A comprehensive automation toolkit for reading, writing, and converting Microsoft Office and PDF files through a streamlined CLI and Python API.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install office-toolkit
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install office-toolkit using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Office Toolkit?
The office-toolkit is a versatile suite of tools designed to bridge the gap between AI coding agents and standard document formats. As a key component of the Openclaw Skills ecosystem, it provides developers and automated agents with the ability to programmatically interact with Word (DOCX), PowerPoint (PPTX), and Excel (XLSX) files, as well as PDFs.
Built on top of industry-standard libraries like python-docx, openpyxl, and pymupdf, this skill ensures high-fidelity document processing. Whether you need to extract data from a complex spreadsheet, generate a stylized report, or convert a presentation into a PDF for distribution, office-toolkit offers a unified interface to handle these tasks efficiently within your automation workflows.
Office Toolkit Use Cases
- Automated generation of project reports in DOCX format with custom styles and tables.
- Extracting text and data from PDF or PowerPoint presentations for AI analysis.
- Converting legacy Office documents into PDF format for secure sharing.
- Programmatic creation of Excel spreadsheets with formulas and data visualization from JSON sources.
- Batch processing document updates and format conversions in CI/CD pipelines.
How Office Toolkit Works
- The user or AI agent triggers a specific script (e.g., docx-read.py) or imports the Python API to target a document file.
- The toolkit identifies the file format and utilizes the relevant underlying engine (python-docx, openpyxl, etc.) to parse or generate content.
- For conversions, the toolkit processes the source file and renders it into the target format (like DOCX to PDF).
- Data is outputted to the local filesystem or returned as structured JSON for further programmatic use within the Openclaw Skills environment.
Office Toolkit Setup
To integrate this skill into your environment, install it via clawhub or use pip to manage dependencies:
# Install via clawhub
clawhub install office-toolkit
# Install all Python dependencies
pip install -r requirements/all.txt
You can also install specific modules if you only need support for certain formats, such as pip install -r requirements/docx.txt for Word support.
Office Toolkit Data Schema & Taxonomy
The office-toolkit skill organizes its operations through a structured directory and clear CLI inputs:
| Component | Description |
|---|---|
scripts/ |
Contains specialized CLI tools for each format (read, write, convert). |
lib/ |
Core logic and shared utilities for document validation and processing. |
requirements/ |
Modular dependency files (base, docx, pptx, xlsx, pdf). |
Read operations can output raw text or structured JSON data, while write operations accept arguments for titles, content, and data paths.
Office Toolkit Advanced Features
- Multi-format conversion support including DOCX to PDF and PPTX to PDF.
- JSON output capability for read operations to facilitate seamless data handoffs between agents.
- Support for complex document elements like tables, formulas, and slide shapes.
- Modular dependency management allowing for a lightweight footprint by installing only required format handlers.
- Comprehensive validation layers to ensure document integrity during write operations.
SKILL.md
Loading
Related Openclaw Skills
Game Deals
A PC gaming discount aggregator that tracks prices across 30+ major digital storefronts using the CheapShark API.
TrafficEye License Plate Reader
A high-performance ANPR and OCR tool for detecting and reading the largest license plate from local images via the TrafficEye API.
Research Summarizer
A professional-grade research agent that converts complex documents into structured, cited, and comparative analytical briefs.
Paper Summary Skill
An automated research assistant designed to extract core insights from academic papers, technical reports, and PDFs.
OpenClaw CoE (Chain of Execution)
A native execution chain skill that provides real-time, step-by-step visibility into how OpenClaw processes complex tasks.
GitHub Repo Quickstart
A developer-first skill designed to distill complex GitHub repositories into actionable, low-friction onboarding guides.
Featured*
