Borrowing it
Nothing to install: this file belongs to ranxi2001/zero2Agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ranxi2001/zero2Agent/main/.claude/skills/chinese-quotes-fix/SKILL.mdgit clone --depth 1 https://github.com/ranxi2001/zero2AgentWrote 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/ranxi2001/zero2agent/chinese-quotes-fix)<a href="https://agentmods.dev/skills/ranxi2001/zero2agent/chinese-quotes-fix"><img src="https://agentmods.dev/badge/skills/ranxi2001/zero2agent/chinese-quotes-fix.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00032 | $0.01537 |
| Opus 5 | $0.00016 | $0.00768 |
| Sonnet 5 | $0.00006 | $0.00307 |
| Haiku 4.5 | $0.00003 | $0.00154 |
Grade A, and why
chinese-quotes-fix 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
python .claude/skills/chinese-quotes-fix/check_quotes.py "path/to/file.md"
批量检查：
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
python .claude/skills/chinese-quotes-fix/fix_quotes.py --dry-run "path/to/file.md"
3. 正式修复
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：
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）
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 135 lines · 32 tokens per session scan A 76293106d72f
chinese-quotes-fix is a skill published in the GitHub repository ranxi2001/zero2Agent (406 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 1,537 once invoked, about $0.0002 per session on Opus 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
advanced-dubbing-studio
Submit audio or video for multilingual dubbing, poll status, and download dubbed audio. Use when the user asks for dubbing, 多语言配音, 视频翻译配音, 译制片, or wants a source clip dubbed into another language.
dcf-model
DCF valuation: free cash flow projections, WACC, terminal value, sensitivity analysis.
interactive-dashboard
Interactive web dashboards: stock trackers, sector heatmaps, portfolio monitors — served via preview URL.
comps-analysis
Comparable company analysis: operating metrics, valuation multiples, peer benchmarking.
initiating-coverage
Full equity research initiation: company research, financial model, valuation, charts, 30-50 page report.
html-report
Self-contained styled HTML reports written to the task directory: PDF-exportable research documents with inline data, charts, and theme-aware CSS.