Office Toolkit

A comprehensive toolkit for Microsoft Office documents (Word, Excel, PowerPoint) and PDF files. Supports reading, writing, format conversion, and batch proce...

Security Scan

The skill's code, instructions, and declared requirements are consistent with an Office/PDF processing toolkit and nothing in the package indicates covert behavior or unrelated privileges.

Purpose & Capability

Name/description, required binary (python3), listed pip packages, and the included scripts all match the stated Office/PDF processing purpose. The dependency lists (python-docx, python-pptx, openpyxl, pymupdf) and CLI scripts directly relate to reading/writing/converting documents.

Instruction Scope

SKILL.md and the CLI scripts only instruct/implement reading, writing and format conversion of user-supplied documents. They do not attempt to read unrelated system files, environment variables, or contact external endpoints. Error messages and examples are consistent with the stated functionality.

Install Mechanism

There is no formal install spec in the registry, but SKILL.md/README instruct the user to pip install requirements/*.txt; the code files are included in the package. Dependencies are standard PyPI packages (no external URL downloads or archive extracts). This is reasonable but note the package expects the operator to install Python packages (use a venv).

Credentials

The skill requests no environment variables or credentials. The scripts do not read env vars or config paths. Dependency and runtime requirements are proportional to the functionality.

Persistence & Privilege

Skill is not always-enabled, is user-invocable, and does not request elevated/persistent privileges or modify other skills or system-wide config. Autonomous invocation is allowed (platform default) but not combined with other red flags.

Assessment

This package appears coherent and implements the advertised document processing features. Before installing: (1) install dependencies in an isolated virtualenv, (2) review and run the scripts on non-sensitive sample files first, (3) be cautious converting DOCX→PDF if you install/use docx2pdf because that conversion uses Microsoft Word/LibreOffice and could trigger document macros/behaviour on your system, and (4) verify the package source/owner if you require provenance — the registry metadata shows an unknown owner and no homepage. If you plan to run it in automated agents, restrict the agent's file access to only the directories you trust.

Comprehensive document processing toolkit for Office and PDF files.

ClawHub: https://clawhub.ai/weiwei2027/office-toolkit Install: clawhub install office-toolkit

Supported Formats

Format	Read	Write	Convert From	Convert To
DOCX	✅	✅	-	PDF
PPTX	✅	✅	-	PDF
XLSX	✅	✅	-	-
PDF	✅	✅ (from DOCX/PPTX)	DOCX, PPTX	-

Quick Start

Read Documents

# Word
docx-read.py document.docx

# PowerPoint
pptx-read.py presentation.pptx

# Excel
xlsx-read.py spreadsheet.xlsx

# PDF
pdf-read.py document.pdf

Create Documents

# Word with content
docx-write.py output.docx --title "Report" --content "Hello World"

# PowerPoint with slides
pptx-write.py output.pptx --title "Presentation" --slides 5

# Excel with data
xlsx-write.py output.xlsx --sheet "Data" --data data.json

Convert Formats

# DOCX to PDF
convert.py document.docx --to pdf

# PPTX to PDF
convert.py presentation.pptx --to pdf

Installation

# Install all dependencies
pip install -r requirements/all.txt

# Or install only what you need
pip install -r requirements/docx.txt   # Word only
pip install -r requirements/pptx.txt   # PowerPoint only
pip install -r requirements/xlsx.txt   # Excel only
pip install -r requirements/pdf.txt    # PDF only

Directory Structure

office-toolkit/
├── SKILL.md                    # This file
├── requirements/               # Dependency files
│   ├── base.txt               # Core dependencies
│   ├── docx.txt               # python-docx
│   ├── pptx.txt               # python-pptx
│   ├── xlsx.txt               # openpyxl
│   └── pdf.txt                # pymupdf
├── scripts/                    # CLI tools
│   ├── docx-read.py
│   ├── docx-write.py
│   ├── pptx-read.py
│   ├── pptx-write.py
│   ├── xlsx-read.py
│   ├── xlsx-write.py
│   ├── pdf-read.py
│   ├── pdf-write.py
│   └── convert.py
├── lib/                        # Shared library
│   ├── __init__.py
│   ├── base.py                # Base classes
│   ├── utils.py               # Utilities
│   └── validators.py          # Input validation
└── tests/                      # Test suite
    ├── test_docx.py
    ├── test_pptx.py
    ├── test_xlsx.py
    └── test_pdf.py

Python API Usage

from lib.base import DocumentProcessor

# Process Word document
processor = DocumentProcessor('docx')
text = processor.read('document.docx')
processor.write('output.docx', content="New content")

# Convert format
processor.convert('document.docx', 'pdf')

Notes

• DOCX: Uses python-docx library. Supports text, tables, styles, images.
• PPTX: Uses python-pptx library. Supports slides, text, shapes, charts.
• XLSX: Uses openpyxl library. Supports cells, formulas, charts, styling.
• PDF: Uses pymupdf (fitz) for reading, reportlab for creation.

Roadmap

• Excel support (xlsx read/write) - ✅ Added in v1.0.1
• PDF creation from scratch
• Format conversion improvements
• Batch processing
• Template system

Changelog

v1.0.1 (2026-03-20)

• Added Excel (.xlsx) read/write support
• Improved error handling with helpful messages
• Added JSON output option for read operations
• Added PDF page selection support

v1.0.0 (2026-03-20)

• Initial release
• DOCX/PPTX/PDF read and write support