A local AI-powered workflow for extracting, translating, and summarizing academic PDF papers at zero cost.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pdf-processor
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 pdf-processor 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 PDF Processor?
PDF Processor is a specialized tool designed to streamline the consumption of academic literature by leveraging local Large Language Models (LLMs). As a key addition to the Openclaw Skills ecosystem, it handles the end-to-end lifecycle of a research paper, from raw text extraction to high-quality English-to-Chinese translation and concise summary generation.
By utilizing Ollama and the qwen2.5:7b model locally, this skill ensures that researchers and developers can process massive volumes of documents without incurring API fees or compromising data privacy. It is engineered for reliability, featuring sophisticated text-splitting logic and progress management to handle even the most complex technical documents.
PDF Processor Use Cases
- Translating dense English research papers into readable Chinese versions for faster comprehension.
- Batch processing academic archives to generate 200-character summaries for quick literature review.
- Organizing large PDF collections into structured directories with automated indexing and metadata extraction.
- Processing sensitive or proprietary documents locally to avoid uploading data to third-party cloud AI services.
How PDF Processor Works
- The system extracts text from the PDF page-by-page and saves it to a temporary processing directory.
- It identifies the document language and extracts the paper title, translating it if necessary.
- For English documents, the text is split into segments (approx. 2000-4000 characters) based on natural paragraph boundaries to maintain context.
- Each segment is sent to the local Ollama API for sequential translation with real-time progress tracking.
- The abstract and introduction are used to generate a punchy, 200-character Chinese summary highlighting core contributions.
- Files are automatically moved to final 'Completed' directories, and an index is updated for easy searching.
PDF Processor Setup
First, ensure you have the required Python libraries and Ollama installed with the correct model:
pip install pdfplumber requests
ollama pull qwen2.5:7b
To process a PDF, run the script with the input path and your desired output directory:
python3 scripts/process_pdf.py path/to/paper.pdf ~/Documents/AcademicLibrary
PDF Processor Data Schema & Taxonomy
The skill manages a structured directory to keep your research organized:
| Directory | File Type | Purpose |
|---|---|---|
/processed/original/ |
The original source file after processing. | |
/processed/translation/ |
.txt | Full translated text with metadata. |
/processed/summary/ |
.txt | 200-character summary and dual-language titles. |
/processing/ |
.json | Progress tracking files for resume capability. |
/index/ |
.md/.json | Searchable index of all processed literature. |
PDF Processor Advanced Features
- Local LLM Execution: Uses Ollama to run models locally, ensuring zero cost and high privacy for all Openclaw Skills users.
- Breakpoint Resume: Automatically saves translation progress to a JSON file, allowing the script to resume from the exact point of failure.
- Intelligent Text Splitting: Prioritizes paragraph boundaries and punctuation to ensure translation segments remain grammatically coherent.
- Real-time Progress Monitoring: Displays current segment status, percentage completion, and character counts during execution.
- Automated Indexing: Includes a secondary script to generate a searchable catalog of all processed papers based on their summaries.
SKILL.md
Loading
Related Openclaw Skills
Google & Meta Ads Spy Tool
An AI-powered competitive intelligence engine that scrapes, analyzes, and rebuilds winning ad creatives from any competitor.
Pretext Reporter
A high-performance text measurement and Canvas layout reporting tool supporting multi-language scripts, emojis, and bidirectional text.
Novel Outliner
Novel Outliner is a specialized tool that automatically deconstructs complex novel outlines into structured, per-chapter writing prompts for AI agents.
Monero CPU Mining Setup
A technical guide for securely deploying and optimizing XMRig for Monero mining on Windows, Linux, and macOS.
Anime Ebook Reader
A comprehensive AI assistant designed to read, manage, and summarize light novels and ebooks in multiple digital formats.
Feishu Project Open API
A robust integration for managing Feishu Project lifecycles, workflow templates, and automated progress analysis through the Feishu Project Open API.
Featured*
