Office Document Editor

Professional document editing for any DOCX/PPTX file from any source.

Quick Reference

| Task | Approach | |------|----------| | Fetch file from upload | bash scripts/fetch_file.sh upload | | Fetch file from URL | bash scripts/fetch_file.sh https://example.com/file.docx | | Fetch file from SFTP | bash scripts/fetch_file.sh sftp://user@host:/path/file.docx | | Edit DOCX | uv run python scripts/docx_editor.py input.docx output.docx edits.json | | Edit PPTX | uv run python scripts/pptx_editor.py input.pptx output.pptx edits.json | | Generate diff | uv run python scripts/generate_diff.py old.docx new.docx diff.md | | Interactive mode | bash scripts/interactive_edit.sh |

---

File Sources

Uploaded Files (Chat Attachments)

# Get latest uploaded DOCX
bash scripts/fetch_file.sh upload output.docx

# Get latest uploaded PPTX
bash scripts/fetch_file.sh upload output.pptx

Location: ~/.openclaw/workspace/media/inbound/file_*.docx

Local Filesystem Paths

# Copy from local path
bash scripts/fetch_file.sh ~/Documents/report.docx output.docx

# Or direct path
bash scripts/fetch_file.sh /absolute/path/file.pptx output.pptx

Public URLs

# Download from URL
bash scripts/fetch_file.sh https://example.com/document.docx output.docx

SFTP/SSH Remote Files

# Fetch via SFTP
bash scripts/fetch_file.sh sftp://user@host:/path/file.docx output.docx

---

Creating Edit Rules

Create edits.json with your editing instructions:

{
  "description": "Edit description",
  "replacements": [
    {
      "search": "old text",
      "replace": "new text",
      "style": "highlight"
    }
  ],
  "additions": [
    {
      "after": "after this text",
      "text": "add this text",
      "style": "highlight"
    }
  ],
  "slides": [
    {
      "action": "rearrange",
      "order": [0, 2, 1, 3]
    }
  ]
}

Supported Styles

1. replace - Direct replacement
2. highlight - Yellow highlight
3. delete - Strikethrough
4. bold - Bold text
5. underline - Underline

Slide Actions (PPTX only)

1. rearrange - Change slide order
2. add - Add new slide
3. remove - Delete slide

---

Editing Documents

Edit DOCX

uv run python scripts/docx_editor.py input.docx output.docx edits.json

Features:

1. Paragraph text editing
2. Table cell editing
3. Format preservation
4. Multiple replacements
5. Text additions

Edit PPTX

uv run python scripts/pptx_editor.py input.pptx output.pptx edits.json

Features:

1. Slide text replacement
2. Slide rearrangement
3. Add/remove slides
4. Format preservation

Generate Diff Report

uv run python scripts/generate_diff.py input.docx output.docx diff-report.md

Output: Standard Unified Diff format in Markdown.

---

Complete Workflow

Step 1: Fetch File

# From upload
bash scripts/fetch_file.sh upload input.docx

# From URL
bash scripts/fetch_file.sh https://example.com/file.docx input.docx

# From local path
bash scripts/fetch_file.sh ~/Documents/file.docx input.docx

Step 2: Create Edit Rules

{
  "description": "IRB Review Response",
  "replacements": [
    {
      "search": "2026 年 2 月 28 日",
      "replace": "2026 年 8 月 31 日",
      "style": "highlight"
    }
  ]
}

Step 3: Execute Edit

uv run python scripts/docx_editor.py input.docx output.docx edits.json

Step 4: Generate Reports

# Unified Diff
uv run python scripts/generate_diff.py input.docx output.docx diff.md

# Convert to Markdown
uv run markitdown output.docx > output.md

Step 5: Version Control

git add *.docx *.md diff.md
git commit -m "Edit: Description of changes"

---

Interactive Mode

For guided editing:

bash scripts/interactive_edit.sh

This will prompt you through:

1. File source selection
2. Edit type selection
3. Details collection
4. Output location

---

Examples

Example 1: Text Replacement with Highlight

{
  "replacements": [
    {
      "search": "February 28, 2026",
      "replace": "August 31, 2026",
      "style": "highlight"
    }
  ]
}

Example 2: Add Text After Question

{
  "additions": [
    {
      "after": "What is the research topic?",
      "text": "[ANSWER] Data Structures and Algorithms",
      "style": "highlight"
    }
  ]
}

Example 3: Rearrange Slides

{
  "slides": [
    {
      "action": "rearrange",
      "order": [0, 2, 1, 3, 4]
    }
  ]
}

---

Notes

Format Preservation

1. ✅ Text, paragraphs, tables: Fully preserved
2. ✅ Highlights, strikethrough, bold: Supported
3. ⚠️ Complex styles (custom themes): May be lost
4. ❌ Images, charts: Manual handling required

Table Text Replacement

python-docx requires exact match (including spaces, punctuation, newlines) for table text.

Solutions:

1. Use shorter search strings
2. Use markitdown to preview table content first
3. Use exact match in JSON

Git Best Practices

1. Use local Git repo (do not upload to GitHub)
2. Add sensitive files to .gitignore
3. Backup to secure location regularly

---

Dependencies

1. uv: Package management and virtual environment
2. python-docx: DOCX editing
3. python-pptx: PPTX editing
4. mammoth: DOCX to Markdown conversion
5. markitdown: Universal document conversion
6. curl: URL downloads
7. sftp: SFTP file transfers (optional)

Installation

cd ~/.openclaw/workspace/skills/office-document-editor
uv sync

---

Troubleshooting

"No replacements made"

Cause: Text doesn't match exactly

Solution:

# Preview content
uv run markitdown input.docx

# Use exact text from preview

"Virtual environment not found"

Solution:

cd ~/.openclaw/workspace/skills/office-document-editor
uv sync

"File not found"

Solutions:

1. Check file path is correct
2. Try uploading the file again
3. Verify URL is accessible
4. Check SFTP credentials

---

Scripts Reference

fetch_file.sh

Universal file fetcher for all source types.

bash scripts/fetch_file.sh <source> [output_filename]

Sources:

1. upload - Latest uploaded file
2. /path/to/file - Local path
3. https://... - Public URL
4. sftp://... - SFTP remote

docx_editor.py

Edit Word documents with formatting.

uv run python scripts/docx_editor.py input.docx output.docx edits.json

pptx_editor.py

Edit PowerPoint presentations.

uv run python scripts/pptx_editor.py input.pptx output.pptx edits.json

generate_diff.py

Generate Unified Diff reports.

uv run python scripts/generate_diff.py old.docx new.docx diff.md

interactive_edit.sh

Interactive guided editing.

bash scripts/interactive_edit.sh

workflow_complete.sh

Complete automated workflow.

bash scripts/workflow_complete.sh input.docx edits.json