范围、倍数）、括号、冒号、连接号、英文缩写的细则，见 references/typography.md。文档里出现这些内容时读它。
写一整套产品手册或文档站、需要规划目录和文件名时，读 references/manual-structure.md。
AI 腔清单
自检时逐条对照。左边是要找的写法，右边是改法。
| 找这种写法 | 改成 |
|---|---|
| 开场套话：“随着……的发展”“在当今……”“值得注意的是”“需要指出的是”“让我们来看看”“接下来我们将介绍” | 删掉，第一句直接说内容 |
| 结尾套话：“总的来说”“综上所述”“总而言之”，或重复前文的总结段 | 删掉。确实需要结尾，只写新信息，比如下一步做什么 |
| 客套话：“希望对你有帮助”“如有问题欢迎交流” | 删掉 |
| 对比句式：“不是 A，而是 B”“与其说 A，不如说 B” | 直接说 B |
| 递进句式：“不仅……而且/更……” | 拆成两个陈述句 |
| 硬凑三个：三个排比形容词、每组都是三项的列表 | 有几项写几项 |
| 设问自答：“关键是什么？答案很简单：”“原因很简单：” | 直接给结论 |
| 宣传腔形容词：强大、灵活、无缝、全面、极致、优雅、轻松、一站式 | 换成具体事实，没有事实就删 |
| 黑话：赋能、抓手、闭环、链路、沉淀、对齐、颗粒度、维度、底层逻辑、范式、打通 | 换成白话。代码或业务里的正式名称（如“调用链路”）保留 |
破折号 —— 用来插入解释 | 改用逗号、冒号、括号，或拆成两句。全文最多一两处 |
| 翻译腔：“进行 + 动词”“通过……的方式”“作为一个……”、一句里多个“的” | 直接用动词，拆开长定语 |
| 过度含糊：“在某种程度上”“在一定情况下可能会” | 确定就直接说；不确定就说清条件 |
| 感叹号、emoji 标题或列表符号 | 句号，纯文字标题 |
| 每段都加粗、一两句话也拆成列表、小标题比段落还密 | 按“段落与结构”重排 |
© leter, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/zh-tech-writing of leter/zh-tech-writing.
- SKILL.md
- references/manual-structure.md
- references/typography.md
Open the folder on GitHubat commit ffda935
Compare with similar skills
Chinese Technical Writing next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Chinese Technical Writing this skillleter/zh-tech-writing | 338 | — | ~656 | Automated safety check: Pass | MIT | |
| Declaudingoaustegard/claude-skills | 150 | — | ~5.2k | Automated safety check: Pass | MIT | |
| Natural Japanese Business Writingcoji/natural-japanese | 1.9k | — | ~2.1k | Automated safety check: Pass | MIT | |
| evlog Content Writingevloghq/evlog | 1.9k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Simple English Rewritervinta/hal-9000 | 138 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Technical Writing Standardcursor/plugins | 10k | 10 repos | ~2.4k | Automated safety check: Pass | None |
Similar skills
Natural Japanese Business Writing
coji/natural-japanese
Writes and edits Japanese business documents so they read clearly and naturally, removes AI-sounding phrasing and can score how AI-like a text reads.
evlog Content Writing
evloghq/evlog
Rules for writing and reviewing evlog docs, blog posts, READMEs, skills and AGENTS.md files, with separate review and rewrite roles, a house voice and a catalog of AI-sounding tells.
Simple English Rewriter
vinta/hal-9000
Rewrites docs, READMEs, issues, comments or UI text in plain Global English that translates well and still sounds native, keeping every fact intact.
- Official
Technical Writing Standard
cursor/plugins
Applies four layers of technical-writing rules to docs, RFCs, readmes, PR descriptions and commit messages so a tired engineer follows them on the first read.
Korean Commit Message Polisher
epoko77-ai/im-not-ai
Rewrites Korean commit messages that read like office jargon or translation into natural wording, leaving the type, scope and meaning untouched.
Related
Categories
Questions about Chinese Technical Writing
What does Chinese Technical Writing do?
Sets writing rules for Chinese technical docs: short plain sentences, consistent typography and a checklist for removing AI-sounding filler. This skill sets a style standard for Chinese technical documents such as READMEs, design documents, API descriptions and tutorials, aiming for text that reads as if an experienced engineer wrote it: plain, specific and in short sentences. For a new document the agent first pins down the reader and what they should be able to do afterward, drafts against the rules, then checks the draft against an AI-tone list.
When should I use Chinese Technical Writing?
Chinese Technical Writing fits situations like: writing a README, design document, API description or tutorial in Chinese; editing existing Chinese documentation for clarity and tone; reviewing a Chinese document and listing problems as original, revision and reason; checking spacing and punctuation between Chinese and English text.
How do I install Chinese Technical Writing in Claude Code?
Run `npx skills add leter/zh-tech-writing --skill zh-tech-writing -a claude-code`. Or copy the skill folder (skills/zh-tech-writing in leter/zh-tech-writing) into .claude/skills/zh-tech-writing in your project. Claude Code loads it when a task matches its description.
How do I install Chinese Technical Writing in Codex?
Run `npx skills add leter/zh-tech-writing --skill zh-tech-writing -a codex`. Or copy the skill folder (skills/zh-tech-writing in leter/zh-tech-writing) into .agents/skills/zh-tech-writing in your project. Codex loads it when a task matches its description.
Can I use Chinese Technical Writing in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add leter/zh-tech-writing --skill zh-tech-writing -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/zh-tech-writing, .gemini/skills/zh-tech-writing, .github/skills/zh-tech-writing and .opencode/skills/zh-tech-writing in your project.
What does Chinese Technical Writing need to run?
SKILL.md names no scripts, command-line tools or credentials: Chinese Technical Writing is instructions for the agent only. Our summary lists: The autocorrect CLI for spacing and punctuation fixes (optional).
Does Chinese Technical Writing access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Chinese Technical Writing safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Chinese Technical Writing use?
Chinese Technical Writing is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Chinese Technical Writing use?
About 656 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 936 tokens, read only when the agent opens those files.
What are the alternatives to Chinese Technical Writing?
Skills that share tags, products or a category with Chinese Technical Writing: Declauding (oaustegard/claude-skills, 150 stars), Natural Japanese Business Writing (coji/natural-japanese, 1.9k stars), evlog Content Writing (evloghq/evlog, 1.9k stars) and Simple English Rewriter (vinta/hal-9000, 138 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Chinese Technical Writing?
leter (a GitHub user) maintains it in leter/zh-tech-writing, which has 338 GitHub stars. The repository was last updated on September 24, 2026.
Source: leter/zh-tech-writing on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.