A high-performance document digitizer that uses multimodal vision to convert multilingual PDFs and complex layouts into perfectly structured Markdown.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install universal-pdf-vision-parse
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 universal-pdf-vision-parse 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 Universal PDF Vision Parser?
The Universal PDF Vision Parser is a high-end multilingual document digitizer designed to overcome the limitations of traditional OCR. By leveraging the Qwen-VL-Max multimodal vision model, this tool sees each page as a high-resolution image, allowing it to accurately capture hand-written notes, complex tables, and diverse languages like French, German, Japanese, and Spanish. It is a powerful addition to the ecosystem of Openclaw Skills for users who need high-readability markdown from visual-heavy documents.
This skill is particularly effective for digitizing academic notes, bilingual textbooks, and documents where structural integrity is just as important as text accuracy. By treating pages as visual data rather than simple character streams, it ensures that the semantic relationship between terms and their translations is preserved.
Universal PDF Vision Parser Use Cases
- Digitizing multilingual language learning notes with complex annotations.
- Converting legacy PDF documents with non-standard layouts into clean, searchable Markdown.
- Processing bilingual documents where standard OCR fails to maintain semantic structure.
- Extracting content from technical documents containing both images and text for knowledge management.
How Universal PDF Vision Parser Works
- Visual Scanning: The skill converts each PDF page into a high-resolution 300 DPI PNG image to ensure maximum clarity.
- Expert Transcription: Using the Qwen-VL-Max model, the system identifies specific languages and transcribes text, translations, and technical explanations.
- Markdown Structuring: The extracted content is automatically formatted with bold keywords, italicized meanings, and clean tables for immediate use in notes or documentation.
Universal PDF Vision Parser Setup
To utilize this powerful entry in the Openclaw Skills collection, you must first obtain a DashScope API Key with access to the qwen-vl-max model.
Install the necessary Python environment dependencies:
pip install pymupdf dashscope
Execute the parsing script via the command line:
python scripts/vision_parse.py --pdf <path_to_pdf> --out <path_to_output.md> --api-key <YOUR_API_KEY> --max-pages 2
Universal PDF Vision Parser Data Schema & Taxonomy
The skill produces a structured Markdown file that mirrors the visual hierarchy of the source PDF. The data is organized as follows:
| Feature | Output Format |
|---|---|
| Document Structure | Standard Markdown headings (#, ##) |
| Emphasis | Text styling using bold and italics for key terms |
| Tabular Data | Github Flavored Markdown (GFM) tables |
| Image Processing | Temporary 300 DPI PNG intermediates (auto-managed) |
Universal PDF Vision Parser Advanced Features
- Multimodal vision-based extraction powered by the advanced Qwen-VL-Max model.
- Automatic language identification supporting Latin, CJK, and other complex character sets.
- High-resolution rendering at 300 DPI for superior text extraction from small or dense fonts.
- Flexible page range controls allowing for targeted extraction or full-document processing.
- Seamless integration with agentic workflows for automated document management within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Platform Health Check
A diagnostic tool to monitor the connectivity, latency, and authentication status of over 20 agent platform APIs.
SkillGuard
SkillGuard is a specialized security tool designed to audit Openclaw Skills for malicious code, prompt injections, and data exfiltration threats.
Content Automator
A high-performance automation pipeline for generating faceless YouTube content using AI scripts, ElevenLabs TTS, and ffmpeg assembly.
chrome-open-tabs
A powerful utility to read and list open browser tabs from Chromium-based browsers, including support for synced mobile and desktop devices.
Vue Table Automation and Excel Export
A specialized automation skill for navigating vue-element-admin tables, updating record importance, and generating Excel reports.
WSB Digest
An automated tool to track trending WallStreetBets stocks and deliver insightful daily reports directly to Discord.
Featured*
