A unified document conversion pipeline designed to batch process files between formats like PDF, Word, Markdown, and HTML using parallel execution.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install batch-convert
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 batch-convert 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 Batch Convert Skill?
The Batch Convert skill provides a high-performance framework for handling large-scale document transformations within an AI agent environment. By utilizing Openclaw Skills, users can automate the conversion of hundreds of files simultaneously while maintaining consistent settings and metadata accuracy. This skill is particularly valuable for developers and teams who need to bridge the gap between different document ecosystems, such as migrating legacy Office files to modern Markdown for AI ingestion or generating distribution-ready PDFs from technical documentation.
The system utilizes a robust backend powered by industry-standard tools like Pandoc, LibreOffice, and MarkItDown. This ensures that even complex layouts are handled with high fidelity during the conversion process. With built-in parallel processing and recursive directory scanning, it transforms manual, time-consuming file management into an efficient, programmatic workflow.
Batch Convert Skill Use Cases
- Converting legacy archives of PDF reports into editable DOCX or Markdown formats for content auditing.
- Batch transforming technical documentation from Markdown to HTML and PDF for product releases.
- Migrating spreadsheets (XLSX) and presentations (PPTX) into Markdown to facilitate LLM training and RAG pipelines.
- Consolidating folders of images or text-based notes into unified PDF documents for archiving.
How Batch Convert Skill Works
- The user specifies a source directory or a list of files to be processed using a simple prompt.
- The skill performs automatic format detection based on file extensions and MIME types to determine the appropriate conversion path.
- A multi-threaded pipeline is initialized, allocating workers to handle file conversions in parallel for maximum speed.
- The system executes specific sub-routines (e.g., LibreOffice for Office files or Pandoc for Markdown) to perform the transformation.
- Progress is tracked in real-time, and converted files are organized into a designated output directory.
- A final JSON report is generated to summarize the status of every file in the batch.
Batch Convert Skill Setup
To enable full functionality for this skill within Openclaw Skills, ensure the following dependencies are installed on your system:
# Install Python dependencies
pip install pdf2docx markitdown python-docx openpyxl
# Install Pandoc for Markdown transformations
# macOS: brew install pandoc | Ubuntu: apt install pandoc
# Install LibreOffice for headless Office conversions
# macOS: brew install libreoffice | Ubuntu: apt install libreoffice
# Install Marp CLI for slide generation
npm install -g @marp-team/marp-cli
Batch Convert Skill Data Schema & Taxonomy
The skill organizes data through a structured pipeline that tracks input and output states. Use the table below to understand the transformation mapping:
| Component | Details |
|---|---|
| Input Formats | MD, PDF, DOCX, XLSX, PPTX, HTML |
| Output Formats | PDF, DOCX, MD, HTML, PPTX |
| Processing Logic | Multi-threaded ThreadPoolExecutor with a default of 4 workers |
| Metadata Output | export_report.json containing success status and file paths for each conversion |
Batch Convert Skill Advanced Features
- Parallel Processing: Utilizes concurrent futures to handle multiple document conversions simultaneously, significantly reducing execution time.
- Recursive Discovery: Supports deep-nested directory traversal to find and convert files across entire project structures.
- Headless Office Support: Integrates with LibreOffice's headless mode to convert complex proprietary formats without a GUI.
- Automatic MIME Mapping: Uses advanced format detection to ensure the correct converter is used regardless of file extension accuracy.
- Error Resilience: Includes a robust error-handling logic that logs failures but continues processing the remaining batch items.
SKILL.md
Loading
Related Openclaw Skills
Applicant Screening
A sophisticated recruitment tool that automates the evaluation and scoring of job applications against specific role requirements.
AI Slides
A sophisticated AI skill that automates the end-to-end creation of structured, high-impact presentations using Marp markdown formatting.
qshell-copilot
A powerful AI-driven wrapper for the qshell CLI to manage Qiniu Cloud Storage through natural language commands.
Solana Portfolio Tracker
A specialized tool for managing Solana investment portfolios by tracking multi-wallet balances and asset valuations.
Batch Processor
Process hundreds of documents simultaneously using parallel execution, progress tracking, and resilient checkpointing logic.
Chat with PDF
An advanced AI skill for intelligent conversations, data extraction, and automated summarization of PDF documents.
Featured*
