Word Proofreader logo

Word Proofreader

Community
didixuxu
word-proofreader

Use when user has a Word document that needs typo correction, text polishing, or proofreading. Triggers on requests to fix typos, correct errors, polish writing, proofread, or when user says "校对", "纠错", "润色", "改错别字", "检查错别字".

Overview

Publisherdidixuxu
Repositorydidi-skills
Skill nameword-proofreader
Stars
86
Forks
8
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by didixuxu on GitHub. Read the source before you install it.

Installation

Install the Word Proofreader AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/didixuxu/didi-skills/tree/main/word-proofreader
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/didixuxu/didi-skills.git /tmp/didi-skills
mkdir -p .claude/skills
cp -r /tmp/didi-skills/word-proofreader .claude/skills/word-proofreader
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Word Proofreader in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Word Proofreader on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Word Proofreader is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Word Proofreader

纠正 Word 文档中的错别字、润色文字表达、统一排版格式,并通过 Word 修订模式(Track Changes)记录每处文字修改。

When to Use

  • 用户提供 .docx 文件需要校对
  • 请求"校对"、"纠错"、"润色"、"改错别字"、"检查拼写"
  • 需要统一文档排版格式
  • 需要修订追踪记录

When NOT to Use

  • 需要从零创建文档 → 用 word-formatter
  • 需要生成图表和配图 → 用 word-formatter
  • 只需读取文档内容不做修改

Workflow

1. 读取文档 → 2. 选择模式 → 3. 逐段分析 → 4. 应用修正(Track Changes) → 5. 输出

Step 1: 读取文档

bash
python ~/.claude/skills/word-proofreader/proofreader.py extract "/path/to/document.docx"

输出 JSON 格式的段落列表,包含段落索引、文本和样式名。

Step 2: 用户选择处理模式

使用 AskUserQuestion 询问:

模式说明
仅纠错只修正错别字、拼写错误、标点符号问题
纠错+润色纠错 + 优化用词、调整句式、提升可读性
全面处理纠错 + 润色 + 统一排版(字体字号、行距段距、标题层级)

Step 3: 逐段分析

读取 extract 输出的段落列表,对每个段落进行分析。

分析要点:

纠错(所有模式都执行)

  • 中文错别字(同音字、形近字替换错误)
  • 英文拼写错误
  • 标点符号(中英文标点混用、多余/缺失标点)
  • 数字和单位格式

润色(纠错+润色 和 全面处理 模式)

  • 冗余表达精简
  • 用词不当替换
  • 句式优化(过长句子拆分、被动句转主动句等)
  • 逻辑连接词补充
  • 注意:润色要保持原文风格和语气,不过度改写

生成修正 JSON,写入临时文件:

json
{
  "paragraphs": [
    {
      "index": 0,
      "original": "这个方案的目地是为了提高工作效率,使的我们能够更加好的完成任务。",
      "corrected": "这个方案的目的是提高工作效率,使我们能够更好地完成任务。",
      "changes": [
        {"type": "typo", "from": "目地", "to": "目的"},
        {"type": "typo", "from": "使的", "to": "使"},
        {"type": "polish", "from": "为了提高", "to": "提高"},
        {"type": "polish", "from": "更加好的", "to": "更好地"}
      ]
    }
  ]
}

重要: 只输出有修改的段落,无需修改的段落不要包含在 JSON 中。

Step 4: 应用修正

将修正 JSON 保存为临时文件后执行:

bash
python ~/.claude/skills/word-proofreader/proofreader.py apply \
  "/path/to/document.docx" \
  "/tmp/corrections.json" \
  --output "/path/to/document_proofread.docx" \
  --mode full

--mode 参数:

  • typo_only - 不排版
  • typo_polish - 不排版
  • full - 排版

自定义排版参数(可选):

bash
--format /tmp/format_config.json

format_config.json 示例:

json
{
  "body_font_cn": "SimSun",
  "body_font_en": "Times New Roman",
  "body_size": 12,
  "heading1_size": 22,
  "heading2_size": 16,
  "heading3_size": 14,
  "line_spacing": 1.5,
  "space_after": 6
}

Step 5: 输出

脚本会输出修改统计。向用户报告:

完成!
- 输出文件:/path/to/document_proofread.docx
- 修改段落:X / Y
- 错别字修正:N 处
- 润色优化:M 处

请用 Word 打开文件,在「审阅」→「修订」中查看每处修改,可逐条接受或拒绝。

Dependencies

bash
pip install python-docx

Error Handling

错误处理方式
文件不存在提示用户检查路径
格式不支持仅支持 .docx
python-docx 未安装提示 pip install
文档加密/受保护提示用户先解除保护

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Word Proofreader AI skill do?

Use when user has a Word document that needs typo correction, text polishing, or proofreading. Triggers on requests to fix typos, correct errors, polish writing, proofread, or when user says "校对", "纠错", "润色", "改错别字", "检查错别字".

Why use Word Proofreader on TypingMind?

Because you install it once and use it with any model. Word Proofreader is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Word Proofreader in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/didixuxu/didi-skills/tree/main/word-proofreader. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Word Proofreader?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Word Proofreader?

As many as you like. As long as a model supports skills, you can use Word Proofreader with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Word Proofreader AI skill free?

It is published on GitHub by didixuxu. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇