Humanizer Zh
ai-zixun/humanizer-zh
Remove signs of AI-generated, translated, or overly mechanical Chinese prose.
A skill your agent uses when a user asks to polish, rewrite, humanize, de-AI, localize, or oralize Chinese writing, including short-video scripts, articles, social posts, speeches, newsletters, and…
Install Humanized Chinese Writing Polisher
$ npx skills add EthanYoQ/agent-xiaohongshu-workbench --skill humanized-chinese-writing-polisher -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install EthanYoQ/agent-xiaohongshu-workbench humanized-chinese-writing-polisher --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/EthanYoQ/agent-xiaohongshu-workbench.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/humanized-chinese-writing-polisher .claude/skills/humanized-chinese-writing-polisher && 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 "humanized-chinese-writing-polisher" agent skill from https://github.com/EthanYoQ/agent-xiaohongshu-workbench/tree/main/.agents/skills/humanized-chinese-writing-polisher into .claude/skills/humanized-chinese-writing-polisher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanized-chinese-writing-polisher", 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/EthanYoQ/agent-xiaohongshu-workbench/tree/main/.agents/skills/humanized-chinese-writing-polisherType 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 EthanYoQ/agent-xiaohongshu-workbench --skill humanized-chinese-writing-polisher -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install EthanYoQ/agent-xiaohongshu-workbench humanized-chinese-writing-polisher --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/EthanYoQ/agent-xiaohongshu-workbench.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/humanized-chinese-writing-polisher .agents/skills/humanized-chinese-writing-polisher && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "humanized-chinese-writing-polisher" agent skill from https://github.com/EthanYoQ/agent-xiaohongshu-workbench/tree/main/.agents/skills/humanized-chinese-writing-polisher into .agents/skills/humanized-chinese-writing-polisher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanized-chinese-writing-polisher", 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 EthanYoQ/agent-xiaohongshu-workbench --skill humanized-chinese-writing-polisher -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install EthanYoQ/agent-xiaohongshu-workbench humanized-chinese-writing-polisher --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/EthanYoQ/agent-xiaohongshu-workbench.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/humanized-chinese-writing-polisher .cursor/skills/humanized-chinese-writing-polisher && 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 "humanized-chinese-writing-polisher" agent skill from https://github.com/EthanYoQ/agent-xiaohongshu-workbench/tree/main/.agents/skills/humanized-chinese-writing-polisher into .cursor/skills/humanized-chinese-writing-polisher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanized-chinese-writing-polisher", 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/EthanYoQ/agent-xiaohongshu-workbench.git --path .agents/skills/humanized-chinese-writing-polisher--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 EthanYoQ/agent-xiaohongshu-workbench --skill humanized-chinese-writing-polisher -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install EthanYoQ/agent-xiaohongshu-workbench humanized-chinese-writing-polisher --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/EthanYoQ/agent-xiaohongshu-workbench.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/humanized-chinese-writing-polisher .gemini/skills/humanized-chinese-writing-polisher && 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 "humanized-chinese-writing-polisher" agent skill from https://github.com/EthanYoQ/agent-xiaohongshu-workbench/tree/main/.agents/skills/humanized-chinese-writing-polisher into .gemini/skills/humanized-chinese-writing-polisher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanized-chinese-writing-polisher", 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 EthanYoQ/agent-xiaohongshu-workbench humanized-chinese-writing-polisherInstalls 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 EthanYoQ/agent-xiaohongshu-workbench --skill humanized-chinese-writing-polisher -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/EthanYoQ/agent-xiaohongshu-workbench.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/humanized-chinese-writing-polisher .github/skills/humanized-chinese-writing-polisher && 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 "humanized-chinese-writing-polisher" agent skill from https://github.com/EthanYoQ/agent-xiaohongshu-workbench/tree/main/.agents/skills/humanized-chinese-writing-polisher into .github/skills/humanized-chinese-writing-polisher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanized-chinese-writing-polisher", 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 EthanYoQ/agent-xiaohongshu-workbench --skill humanized-chinese-writing-polisher -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install EthanYoQ/agent-xiaohongshu-workbench humanized-chinese-writing-polisher --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/EthanYoQ/agent-xiaohongshu-workbench.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/humanized-chinese-writing-polisher .opencode/skills/humanized-chinese-writing-polisher && 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 "humanized-chinese-writing-polisher" agent skill from https://github.com/EthanYoQ/agent-xiaohongshu-workbench/tree/main/.agents/skills/humanized-chinese-writing-polisher into .opencode/skills/humanized-chinese-writing-polisher/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanized-chinese-writing-polisher", 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
humanized-chinese-writing-polisher- GitHub stars
- 154
- Token cost
- ~1.1k tokens
- SKILL.md length
- 212 words
- Files
- 4 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when a user asks to polish, rewrite, humanize, de-AI, localize, or oralize Chinese writing, including short-video scripts, articles, social posts, speeches, newsletters, and…
- Works in 6 steps: 先像人，再像文章 → 保留原意，不乱加观点 → 中文语境优先 → …
- A user asks to polish
- SKILL.md covers 目标, 触发条件, 默认假设 and 核心原则, plus 6 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Humanized Chinese Writing Polisher is an agent skill from EthanYoQ/agent-xiaohongshu-workbench. Use this skill when a user asks to polish, rewrite, humanize, de-AI, localize, or oralize Chinese writing, including short-video scripts, articles, social posts, speeches, newsletters, and personal-IP content. The skill diagnoses “AI味”, preserves the user's meaning, adapts to optional style samples, replaces translation-like phrasing with natural Chinese expression, and outputs a polished version plus concise revision notes.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/anti_ai_flavor_rules.md` and `references/quality_checklist.md`).
It sits in Writing & Content, covering Humanizing AI text, Newsletters and Social media posts. It works with Xiaohongshu. The repository describes itself as: 小红书图文内容工作台：把账号定位、热点研究、选题、原创文稿、品牌配图、预览和人工确认组织成一条可控流程。 The licence is MIT.
When your agent uses it
- A user asks to polish
- Oralize Chinese writing
- Including short-video scripts
- Personal-IP content
Example prompts
- “/humanized-chinese-writing-polisher”
Workflow steps
6 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 6e58278. 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 (its code samples are markdown).
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
Humanized Chinese Writing Polisher loads about 1.1k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 116 tokens; SKILL.md has 212 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 EthanYoQ/agent-xiaohongshu-workbench at commit 6e58278, republished under its MIT licence (© EthanYoQ). 212 words, ~1,107 tokens.
Download SKILL.mdSave it as
.claude/skills/humanized-chinese-writing-polisher/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- humanized-chinese-writing-polisher
- description
- Use this skill when a user asks to polish, rewrite, humanize, de-AI, localize, or oralize Chinese writing, including short-video scripts, articles, social posts, speeches, newsletters, and personal-IP content. The skill diagnoses “AI味”, preserves the user's meaning, adapts to optional style samples, replaces translation-like phrasing with natural Chinese expression, and outputs a polished version plus concise revision notes.
中文真人感写作润色 Skill
目标
把用户提供的中文稿件润色成更自然、更像真人表达、更少 AI 味、更符合中文语境和用户个人风格的版本。
本 skill 适合处理：
- 中文短视频口播稿
- 知识类文章、公众号文章、长微博
- 小红书、朋友圈、个人 IP 文案
- 演讲稿、课程稿、直播逐字稿
- 用户希望“更像我说话”的已有稿件
核心不是把文字改得更华丽，而是让它：
- 读起来顺：没有拗口长句，没有翻译腔。
- 听起来像人：有自然停顿、口语转折、轻微个人习惯。
- 解释得清楚：复杂概念先讲人话，再讲逻辑。
- 符合中文语境：案例、比喻、梗优先使用中文用户熟悉的环境。
- 保留原意和个人风格：不擅自改观点，不把所有人都改成同一种“AI 口语风”。
触发条件
当用户出现以下意图时，优先使用本 skill：
- “帮我润色这段稿子”
- “去掉 AI 味”
- “改得更像真人说话”
- “改成口播稿”
- “改得更自然 / 更通俗 / 更顺”
- “这段话太书面了，帮我改口语一点”
- “模仿我的风格改一下”
- “把这篇文章改成中文互联网表达”
- “让它不要像 AI 写的”
- “帮我把复杂内容讲简单”
如果用户要求的是严肃论文、法律合同、政府公文、医学说明、证券投资建议等高正式度或高风险文本，不要强行口语化。可以只做轻度流畅度优化，并提醒用户需要保持准确、正式和可核验。
如果文本涉及考试真题、政策文件、新闻热点、公共事件、医疗法律金融等事实敏感场景，不要为了增强说服力补充未经核验的具体题目、官方表述、数据、人物言论或事件细节。用户没有提供来源时，只围绕用户给定主题做表达优化，并把不确定内容写成观点讨论或待核验信息。
默认假设
如果用户没有说明细节，默认采用：
- 语言：简体中文
- 润色强度：中度
- 用途：通用中文内容；如果明显像口播稿，则按口播稿处理
- 风格：自然、清楚、有真人感、不油腻、不营销号、不过度玩梗
- 输出：先给“润色后版本”，再给“主要修改点”
不要为了确认小细节而中断任务。只有在缺少原文、完全无法判断任务目标，或用户要求模仿某个未提供样本的个人风格时，才需要简短询问。
核心原则
1. 先像人，再像文章
不要追求每句话都工整、对称、完整。真人表达允许短句、停顿、追问、轻微重复和一点点口头禅。
2. 保留原意，不乱加观点
润色不是重新创作。除非用户要求“深度重写”或“补充案例”，否则不要新增事实、结论、数据、评价或立场。
涉及高考、考试、政策、新闻等公共议题时，尤其要保守：可以优化表达方式、论证顺序和口播节奏，但不要编造真题内容、命题方向、官方材料、社会案例或统计数据。
3. 中文语境优先
需要案例、比喻、商业故事、生活场景时，优先使用中文用户熟悉的企业、平台、生活经验和网络语境。不要默认使用星巴克、沃尔玛、硅谷车库、汉堡薯条等英文语料常见例子。
4. 个人风格大于通用模板
如果存在 style_samples/ 或用户粘贴了自己的过往稿件、SRT 字幕、口播逐字稿，先提炼用户风格，再润色。保留用户常用的解释方式、断句习惯、口头禅、情绪强度和比喻偏好。
5. 不要从 AI 味改成营销号味
去 AI 味不等于强行加入“家人们”“太炸裂了”“直接封神”“看懂的人已经赢麻了”。网络梗只能少量使用，并且必须服务于表达。
6. 口播优先读感
如果是口播稿，第一标准是读出来顺。看到长句、抽象词堆叠、连续书面转折，要主动拆句、换词、加停顿。
工作流
第一步：判断稿件用途和润色强度
根据用户输入判断文本类型：
- 口播稿：重点优化节奏、停顿、听感。
- 文章：重点优化逻辑、可读性、自然表达。
- 社媒文案：重点优化开头、信息密度、个人感。
- 演讲 / 课程稿：重点优化层次、过渡、讲解顺序。
润色强度分三档：
- 轻度润色：保留原结构，只改不顺和 AI 套话。
- 中度润色：默认模式；重组部分句子，增强口语和中文语境。
- 深度重写：适合 AI 味很重的稿子；可重建开头、调整结构、增强故事感。
第二步：读取或提炼风格
如果用户提供了样本，或文件夹中有 style_samples/，优先参考样本。提炼以下信息：
- 常用开头方式
- 常用转折词和口头禅
- 句子平均长度和断句习惯
- 喜欢的案例类型
- 情绪强度：冷静、吐槽、犀利、温和、陪伴感等
- 禁用表达：用户明确不喜欢的词、梗、语气
没有样本时，使用默认自然风格，不要假装已经掌握用户个人风格。
第三步：诊断 AI 味
扫描原文中的问题：
- 书面套话：例如“在当今时代”“不难发现”“值得注意的是”
- 翻译腔：例如“这使得我们能够”“提供了一个机会去”
- 抽象名词堆叠：例如“内容生产效率的系统性提升”
- 万能总结：例如“不仅……更是……”
- 机械排比：三段以上结构完全一致的句子
- 假口语：强行加入热梗或过度夸张语气
- 不符合中文语境的例子和比喻
需要更详细规则时，参考 references/anti_ai_flavor_rules.md。
第四步：改写
按以下顺序改写：
- 保观点：先确认核心观点和事实不变。
- 拆长句：把拗口长句拆成更适合阅读或口播的短句。
- 换人话：把书面词、抽象词、翻译腔换成自然中文。
- 补连接：让段落之间像真人讲述，而不是像报告目录。
- 换语境：把不接地气的例子换成中文用户熟悉的例子。
- 加读感：口播稿可加入自然停顿、追问、转折和轻微重复。
- 控梗量：只在合适位置加入少量热梗，不硬塞。
第五步：自检
输出前做一次自检：
- 是否改变了用户原意？
- 是否新增了未经证实的事实？
- 如果涉及考试 / 政策 / 新闻 / 公共事件，是否避免了编造具体题目、官方说法、数据和事件细节？
- 是否还有明显 AI 套话？
- 是否出现营销号、鸡汤味、油腻感？
- 是否过度口语化，导致不专业？
- 是否读起来顺？如果是口播稿，是否一口气能读下来？
- 是否符合用户样本中的个人风格？
需要自检清单时，参考 references/quality_checklist.md。
输出格式
默认输出：
## 润色后版本
<完整润色稿>
## 主要修改点
1. <说明改了什么>
2. <说明改了什么>
3. <说明改了什么>
## 可继续校准的地方
<指出仍可根据用户个人风格微调的地方；没有就写“暂时没有明显需要人工确认的地方”。>如果用户明确说“只要最终稿”，只输出润色后的正文，不要输出说明。
如果是口播稿，默认可以使用自然换行；只有用户需要时才加入停顿符号：
/：短停顿//：长停顿
更详细输出格式见 references/output_formats.md。
风格样本使用方法
如果用户上传或放入自己的 SRT / 文章 / 逐字稿：
- 不要直接复制样本里的具体隐私内容。
- 只提炼风格规律。
- 风格规律优先于通用规则。
- 如果样本之间风格冲突，以用户本次说明为最高优先级。
样本放置说明见 style_samples/README.md。
反馈迭代机制
当用户反馈“这里还是拗口”“不像我”“太营销号”“太书面”“梗太多”时：
- 先修改当前稿件。
- 再总结一条可复用规则。
- 建议用户把这条规则记录到
iteration_logs/或个人风格画像中。
反馈迭代方法见 references/revision_loop.md。
支撑文件索引
references/anti_ai_flavor_rules.md：AI 味诊断与替换规则references/chinese_context_examples.md：中文语境案例、生活场景和网络梗库references/oral_rhythm_rules.md：口播节奏、断句、停顿规则references/style_profile_template.md：个人风格画像模板和提取方法references/revision_loop.md：反馈—修改—沉淀规则的迭代流程references/bad_to_good_examples.md：典型 AI 表达和真人表达对照references/genre_modes.md：不同内容类型的润色策略references/output_formats.md：常用输出格式references/quality_checklist.md：最终质量检查表
禁止事项
- 不要编造事实、数据、来源或人物言论。
- 不要把所有稿件都改成短视频营销号。
- 不要因为“真人感”而牺牲专业准确性。
- 不要过度使用网络热梗。
- 不要把用户的个人口头禅全部删掉。
- 不要为了显得高级而堆概念。
- 不要输出空泛的“优化得更自然、更流畅”说明；修改点要具体。
© EthanYoQ, 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 3 other files (references) in .agents/skills/humanized-chinese-writing-polisher of EthanYoQ/agent-xiaohongshu-workbench.
- SKILL.md
- LICENSE
- references/anti_ai_flavor_rules.md
- references/quality_checklist.md
Open the folder on GitHubat commit 6e58278
Compare with similar skills
Humanized Chinese Writing Polisher 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 |
|---|---|---|---|---|---|---|
| Humanized Chinese Writing Polisher this skillEthanYoQ/agent-xiaohongshu-workbench | 154 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Humanizer Zhai-zixun/humanizer-zh | 179 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Anti Vibe Writingweijt606/anti-vibe-writing | 120 | — | ~3.9k | Automated safety check: Pass | MIT | |
| Anti AI Writingartemnovitckii/content-skills | 102 | — | ~3k | Automated safety check: Pass | MIT | |
| Content Strategy And Assemblyjacob-dietle/context-os | 111 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Podcast Pipelineericosiu/ai-marketing-skills | 3.6k | 1 repos | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Anti Vibe Writing
weijt606/anti-vibe-writing
A skill your agent uses when the user wants to humanize, de-AI, polish, or warm up an AI-generated document, in English or Chinese.
Anti AI Writing
artemnovitckii/content-skills
A skill your agent uses when writing or auditing any written content — captions, carousels, newsletters, threads, LinkedIn posts, long-form — and as the FINAL filter on every piece.
Content Strategy And Assembly
jacob-dietle/context-os
This skill should be used when producing content (newsletter posts, blog posts, LinkedIn posts) from existing corpus material.
Podcast Pipeline
ericosiu/ai-marketing-skills
Podcast-to-Everything content pipeline. An agent skill from ericosiu/ai-marketing-skills.
Linkedin Repurposer
sergebulaev/linkedin-skills
Repurpose existing content into a native LinkedIn post. An agent skill from sergebulaev/linkedin-skills.
Related
Works with
Categories
Questions about Humanized Chinese Writing Polisher
What does Humanized Chinese Writing Polisher do?
A skill your agent uses when a user asks to polish, rewrite, humanize, de-AI, localize, or oralize Chinese writing, including short-video scripts, articles, social posts, speeches, newsletters, and…. Humanized Chinese Writing Polisher is an agent skill from EthanYoQ/agent-xiaohongshu-workbench. Use this skill when a user asks to polish, rewrite, humanize, de-AI, localize, or oralize Chinese writing, including short-video scripts, articles, social posts, speeches, newsletters, and personal-IP content.
When should I use Humanized Chinese Writing Polisher?
Humanized Chinese Writing Polisher fits situations like: A user asks to polish; oralize Chinese writing; including short-video scripts; personal-IP content.
How do I install Humanized Chinese Writing Polisher in Claude Code?
Run `npx skills add EthanYoQ/agent-xiaohongshu-workbench --skill humanized-chinese-writing-polisher -a claude-code`. Or copy the skill folder (.agents/skills/humanized-chinese-writing-polisher in EthanYoQ/agent-xiaohongshu-workbench) into .claude/skills/humanized-chinese-writing-polisher in your project. Claude Code loads it when a task matches its description.
How do I install Humanized Chinese Writing Polisher in Codex?
Run `npx skills add EthanYoQ/agent-xiaohongshu-workbench --skill humanized-chinese-writing-polisher -a codex`. Or copy the skill folder (.agents/skills/humanized-chinese-writing-polisher in EthanYoQ/agent-xiaohongshu-workbench) into .agents/skills/humanized-chinese-writing-polisher in your project. Codex loads it when a task matches its description.
Can I use Humanized Chinese Writing Polisher 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 EthanYoQ/agent-xiaohongshu-workbench --skill humanized-chinese-writing-polisher -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/humanized-chinese-writing-polisher, .gemini/skills/humanized-chinese-writing-polisher, .github/skills/humanized-chinese-writing-polisher and .opencode/skills/humanized-chinese-writing-polisher in your project.
What does Humanized Chinese Writing Polisher need to run?
SKILL.md names no scripts, command-line tools or credentials: Humanized Chinese Writing Polisher is instructions for the agent only.
Does Humanized Chinese Writing Polisher 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 Humanized Chinese Writing Polisher 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 Humanized Chinese Writing Polisher use?
Humanized Chinese Writing Polisher 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 Humanized Chinese Writing Polisher use?
About 1.1k tokens (SKILL.md is roughly 4.4k 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 2.7k tokens, read only when the agent opens those files.
What are the alternatives to Humanized Chinese Writing Polisher?
Skills that share tags, products or a category with Humanized Chinese Writing Polisher: Humanizer Zh (ai-zixun/humanizer-zh, 179 stars), Anti Vibe Writing (weijt606/anti-vibe-writing, 120 stars), Anti AI Writing (artemnovitckii/content-skills, 102 stars) and Content Strategy And Assembly (jacob-dietle/context-os, 111 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Humanized Chinese Writing Polisher?
EthanYoQ (a GitHub user) maintains it in EthanYoQ/agent-xiaohongshu-workbench, which has 154 GitHub stars. The repository was last updated on September 7, 2026.
Source: EthanYoQ/agent-xiaohongshu-workbench on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.