Skip to content
Skills Library
Documents & office · Tool integration

Documents

/Documents

Document processing. USE WHEN document, process file. SkillSearch('documents') for docs.

Repository
pai ↗
Licence
MIT
Last repository change
09.06.2026

Assessment and security

95/ 100Class: good
Format20 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
39
Scripts
23
HTML comments
0
URLs in SKILL.md
1
Deprecation

No signals detected. Repository changed on 09.06.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What to check before installing
  • 23 scripts in this package. Review them before installing, as Claude may execute them.

Scripts: Docx/Ooxml/Scripts/pack.py, Docx/Ooxml/Scripts/unpack.py, Docx/Ooxml/Scripts/validate.py, Docx/Scripts/__init__.py, Docx/Scripts/document.py, Docx/Scripts/utilities.py, Pdf/Scripts/check_bounding_boxes.py, Pdf/Scripts/check_bounding_boxes_test.py

What it does and when to use it

Document processing. USE WHEN document, process file. SkillSearch('documents') for docs.

Triggers from the description

documents
Original author description

Document processing. USE WHEN document, process file. SkillSearch('documents') for docs.

How it works

  1. Customization
  2. 🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)
  3. 🎯 Load Full CORE Context
  4. When to Activate This Skill
  5. 🔀 Document Type Routing
  6. 📋 Document Processing Principles
  7. Examples
  8. 🔗 Integration with Other Skills
  9. 🎯 Key Principles
  10. 📚 Full Reference Documentation
Original SKILL.md headings · 295 lines, 1,468 words
SKILL.md preview
---
name: Documents
description: Document processing. USE WHEN document, process file. SkillSearch('documents') for docs.
---

## Customization

**Before executing, check for user customizations at:**
`~/.claude/skills/CORE/USER/SKILLCUSTOMIZATIONS/Documents/`

If this directory exists, load and apply any PREFERENCES.md, configurations, or resources found there. These override default behavior. If the directory does not exist, proceed with skill defaults.


## 🚨 MANDATORY: Voice Notification (REQUIRED BEFORE ANY ACTION)

**You MUST send this notification BEFORE doing anything else when this skill is invoked.**

1. **Send voice notification**:
   ```bash
   curl -s -X POST http://localhost:8888/notify \
     -H "Content-Type: application/json" \
     -d '{"message": "Running the WORKFLOWNAME workflow in the Documents skill to ACTION"}' \
     > /dev/null 2>&1 &
   ```

2. **Output text notification**:
   ```
   Running the **WorkflowName** workflow in the **Documents** skill to ACTION...
   ```

**This is not optional. Execute this curl command immediately upon skill invocation.**

# Documents Skill

## 🎯 Load Full CORE Context

**Before starting any task with this skill, load complete CORE context:**

`read ~/.claude/skills/CORE/SKILL.md`


## When to Activate This Skill

### Word Documents (DOCX)
- User wants to create, edit, or analyze Word documents
- User mentions "tracked changes", "redlining", "document review"
- User needs to convert documents to other formats
- User wants to work with document structure, comments, or formatting

### PDF Files
- User wants to create, merge, split, or manipulate PDFs
- User mentions "extract text from PDF", "PDF tables", "fill PDF form"
- User needs to convert PDFs to/from other formats
- User wants to add watermarks, passwords, or extract images

### PowerPoint Presentations (PPTX)
- User wants to create or edit presentations
- User mentions "slides", "presentation template", "speaker notes"
- User needs to convert presentations to other formats
- User wants to work with slide layouts or design elements

### Excel Spreadsheets (XLSX)
- User wants to create or edit spreadsheets
- User mentions "formulas", "financial model", "data analysis"
- User needs to work with Excel tables, charts, or pivot tables
- User wants to convert spreadsheets to/from other formats

## 🔀 Document Type Routing

This skill organizes document processing across 4 document types:

### Word Documents (DOCX)

**Reference Documentation:**
- `docx/SKILL.md` - Complete DOCX processing guide
- `docx/docx-js.md` - Creating new documents with JavaScript
- `docx/ooxml.md` - Editing existing documents with OOXML

**Routing Logic:**
- "Create Word document", "new docx" → Create workflow (docx-js)
- "Edit Word document", "tracked changes", "redlining" → Edit workflow (OOXML)
- "Read Word document", "extract text from docx" → Read workflow (pandoc)
- "Document review", "track changes" → Redlining workflow

**Supporting Resources:**
- Scripts: `~/.claude/skills/documents/docx/Scripts/`
- OOXML tools: `~/.claude/skills/documents/docx/ooxml/`
- License: `~/.claude/skills/documents/docx/LICENSE.txt`

**Key Capabilities:**
- Create professional documents with docx-js
- Edit with tracked changes (redlining workflow)
- Extract text/comments with pandoc
- Convert to images for visual inspection
- Work with raw OOXML for advanced features

### PDF Processing

**Reference Documentation:**
- `pdf/SKILL.md` - Complete PDF processing guide
- `pdf/forms.md` - Filling PDF forms
- `pdf/reference.md` - Advanced features and troubleshooting

**Routing Logic:**
- "Create PDF" → Creation workflow (reportlab)
- "Merge PDFs", "split PDF" → Manipulation workflow (pypdf)
- "Extract text from PDF" → Extraction workflow (pdfplumber)
- "Fill PDF form" → Forms workflow (pdf-lib or pypdf)
- "Extract tables from PDF" → Table extraction (pdfplumber + pandas)

**Supporting Resources:**
- Scripts: `~/.claude/skills/documents/pdf/Scripts/`
- License: `~/.claude/skills/documents/pdf/LICENSE.txt`

**Key Capabilities:**
- Create PDFs with reportlab
- Extract text/tables with pdfplumber
- Merge/split with pypdf or qpdf
- Fill forms programmatically
- Add watermarks and password protection
- Extract images from PDFs

### PowerPoint Presentations (PPTX)

**Reference Documentation:**
- `pptx/SKILL.md` - Complete PPTX processing guide
- `pptx/html2pptx.md` - Creating presentations from HTML
- `pptx/ooxml.md` - Editing existing presentations

**Routing Logic:**
- "Create presentation", "new slides" → Creation workflow (html2pptx)
- "Edit presentation", "modify slides" → Edit workflow (OOXML)
- "Use presentation template" → Template workflow
- "Extract slide text" → Read workflow (markitdown)
- "Create thumbnail grid" → Thumbnail workflow

**Supporting Resources:**
- Scripts: `~/.claude/skills/documents/pptx/Scripts/`
- OOXML tools: `~/.claude/skills/documents/pptx/ooxml/`
- License: `~/.claude/skills/documents/pptx/LICENSE.txt`

**Key Capabilities:**
- Create presentations with html2pptx (HTML → PPTX)
- Professional design with color palettes and layouts
- Edit with OOXML for advanced features
- Work with templates (rearrange, inventory, replace)
- Generate thumbnail grids for visual analysis
- Convert to images for inspection

### Excel Spreadsheets (XLSX)

**Reference Documentation:**
- `xlsx/SKILL.md` - Complete XLSX processing guide
- `xlsx/recalc.py` - Formula recalculation script

**Routing Logic:**
- "Create spreadsheet", "new Excel file" → Creation workflow (openpyxl)
- "Edit spreadsheet", "modify Excel" → Edit workflow (openpyxl)
- "Analyze data", "read Excel" → Analysis workflow (pandas)
- "Financial model", "formulas" → Financial modeling workflow
- "Recalculate formulas" → Recalculation workflow (recalc.py)

**Supporting Resources:**
- Recalc script: `~/.claude/skills/documents/xlsx/recalc.py`
- License: `~/.claude/skills/documents/xlsx/LICENSE.txt`

**Key Capabilities:**
- Create spreadsheets with formulas (openpyxl)
- Data analysis with pandas
- Financial modeling with color coding standards
- Formula recalculation with LibreOffice
- Error detection and validation
- Preserve formatting and formulas when editing

## 📋 Document Processing Principles

### DOCX Best Practices
1. **Tracked Changes** - Use redlining workflow for professional document review
2. **Minimal Edits** - Only mark text that actually changes, preserve original RSIDs
3. **Batch Changes** - Group related edits (3-10 changes) for efficient processing
4. **Verification** - Always convert to markdown to verify changes applied correctly

### PDF Best Practices
1. **Library Selection** - pypdf for basic ops, pdfplumber for text/tables, reportlab for creation
2. **OCR for Scanned** - Use pytesseract + pdf2image for scanned documents
3. **Form Filling** - Follow forms.md for programmatic form completion
4. **Command Line** - Use qpdf/pdftotext for simple operations

### PPTX Best Practices
1. **Design First** - Analyze content and choose appropriate colors/layouts before coding
2. **Web-Safe Fonts** - Only use web-safe fonts (Arial, Helvetica, Times, etc.)
3. **Visual Verification** - Always generate thumbnails to inspect layout issues
4. **Template Analysis** - Create inventory before using templates to understand structure

### XLSX Best Practices
1. **Use Formulas** - ALWAYS use Excel formulas, NEVER hardcode calculated values
2. **Zero Errors** - Deliver with zero formula errors (#REF!, #DIV/0!, etc.)
3. **Recalculate** - Run recalc.py after creating/editing to update formula values
4. **Financial Standards** - Follow color coding (blue inputs, black formulas, green links)

## Examples

**Example 1: Create proposal with tracked changes**
```
User: "Create a consulting proposal doc with redlining"
→ Routes to DOCX workflows
→ Creates document with docx-js
→ Enables tracked changes for review workflow
→ Outputs professional .docx with revision marks
```

**Example 2: Fill a PDF form programmatically**
```
User: "Fill out this NDA PDF with my info"
→ Routes to PDF workflows
→ Reads form fields from PDF
→ Fills fields programmatically with pdf-lib
→ Outputs completed, flattened PDF
```

**Example 3: Build financial model spreadsheet**
```
User: "Create a revenue projection spreadsheet"
→ Routes to XLSX workflows
→ Creates workbook with openpyxl
→ Adds formulas (never hardcoded values)
→ Runs recalc.py to update calculations
```

## 🔗 Integration with Other Skills

### Feeds Into:
- **writing** skill - Creating documents for blog posts and newsletters
- **business** skill - Creating consulting proposals and financial models
- **research** skill - Extracting data from research documents

### Uses:
- **media** skill - Creating images for document illustrations
- **development** skill - Building document processing automation
- **system** skill - Command-line tools and scripting

## 🎯 Key Principles

### Document Creation
1. **Quality First** - Professional formatting and structure from the start
2. **Template Reuse** - Leverage existing templates when available
3. **Validation** - Always verify output (visual inspection, error checking)
4. **Automation** - Use scripts for repetitive tasks

### Document Editing
1. **Preserve Intent** - Maintain original formatting and structure
2. **Track Changes** - Use proper workflows for document review
3. **Batch Processing** - Group related operations for efficiency
4. **Error Prevention** - Validate before finalizing

### Document Analysis
1. **Right Tool** - Choose appropriate library/tool for the task
2. **Data Integrity** - Preserve original data when extracting/converting
3. **Format Awareness** - Understand document structure (OOXML, PDF structure, etc.)
4. **Performance** - Use efficient methods for large documents

## 📚 Full Reference Documentation

**Word Documents (DOCX):**
- Main Guide: `~/.claude/skills/documents/docx/SKILL.md`
- Creation Reference: `~/.claude/skills/documents/docx/docx-js.md`
- Editing Reference: `~/.claude/skills/documents/docx/ooxml.md`

**PDF Processing:**
- Main Guide: `~/.claude/skills/documents/pdf/SKILL.md`
- Forms Guide: `~/.claude/skills/documents/pdf/forms.md`
- Advanced Reference: `~/.claude/skills/documents/pdf/reference.md`

**PowerPoint Presentations (PPTX):**
- Main Guide: `~/.claude/skills/documents/pptx/SKILL.md`
- Creation Reference: `~/.claude/skills/documents/pptx/html2pptx.md`
- Editing Reference: `~/.claude/skills/documents/pptx/ooxml.md`

**Excel Spreadsheets (XLSX):**
- Main Guide: `~/.claude/skills/documents/xlsx/SKILL.md`
- Recalc Script: `~/.claude/skills/documents/xlsx/recalc.py`

---

## Summary

**The documents skill provides comprehensive document processing:**

- **DOCX** - Create, edit, analyze Word documents with tracked changes support
- **PDF** - Create, manipulate, extract from PDFs with form filling capabilities
- **PPTX** - Create, edit presentations with professional design and templates
- **XLSX** - Create, edit spreadsheets with formulas and financial modeling

**Reference-based organization** - Each document type has complete guides and tooling

**Routing is automatic** - Analyzes user intent and activates appropriate document type workflow

**Professional quality** - Standards and best practices for production-ready documents
Files in this package (39)
  • SKILL.md 11 KB
  • Docx/LICENSE.txt 1 KB
  • Docx/SKILL.md 12 KB
  • Docx/docx-js.md 16 KB
  • Docx/ooxml.md 23 KB
  • Docx/Ooxml/Scripts/pack.py 5 KB
  • Docx/Ooxml/Scripts/unpack.py 1 KB
  • Docx/Ooxml/Scripts/validate.py 2 KB
  • Docx/Scripts/__init__.py 1 KB
  • Docx/Scripts/document.py 49 KB
  • Docx/Scripts/utilities.py 13 KB
  • Pdf/LICENSE.txt 1 KB
  • Pdf/SKILL.md 11 KB
  • Pdf/forms.md 9 KB
  • Pdf/reference.md 16 KB
  • Pdf/Scripts/check_bounding_boxes.py 3 KB
  • Pdf/Scripts/check_bounding_boxes_test.py 9 KB
  • Pdf/Scripts/check_fillable_fields.py 1 KB
  • Pdf/Scripts/convert_pdf_to_images.py 1 KB
  • Pdf/Scripts/create_validation_image.py 2 KB
  • Pdf/Scripts/extract_form_field_info.py 6 KB
  • Pdf/Scripts/fill_fillable_fields.py 5 KB
  • Pdf/Scripts/fill_pdf_form_with_annotations.py 4 KB
  • Pptx/LICENSE.txt 1 KB
  • Pptx/SKILL.md 28 KB
  • Pptx/html2pptx.md 19 KB
  • Pptx/ooxml.md 10 KB
  • Pptx/Ooxml/Scripts/pack.py 5 KB
  • Pptx/Ooxml/Scripts/unpack.py 1 KB
  • Pptx/Ooxml/Scripts/validate.py 2 KB
  • Pptx/Scripts/html2pptx.js 37 KB
  • Pptx/Scripts/inventory.py 37 KB
  • Pptx/Scripts/rearrange.py 8 KB
  • Pptx/Scripts/replace.py 13 KB
  • Pptx/Scripts/thumbnail.py 15 KB
  • Workflows/ProcessLargePdfGemini3.md 18 KB
  • Xlsx/LICENSE.txt 1 KB
  • Xlsx/SKILL.md 13 KB
  • Xlsx/recalc.py 6 KB

Versions

RepositoryScoreLicence
This page · virtualian/pai95MIT
magnus919/agent-skills100MIT
astrbotdevs/astrbot100AGPL-3.0
BasemTarekkamal/orbit100MIT
asgeirtj/system_prompts_leaks100CC0-1.0
vincentwei1021/synapse100AGPL-3.0
virtualian/pai95MIT
virtualian/pai95MIT
virtualian/pai95MIT

Database snapshot: 13.11.2026 · package version 832e51627ff1 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 95Docx
    Word document processing. USE WHEN docx, Word document. SkillSearch('docx') for docs.
  • 91Pdf
    PDF processing. USE WHEN pdf, PDF file. SkillSearch('pdf') for docs.
  • 95document-processing
    Create, edit, and analyze office documents (PDF, DOCX, PPTX, XLSX). Use when working with PDFs, Word documents, PowerPoint presentations, or Excel spreadsheets. Covers text extraction, form filling, document creation, and data analysis.
  • 100document-processing
    This skill should be used when the user says \"process documents\", \"extract text from PDF\", \"OCR this document\", \"convert PDF to markdown\", \"extract emails from documents\", \"parse document\", \"document conversion\", \"batch OCR\", \"extract structured data from PDF\",…
  • 100document-processing-expert
    Read, generate and modify office documents and PDFs from code: PDF extraction and forms, Word documents, Excel workbooks and PowerPoint decks. Use when the user mentions PDF, DOCX, XLSX, PPTX, Word, Excel, PowerPoint or spreadsheets, wants data extracted from documents, needs a…
  • 90document-processor
    Guidance for processing documents, extracting content, and transforming structured information. Use when the user asks to process, parse, extract, or transform document content such as PDFs, Word files, or spreadsheets.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.