Agent skill

Chinese Quotes Fix

by ranxi2001 in ranxi2001/zero2Agent

Check and fix Chinese quote pairing in Markdown files generated by ClaudeCode or other agents, while preserving Markdown syntax and protected blocks.

MITAuto-check passedDocuments & Office

Install Chinese Quotes Fix

skills CLI
$ npx skills add ranxi2001/zero2Agent --skill chinese-quotes-fix -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ranxi2001/zero2Agent chinese-quotes-fix --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ranxi2001/zero2Agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/chinese-quotes-fix .claude/skills/chinese-quotes-fix && rm -rf skills-src

Use ~/.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/

Facts

Skill name
chinese-quotes-fix
GitHub stars
715
Token cost
~735 tokens
SKILL.md length
190 words
Files
5
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Check and fix Chinese quote pairing in Markdown files generated by ClaudeCode or other agents, while preserving Markdown syntax and protected blocks.

  • Works in 4 steps: 先检查 → 预览修复 → 正式修复 → …
  • Tasks that involve Markdown
  • SKILL.md covers 适用场景, 保护区规则, 标准工作流 and 配对策略, plus 3 more sections
  • Runs Python scripts from its folder; calls python

What it does

Chinese Quotes Fix is an agent skill from ranxi2001/zero2Agent. Check and fix Chinese quote pairing in Markdown files generated by ClaudeCode or other agents, while preserving Markdown syntax and protected blocks.

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `check_quotes.py`, `fix_quotes.py` and `quote_utils.py`).

It sits in Documents & Office, covering Markdown. It works with Mermaid. The repository describes itself as: 面向大厂Agent研发岗位求职的agent教程网站,涵盖技术路线与面试八股文. The licence is MIT.

When your agent uses it

  • Tasks that involve Markdown

Example prompts

  • “/chinese-quotes-fix”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. 先检查
  2. 预览修复
  3. 正式修复
  4. 修复配对问题(弯引号方向错误)

What it can do on your machine

Read from SKILL.md and the folder at commit 472ce78. 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

    Ships script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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 Quotes Fix loads about 735 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 190 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~735

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 ranxi2001/zero2Agent at commit 472ce78, republished under its MIT licence (© ranxi2001). 190 words, ~735 tokens.

Download SKILL.mdSave it as .claude/skills/chinese-quotes-fix/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
chinese-quotes-fix
description
Check and fix Chinese quote pairing in Markdown files generated by ClaudeCode or other agents, while preserving Markdown syntax and protected blocks.

中文引号修复技能

用于检查并修复 Markdown 文档里的中文引号问题(双引号 + 单引号),重点处理 ClaudeCode / Agent 生成文档中常见的这类错误:

  • 正文里混入英文直双引号 "
  • 正文里中文语境下的直单引号 '(如 '客户为先')未转为中文单引号 ‘’
  • 左右引号方向不配对
  • Mermaid、YAML、代码块、HTML 属性等语法区域被误改

核心目标不是“全局轮流替换”,而是只修正文 prose,并尽量准确判断每个直引号应该变成左引号还是右引号。

适用场景

  • ClaudeCode 输出的教程、博客、知识库文档
  • 含有 Mermaid 流程图、HTML 片段、Markdown 链接的 Markdown 文件
  • 中文正文为主,夹杂英文术语,例如 "做 Agent"、"微调"、"一问一答"

保护区规则

以下区域中的直引号默认不改动:

  • YAML front matter
  • Fenced code blocks,包括 ``` 和 ~~~
  • Inline code
  • Mermaid HTML 块,例如 <div class="mermaid">...</div>
  • Markdown 链接与引用式链接定义
  • HTML tag / attribute / comment
  • 常见非正文 HTML block,例如 details、table、svg、pre

这条规则是为了避免把语法中的合法直引号误改成中文弯引号,导致 Markdown、HTML 或 Mermaid 失效。

标准工作流

1. 先检查
bash
python .claude/skills/chinese-quotes-fix/check_quotes.py "path/to/file.md"

批量检查:

bash
python .claude/skills/chinese-quotes-fix/check_quotes.py "docs/**/*.md"

检查输出会区分:

  • 文件里一共有多少个直双引号 / 直单引号
  • 有多少个在正文里,属于可修复目标(单引号仅检测 CJK 语境)
  • 哪些行仍有正文直引号
  • 当前正文里的弯引号是否存在配对问题(双引号和单引号分别报告)
  • 只要存在正文直引号或配对问题,命令就返回非零退出码,便于 CI 和自动化校验阻止错误内容发布
2. 预览修复
bash
python .claude/skills/chinese-quotes-fix/fix_quotes.py --dry-run "path/to/file.md"
3. 正式修复
bash
python .claude/skills/chinese-quotes-fix/fix_quotes.py "path/to/file.md"
4. 修复配对问题(弯引号方向错误)

当 check 报告 pairing issues(如 ”Context Engineering” 应为 “Context Engineering”)时,使用 --fix-pairing:

bash
python .claude/skills/chinese-quotes-fix/fix_quotes.py --fix-pairing --dry-run "path/to/file.md"
python .claude/skills/chinese-quotes-fix/fix_quotes.py --fix-pairing "path/to/file.md"

此模式会分析上下文判断每个弯引号的正确方向,将误用为开引号的 ” 修正为 “,反之亦然。

配对策略

双引号

脚本不会简单按“第 1 个左引号、第 2 个右引号”做全局替换,而是结合上下文判断:

  • 行首、冒号、左括号等之后的直引号,优先判为开引号 “
  • 标点、句末、右括号之前的直引号,优先判为闭引号 ”
  • 如果一行里已经出现现成的 “ / ”,会把它们纳入状态判断,尽量修复混用场景
  • 状态按行重置,避免上一段的未闭合引号污染下一段
单引号

单引号使用同样的上下文判断逻辑,但额外增加 CJK 语境检测:

  • 只有当直单引号 ' 的前后邻近字符包含 CJK 文字或中文标点时,才判定为中文单引号并进行转换
  • 英文语境中的撇号(如 don't、it's)不会被误改
  • 转换目标:' → ‘(U+2018)或 ’(U+2019)

常见修复场景:

  • “客户为先” 中的 '客户为先' → ‘客户为先’
  • 京东的'多快好省'理念 → 京东的‘多快好省’理念

推荐使用方式

当你刚完成一篇 agent 生成的中文文档时,建议顺序如下:

  1. 先完成正文生成或格式整理
  2. 再跑 check_quotes.py
  3. 如果存在正文直引号,再用 fix_quotes.py --dry-run
  4. 预览无误后正式执行修复
  5. 最后抽查 Mermaid、YAML、链接和 HTML 片段

验收清单

修复完成后至少确认这几项:

  • 正文里的 " 已替换成配对的 “”
  • CJK 语境中的 ' 已替换成配对的 ‘’
  • 英文撇号(don't、it's)保持原样
  • Mermaid 中的 [“text”] 保持原样
  • YAML 里的 title: “...” 保持原样
  • Markdown 链接没有被破坏
  • check_quotes.py 不再报 Needs fix
  • check_quotes.py 的双引号和单引号 Pairing issues 均为 0

注意事项

  • 单引号仅在 CJK 语境下修复(前后邻近字符为中文字或中文标点),英文撇号不受影响
  • 如果某些 HTML block 内部本身就是正文,但你不希望保护它们,需要按具体场景再调规则
  • 如果文档里故意保留英文学术用法的直引号,修复前请先用 --dry-run 确认
  • Windows 控制台可能不是 UTF-8,脚本已经做了安全输出处理,但最终内容仍建议以文件实际渲染结果为准

© ranxi2001, 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 4 other files in .agents/skills/chinese-quotes-fix of ranxi2001/zero2Agent.

  • SKILL.md
  • check_quotes.py
  • fix_quotes.py
  • quote_utils.py
  • test_quote_utils.py

Open the folder on GitHubat commit 472ce78

Compare with similar skills

Chinese Quotes Fix 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.

Chinese Quotes Fix compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Chinese Quotes Fix this skillranxi2001/zero2Agent715—~735Automated safety check: PassMIT
Markdown to Word Convertercat-xierluo/SuitAgent205—~559Automated safety check: PassMIT
State Trend Advisordigoal/blog8.6k—~1kAutomated safety check: PassGPL-2.0
Enterprise Plannerdigoal/blog8.6k—~1.1kAutomated safety check: PassGPL-2.0
Paper Interpreterdigoal/blog8.6k—~1.1kAutomated safety check: PassGPL-2.0
Personal Plannerdigoal/blog8.6k—~897Automated safety check: PassGPL-2.0

Similar skills

  • Markdown to Word Converter

    cat-xierluo/SuitAgent

    Converts Markdown files into Word documents formatted to Chinese typesetting conventions, with presets for academic, legal, report and book layouts.

    205 GitHub stars~559 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • 顺势而为,跟着国家走——抓取并分析国家五年规划、政策文件及重大新闻,结合询问者背景(擅长领域、特长、爱好),围绕"投资、创业方向、商业思路、产品思路、就业择业、学习规划"六大维度,生成逻辑严密、图文并茂、有数据支撑的战略分析报告,输出到项目 markdown/ 目录。

    8.6k GitHub stars~1k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • 为企业生成深度未来规划与建议书。输入企业名称、简介、网站等基本信息,自动搜索企业相关情报、行业数据、竞争格局,构建完整企业画像,再结合当下环境与未来趋势,输出图文并茂、有数据支撑的战略规划报告(Markdown 格式),保存到当前项目的 markdown/…

    8.6k GitHub stars~1.1k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • 深度解读学术论文,将论文 PDF(文件或 URL)转化为通俗易懂、图文并茂的 Markdown 解读文档,保存到项目的 markdown/ 目录。触发条件:用户上传或提供论文 PDF、提到"解读论文"/"读论文"/"分析这篇论文"/"帮我看这篇 paper",或任何需要深入理解一篇学术论文的场景。即使用户只说"帮我看这个 PDF"但内容是论文,也应使用本…

    8.6k GitHub stars~1.1k tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Personal Planner

    digoal/blog

    为提问者生成个性化的未来规划与建议书。输入提问者的背景信息(职业、年龄、资源、目标、困境等),基于深度画像分析、行业趋势研判和商业洞察,输出一份图文并茂、有数据支撑、逻辑严密的 Markdown 规划报告,保存到项目 markdown/ 目录。触发条件:用户提供个人背景信息并希望获得规划建议,提到"帮我规划"、"未来规划"、"职业规划"、"个人发展"、"我该怎么做"、"给我写一份建议书"、"我的…

    8.6k GitHub stars~897 tokensUpdated yesterday
    Documents & OfficeAuto-check passed
  • Bangunai Blog Manager

    LeoYeAI/openclaw-master-skills

    A skill your agent uses when managing BangunAI Blog content, automating blog workflows, and writing MDX articles with BangunAI conventions.

    2.2k GitHub stars~5.7k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed

More from ranxi2001/zero2Agent

All 8 skills in this repo
  • Drawio Skill

    ranxi2001/zero2Agent

    A skill your agent uses when user requests diagrams, flowcharts, architecture charts, or visualizations.

    715 GitHub stars~6.6k tokensUpdated today
    Auto-check passed
  • Classify Interview Questions

    ranxi2001/zero2Agent

    将批量面经或零散面试题逐题去重并分发:Agent/LLM/AI工程题写入 zero2Agent 的 learn-agent-interview,传统后端八股写入相邻 zero2Leetcode 的夏季八股。大批量输入使用 gpt-5.6-luna API 逐篇并发抽题和语义召回,再审查、去重和写答案;不新建面经实录文章。

    715 GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • New Article

    ranxi2001/zero2Agent

    在 zero2Agent 项目中创建新的学习文章。当用户说"写一篇新文章"、"创建文章"、"新建文章"、"在某模块下添加一篇关于X的文章"、"帮我起草一篇讲XX的内容"、"整理面经"时触发。适用于所有模块下新建内容,包括面试维度拆解文章和面经实录。即使用户没有明确说"文章",只要涉及给 zero2Agent 项目增加教学内容,也应当触发此技能。

    715 GitHub stars~693 tokensUpdated today
    Auto-check passed
  • New Module

    ranxi2001/zero2Agent

    在 zero2Agent 项目中创建新的学习模块。当用户说"新建模块"、"添加模块"、"创建一个新的学习章节"、"我想增加一个关于X的模块"时触发。负责创建模块目录结构、index.md,并同步更新主页 index.html 和 layouts/default.html 的导航。即使用户只是说"我想增加一个讲XX的章节",也应当触发此技能。

    715 GitHub stars~489 tokensUpdated today
    Auto-check passed
  • Scrape Nowcoder

    ranxi2001/zero2Agent

    基于 CDP 原生 WebSocket 抓取牛客网面经文章。当用户说"抓牛客"、"爬牛客面经"、"nowcoder 抓取"、"抓取面经列表"时触发。通过 Chrome 调试端口直接连接已登录的浏览器会话,支持首页、话题、搜索分页和详情全文抓取,输出 Markdown。

    715 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Content Review

    ranxi2001/zero2Agent

    审查 zero2Agent 项目中的文章内容质量。当用户说"审查文章"、"review内容"、"检查这篇文章写得怎么样"、"看看这篇符不符合项目风格"、"帮我看看内容质量"时触发。负责对照项目风格标准进行结构化评审,输出具体的改进建议。即使用户只是说"帮我看看写得怎么样",只要涉及 zero2Agent 的 Markdown 文章,也应当触发此技能。

    715 GitHub stars~385 tokensUpdated today
    Auto-check passed

Works with

Questions about Chinese Quotes Fix

What does Chinese Quotes Fix do?

Check and fix Chinese quote pairing in Markdown files generated by ClaudeCode or other agents, while preserving Markdown syntax and protected blocks. Chinese Quotes Fix is an agent skill from ranxi2001/zero2Agent. Check and fix Chinese quote pairing in Markdown files generated by ClaudeCode or other agents, while preserving Markdown syntax and protected blocks.

When should I use Chinese Quotes Fix?

Chinese Quotes Fix fits situations like: tasks that involve Markdown.

How do I install Chinese Quotes Fix in Claude Code?

Run `npx skills add ranxi2001/zero2Agent --skill chinese-quotes-fix -a claude-code`. Or copy the skill folder (.agents/skills/chinese-quotes-fix in ranxi2001/zero2Agent) into .claude/skills/chinese-quotes-fix in your project. Claude Code loads it when a task matches its description.

How do I install Chinese Quotes Fix in Codex?

Run `npx skills add ranxi2001/zero2Agent --skill chinese-quotes-fix -a codex`. Or copy the skill folder (.agents/skills/chinese-quotes-fix in ranxi2001/zero2Agent) into .agents/skills/chinese-quotes-fix in your project. Codex loads it when a task matches its description.

Can I use Chinese Quotes Fix 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 ranxi2001/zero2Agent --skill chinese-quotes-fix -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chinese-quotes-fix, .gemini/skills/chinese-quotes-fix, .github/skills/chinese-quotes-fix and .opencode/skills/chinese-quotes-fix in your project.

What does Chinese Quotes Fix need to run?

Going by SKILL.md and its folder, Chinese Quotes Fix needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Chinese Quotes Fix 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 Quotes Fix 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 Quotes Fix use?

Chinese Quotes Fix 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 Quotes Fix use?

About 735 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Chinese Quotes Fix?

Skills that share tags, products or a category with Chinese Quotes Fix: Markdown to Word Converter (cat-xierluo/SuitAgent, 205 stars), State Trend Advisor (digoal/blog, 8.6k stars), Enterprise Planner (digoal/blog, 8.6k stars) and Paper Interpreter (digoal/blog, 8.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Chinese Quotes Fix?

ranxi2001 (a GitHub user) maintains it in ranxi2001/zero2Agent, which has 715 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 10, 2026.

Source: ranxi2001/zero2Agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.