word-proofreader

Word Proofreader

Correct typos in Word documents, polish the wording, unify the formatting, and record every text modification through Word Track Changes.

When to Use

• The user provides a .docx file that needs proofreading
• Requests "proofreading," "error correction," "polishing," "fixing typos," "checking spelling"
• Needs to unify the document formatting
• Needs tracked revision records

When NOT to Use

• Need to create a document from scratch → use word-formatter
• Need to generate charts and illustrations → use word-formatter
• Only need to read the document content without making modifications

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: Read the document

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

Output a JSON-format list of paragraphs, including the paragraph index, text, and style name.

Step 2: The user selects a processing mode

Use AskUserQuestion to ask:

Mode	Description
Error correction only	Correct only typos, spelling errors, and punctuation issues
Error correction + polishing	Error correction + optimizing word choice, adjusting sentence structure, improving readability
Comprehensive processing	Error correction + polishing + unified formatting (font and font size, line spacing and paragraph spacing, heading levels)

Step 3: Analyze paragraph by paragraph

Read the paragraph list output by extract and analyze each paragraph.

Analysis points:

Error correction (performed in all modes)

• Chinese typos (incorrect substitutions of homophones or similarly shaped characters)
• English spelling errors
• Punctuation (mixed Chinese and English punctuation, redundant/missing punctuation)
• Number and unit formats

Polishing (error correction + polishing and comprehensive processing modes)

• Condensing redundant expressions
• Replacing inappropriate word choices
• Sentence structure optimization (splitting overly long sentences, converting passive sentences to active sentences, etc.)
• Adding logical connectives
• Note: polishing should preserve the original style and tone, without excessive rewriting

Generate correction JSON and write it to a temporary file:

{
  "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"}
      ]
    }
  ]
}

Important: Output only paragraphs with modifications; do not include paragraphs that need no modification in the JSON.

Step 4: Apply corrections

After saving the correction JSON as a temporary file, execute:

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

--mode Parameters:

• typo_only - No formatting
• typo_polish - No formatting
• full - Formatting

Custom formatting parameters (optional):

--format /tmp/format_config.json

format_config.json example:

{
  "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: Output

The script will output modification statistics. Report to the user:

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

pip install python-docx

Error Handling

Error	Handling method
File does not exist	Prompt the user to check the path
Format not supported	Only .docx is supported
python-docx is not installed	Prompt pip install
Document encrypted/protected	Prompt the user to remove protection first