A comprehensive PDF extraction tool designed for academic researchers to parse papers into structured text, images, and data tables.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install paper-reader
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 paper-reader 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 Paper Reader?
Paper Reader is a robust academic research utility integrated within the Openclaw Skills library. It is specifically designed to handle the complexities of scientific publications, enabling users to programmatically extract structured content including hierarchical sections, experimental data, and visual assets. By transforming static PDF documents into a machine-readable format, it empowers AI agents and researchers to perform deeper analysis and literature reviews more efficiently.
The skill leverages powerful Python libraries to ensure high-fidelity extraction of figures, charts, and mathematical contexts. Whether you are building a personal knowledge base or automating data collection for a meta-analysis, this tool provides the necessary infrastructure to manage scholarly content at scale within the Openclaw Skills framework.
Paper Reader Use Cases
- Automated literature review and summarization for academic projects.
- Extracting experimental results and performance metrics for data meta-analysis.
- Harvesting figures and charts for presentations or training multimodal AI models.
- Converting bibliography sections into structured BibTeX formats for citation management.
- Parsing complex technical methods, loss functions, and network architectures from deep learning papers.
How Paper Reader Works
- The user initiates the process by providing a PDF file through the command line or via the Python API.
- The skill analyzes the document metadata to identify core information like title, authors, and keywords.
- It performs a structural scan of the document to recognize standard academic sections such as Introduction, Methods, and Results.
- Based on the specified configuration flags, the skill extracts text, high-resolution figures, and tabular data.
- The extracted assets are organized into a logical directory structure, making the data ready for use by other Openclaw Skills or external tools.
Paper Reader Setup
To get started with this skill, first install the required Python dependencies:
pip install pdfplumber pymupdf Pillow
You can then run the extraction script directly from your Openclaw Skills directory. For a full extraction of a research paper, use the following command:
python3 ~/.openclaw/skills/paper-reader/read_paper.py paper.pdf --full
Paper Reader Data Schema & Taxonomy
The skill organizes extracted data into a structured output folder named after the paper:
| Component | File/Path | Description |
|---|---|---|
| Full Text | paper.txt |
The complete text content of the PDF. |
| Metadata | metadata.json |
JSON file containing title, authors, abstract, and keywords. |
| Sections | sections/*.txt |
Individual text files for each identified chapter or section. |
| Visuals | figures/*.png |
All extracted images, charts, and figures. |
| Tables | tables/*.csv |
Tabular data converted into structured CSV format. |
Paper Reader Advanced Features
- Multi-modal extraction support for capturing both textual and visual context simultaneously.
- Batch processing mode for handling entire directories of research papers in a single run.
- Intelligent section identification that maps unstructured text to standard academic hierarchies.
- Automated extraction of technical hyperparameters and loss functions from the Methods section.
- Reference management support with automated BibTeX export capabilities.
SKILL.md
Loading
Related Openclaw Skills
Classical Chinese Poetry AI Skill
A comprehensive AI-driven tool for generating authentic classical Chinese poetry and searching an extensive corpus of historical literary works.
AI Intelligent Budget Management
An AI-driven financial framework for multi-dimensional budget preparation, real-time execution tracking, and predictive variance analysis.
Twitch
A local command-line utility for tracking Twitch channel data, scores, and leaderboards without a GUI.
frompdf
A robust PDF extraction API that transforms documents into structured, LLM-ready content including semantic AST, Markdown, and tables without page limits.
ClawJobs
ClawJobs is a collaboration plugin for OpenClaw that enables multiple agent peers to share tasks and synchronize status through a centralized hub.
Newsticker (claw://News)
A specialized newsdesk skill connecting OpenClaw agents to German-language AI, security, and ecosystem updates from ClawNews.de.
Featured*
