De-AI Polish for Chinese Articles
cat-xierluo/legal-skills
Detects and rewrites machine-sounding patterns in the body text of Chinese articles while keeping the author's facts, headings and legal terms intact.
去除中文文本中的 AI 生成痕迹，保留事实、原意和所需语气。用于编辑或审阅文本，使句子更直接、节奏更自然、归因更具体，并清理套话、公式结构、宣传腔、模糊权威、对称排比和聊天机器人残留；不用于虚构经历、事实或情绪。
Install Humanizer Zh
$ npx skills add 843645440/wechat-skill --skill humanizer-zh -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install 843645440/wechat-skill humanizer-zh --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/843645440/wechat-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/humanizer-zh .claude/skills/humanizer-zh && 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 "humanizer-zh" agent skill from https://github.com/843645440/wechat-skill/tree/release/.agents/skills/humanizer-zh into .claude/skills/humanizer-zh/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh", 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/843645440/wechat-skill/tree/release/.agents/skills/humanizer-zhType 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 843645440/wechat-skill --skill humanizer-zh -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install 843645440/wechat-skill humanizer-zh --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/843645440/wechat-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/humanizer-zh .agents/skills/humanizer-zh && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "humanizer-zh" agent skill from https://github.com/843645440/wechat-skill/tree/release/.agents/skills/humanizer-zh into .agents/skills/humanizer-zh/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh", 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 843645440/wechat-skill --skill humanizer-zh -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install 843645440/wechat-skill humanizer-zh --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/843645440/wechat-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/humanizer-zh .cursor/skills/humanizer-zh && 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 "humanizer-zh" agent skill from https://github.com/843645440/wechat-skill/tree/release/.agents/skills/humanizer-zh into .cursor/skills/humanizer-zh/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh", 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/843645440/wechat-skill.git --path .agents/skills/humanizer-zh--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 843645440/wechat-skill --skill humanizer-zh -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install 843645440/wechat-skill humanizer-zh --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/843645440/wechat-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/humanizer-zh .gemini/skills/humanizer-zh && 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 "humanizer-zh" agent skill from https://github.com/843645440/wechat-skill/tree/release/.agents/skills/humanizer-zh into .gemini/skills/humanizer-zh/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh", 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 843645440/wechat-skill humanizer-zhInstalls 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 843645440/wechat-skill --skill humanizer-zh -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/843645440/wechat-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/humanizer-zh .github/skills/humanizer-zh && 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 "humanizer-zh" agent skill from https://github.com/843645440/wechat-skill/tree/release/.agents/skills/humanizer-zh into .github/skills/humanizer-zh/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh", 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 843645440/wechat-skill --skill humanizer-zh -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install 843645440/wechat-skill humanizer-zh --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/843645440/wechat-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/humanizer-zh .opencode/skills/humanizer-zh && 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 "humanizer-zh" agent skill from https://github.com/843645440/wechat-skill/tree/release/.agents/skills/humanizer-zh into .opencode/skills/humanizer-zh/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer-zh", 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
humanizer-zh- GitHub stars
- 109
- Token cost
- ~503 tokens
- SKILL.md length
- 93 words
- Files
- 6 (incl. references)
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- MIT
At a glance
去除中文文本中的 AI 生成痕迹，保留事实、原意和所需语气。用于编辑或审阅文本，使句子更直接、节奏更自然、归因更具体，并清理套话、公式结构、宣传腔、模糊权威、对称排比和聊天机器人残留；不用于虚构经历、事实或情绪。
- Works in 7 steps: 锁定事实：先标出数字、日期、专名、引语、来源、结论状态和必要限定，改写后逐项核对。 → 删除空话：删“值得注意的是”“标志着重要转折”“不断演变的格局”等不增加信息的句子。 → 修正归因：有明确来源就写来源；没有就删掉“专家认为”“多方指出”之类假权威，不自造… → …
- Tasks that involve Humanizing AI text
- SKILL.md covers 不可越过的边界, 先确定声口, 一轮改写法 and 快速检查, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Humanizer Zh is an agent skill from 843645440/wechat-skill. 去除中文文本中的 AI 生成痕迹，保留事实、原意和所需语气。用于编辑或审阅文本，使句子更直接、节奏更自然、归因更具体，并清理套话、公式结构、宣传腔、模糊权威、对称排比和聊天机器人残留；不用于虚构经历、事实或情绪。
Its SKILL.md is about 500 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `agents/openai.yaml`, `references/pattern-catalog.md` and `references/wechat-pipeline-constraints.md`).
It sits in Writing & Content, covering Humanizing AI text. It works with WeChat. The repository describes itself as: 微信公众号内容 Skill 工具包：热点发现、科技写作、去 AI 味、配图、排版、多账号草稿与工作流编排。 The licence is MIT.
When your agent uses it
- Tasks that involve Humanizing AI text
Example prompts
- “/humanizer-zh”
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- 锁定事实：先标出数字、日期、专名、引语、来源、结论状态和必要限定，改写后逐项核对。
- 删除空话：删“值得注意的是”“标志着重要转折”“不断演变的格局”等不增加信息的句子。
- 修正归因：有明确来源就写来源；没有就删掉“专家认为”“多方指出”之类假权威，不自造出处。
- 拆公式结构：处理“不仅……而且……”“不是……而是……”、机械三段式、每节同构和“挑战与展望”模板。
- 恢复自然节奏：长短句交错，能用“是/有/可以”就不用绕弯结构；允许关键词自然重复，不做同义词循环。
- 清理展示痕迹：删聊天式开场、免责声明、讨好语、emoji、过多粗体、内联小标题列表和万能积极结尾。
- 终检：朗读一遍，检查事实未膨胀、立场未漂移、语气符合模式、段落不再像同一模板复制。
What it can do on your machine
Read from SKILL.md and the folder at commit 8ae1abe. 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
Humanizer Zh loads about 503 tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 30 tokens; SKILL.md has 93 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 843645440/wechat-skill at commit 8ae1abe, republished under its MIT licence (© 843645440). 93 words, ~503 tokens.
Download SKILL.mdSave it as
.claude/skills/humanizer-zh/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- humanizer-zh
- description
- 去除中文文本中的 AI 生成痕迹，保留事实、原意和所需语气。用于编辑或审阅文本，使句子更直接、节奏更自然、归因更具体，并清理套话、公式结构、宣传腔、模糊权威、对称排比和聊天机器人残留；不用于虚构经历、事实或情绪。
Humanizer-zh
把文本改得像一个具体的人写的，而不是简单换同义词。目标是更直接、更有节奏、更符合原定声口，同时不扩张事实。
不可越过的边界
- 不新增数字、人物、引语、案例、来源、现场细节、亲历、采访、动机或结论。
- 不把不确定内容改成确定事实，不删除原文中的必要限定和来源边界。
- 不擅自改变立场、受众、文体和风险级别；正式报道不能被改成情绪化自媒体文。
- 保留标题层级、链接、引用、代码、表格和用户要求保留的结构。
- 若原文缺少支撑，不用“更具体”的虚构细节填空；改为删掉空泛主张或明确其不确定性。
先确定声口
按 brief 或原文选择，不把“人味”误解为一律使用第一人称：
| 模式 | 目标 |
|---|---|
| 正式报道 / 公共事件档案 | 克制、清楚、事实优先；情绪来自事实后果，不注入“我很愤怒”等表演性反应 |
| 观点 / 行业专栏 | 可保留第一人称和锋利判断；情绪必须钉在已知机制、成本或责任上 |
| 教程 / 技术说明 | 直接、准确、少铺垫；不强行加个性段落 |
| 普通编辑 | 匹配原文语气，只清理机器痕迹 |
一轮改写法
- 锁定事实：先标出数字、日期、专名、引语、来源、结论状态和必要限定，改写后逐项核对。
- 删除空话：删“值得注意的是”“标志着重要转折”“不断演变的格局”等不增加信息的句子。
- 修正归因：有明确来源就写来源；没有就删掉“专家认为”“多方指出”之类假权威，不自造出处。
- 拆公式结构：处理“不仅……而且……”“不是……而是……”、机械三段式、每节同构和“挑战与展望”模板。
- 恢复自然节奏：长短句交错，能用“是/有/可以”就不用绕弯结构；允许关键词自然重复，不做同义词循环。
- 清理展示痕迹：删聊天式开场、免责声明、讨好语、emoji、过多粗体、内联小标题列表和万能积极结尾。
- 终检：朗读一遍，检查事实未膨胀、立场未漂移、语气符合模式、段落不再像同一模板复制。
优先处理最影响阅读的句子，不为追求“变化”把每句话都改一遍。空洞金句应删；有事实或机制支撑的锋利判断可以保留。
快速检查
- 连续三句长度和结构相同：拆掉其中一句或合并两句。
- 一段里出现多个“此外、然而、同时、值得注意的是”：多数可直接删除。
- “从 A 到 B”不是同一尺度、“三项”只是为了凑完整：改为真实关系和真实数量。
- 破折号、括号、粗体和冒号列表抢过正文：减少展示性标记。
- 段尾总是口号、反问或一句金句：改成事实、代价、未决边界，或直接结束。
- 读起来很顺却没有任何可核验信息：删除或回到来源补证，不润色成更像真的话。
24 类模式及其最短修法见 references/pattern-catalog.md。只有文本顽固、需要解释修改原因或做专项审阅时才加载，不是每次必读。
输出
默认只给改写后的完整文本。用户要求审阅说明时，再附一段简短修改摘要；不要输出内部评分表或逐句思考过程。
在微信公众号流水线中
被 wechat-content-pipeline 调用时：
- 读取
references/wechat-pipeline-constraints.md和流水线的references/humanize-pass.md。 - 只就地改写任务目录里的
article.md一轮，不修改其他产物，不把说明写进正文。 - 保持唯一一级标题、必要二级标题与 Markdown 结构，纯正文字数仍须在 2500—5000。
user-brief.md标有“公共事件档案模式”时使用克制报道声口；其他稿件按 brief 和账号档案决定是否使用强情感第一人称。- 保留 dossier 的结论状态、时间线、来源边界和隐私处理；禁止用修辞强化未被来源支持的指控。
本 Skill 源自 op7418/Humanizer-zh，其上游参考 Wikipedia 的 “Signs of AI writing”。本仓库版本为公众号流水线加入了事实、声口和公共事件约束；同步上游时不得覆盖这些边界。
© 843645440, 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 5 other files (references) in .agents/skills/humanizer-zh of 843645440/wechat-skill.
- SKILL.md
- .gitignore
- LICENSE
- agents/openai.yaml
- references/pattern-catalog.md
- references/wechat-pipeline-constraints.md
Open the folder on GitHubat commit 8ae1abe
Compare with similar skills
Humanizer Zh 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 |
|---|---|---|---|---|---|---|
| Humanizer Zh this skill843645440/wechat-skill | 109 | — | ~503 | Automated safety check: Pass | MIT | |
| De-AI Polish for Chinese Articlescat-xierluo/legal-skills | 720 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Wechat Article WriterLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.5k | Automated safety check: Pass | MIT | |
| HumanizerAzure-Samples/interview-coach-agent-framework | 173 | 38 repos | ~5.8k | Automated safety check: Pass | MIT | |
| Avoid AI Writingconorbronsdon/avoid-ai-writing | 4.9k | 3 repos | ~8.1k | Automated safety check: Pass | MIT | |
| User-Facing Text Cleanupguillaumemeyer/watermarks-remover | 24k | — | ~3.5k | Automated safety check: Pass | MIT |
Similar skills
Wechat Article Writer
LeoYeAI/openclaw-master-skills
WeChat Official Account article writing assistant. An agent skill from LeoYeAI/openclaw-master-skills.
- Official
Humanizer
Azure-Samples/interview-coach-agent-framework
Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.
Avoid AI Writing
conorbronsdon/avoid-ai-writing
Audit and rewrite content to remove AI writing patterns ("AI-isms").
User-Facing Text Cleanup
guillaumemeyer/watermarks-remover
Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.
Install Anti Slop
trycompai/crm
Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.
More from 843645440/wechat-skill
All 9 skills in this repoWechat HTML Cover
843645440/wechat-skill
使用受约束 JSON、固定 HTML/CSS 和 Chrome/Chromium 确定性生成微信公众号封面 PNG。用于完整公众号流水线必须提供 thumbmediaid，或需要准确中文标题、独立封面视觉且不调用图片模型的 1410×600 封面时；不生成正文图片。
Wechat Skill
843645440/wechat-skill
微信公众号文章排版与多账号发布工具，把已有 Markdown、DOCX、PDF 或纯文本转成可直接粘贴或通过官方 API 写入草稿箱/发布的 HTML。用于用户明确要求“公众号排版”“微信排版”“转公众号 HTML”“自动排版”“一键排版”、上传草稿、发布已有文章或配置多账号发布时。单独要求撰写文章时使用…
Wechat Content Pipeline
843645440/wechat-skill
编排中文微信公众号文章。两条入口：用户成稿只排版推草稿（去 AI 味可关，不卡字数）；或给主题由 AI 写（去 AI 味强制开）。可降级配图、封面、随机主题，写入指定账号草稿箱。默认不扫热点、不公开发布。
Wechat Inline Visuals
843645440/wechat-skill
从已完成写作的微信公众号文章中提取观点、对比、流程或已核实数据，并交给固定渲染器一次生成当前主题的公众号正文与原生 HTML 信息模块。用于已选定排版主题后增强手机端扫读体验，同时不生成正文图片、不调用图片模型、不让 Agent 临时编码排版的场景。
Wechat Public Event Archive
843645440/wechat-skill
受控系列选题上游。仓库默认是科技/AI 系列；仅当本机 config/local 启用 public-event 预设时，才核验官方材料并策展公共事件档案。不自动公开发布。
Wechat Viral Writer
843645440/wechat-skill
写有人愿意读完的中文微信公众号文章，并用脚本把「好不好」量化成分数。四个维度：信息量（每 300 字一个具体信息）、利他性（读者能带走的东西）、可读性（手机竖屏节奏）、抓人（钩子密度与闭环）。写完必须跑 scoredraft.py 体检并修到 blocking=0 且 score≥75。自带默认关闭的热点雷达开关（hotradar.py），开启后聚合 8…
Related
Works with
Categories
Questions about Humanizer Zh
What does Humanizer Zh do?
去除中文文本中的 AI 生成痕迹，保留事实、原意和所需语气。用于编辑或审阅文本，使句子更直接、节奏更自然、归因更具体，并清理套话、公式结构、宣传腔、模糊权威、对称排比和聊天机器人残留；不用于虚构经历、事实或情绪。. Humanizer Zh is an agent skill from 843645440/wechat-skill.
When should I use Humanizer Zh?
Humanizer Zh fits situations like: tasks that involve Humanizing AI text.
How do I install Humanizer Zh in Claude Code?
Run `npx skills add 843645440/wechat-skill --skill humanizer-zh -a claude-code`. Or copy the skill folder (.agents/skills/humanizer-zh in 843645440/wechat-skill) into .claude/skills/humanizer-zh in your project. Claude Code loads it when a task matches its description.
How do I install Humanizer Zh in Codex?
Run `npx skills add 843645440/wechat-skill --skill humanizer-zh -a codex`. Or copy the skill folder (.agents/skills/humanizer-zh in 843645440/wechat-skill) into .agents/skills/humanizer-zh in your project. Codex loads it when a task matches its description.
Can I use Humanizer Zh 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 843645440/wechat-skill --skill humanizer-zh -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/humanizer-zh, .gemini/skills/humanizer-zh, .github/skills/humanizer-zh and .opencode/skills/humanizer-zh in your project.
What does Humanizer Zh need to run?
SKILL.md names no scripts, command-line tools or credentials: Humanizer Zh is instructions for the agent only.
Does Humanizer Zh 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 Humanizer Zh 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 Humanizer Zh use?
Humanizer Zh is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Humanizer Zh use?
About 503 tokens (SKILL.md is roughly 2k 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 1.1k tokens, read only when the agent opens those files.
What are the alternatives to Humanizer Zh?
Skills that share tags, products or a category with Humanizer Zh: De-AI Polish for Chinese Articles (cat-xierluo/legal-skills, 720 stars), Wechat Article Writer (LeoYeAI/openclaw-master-skills, 2.2k stars), Humanizer (Azure-Samples/interview-coach-agent-framework, 173 stars) and Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Humanizer Zh?
843645440 (a GitHub user) maintains it in 843645440/wechat-skill, which has 109 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 14, 2026.
Source: 843645440/wechat-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.