A CLI tool that automates the search, download, and high-fidelity parsing of arXiv academic papers into AI-friendly Markdown.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install paper-parser-skill
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-parser-skill 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 Parser Skill?
The paper-parser-skill is a specialized utility designed to bridge the gap between academic research and AI consumption. It automates the entire lifecycle of document acquisition, from searching the arXiv database to downloading PDFs and converting them into structured, layout-aware Markdown using the MinerU API. As part of the growing ecosystem of Openclaw Skills, this tool ensures that researchers and developers can easily ingest the latest scientific literature into their local knowledge bases or AI agents.
By leveraging advanced layout analysis, the skill transforms complex PDFs—complete with tables, images, and formulas—into a format that LLMs can process with high accuracy. It emphasizes local data control, storing all search results and documents in a user-defined workspace while utilizing secure, external parsing for structural conversion.
Paper Parser Skill Use Cases
- Automating the creation of RAG (Retrieval-Augmented Generation) datasets from academic literature.
- Conducting systematic literature reviews by batch searching and downloading papers based on specific research queries.
- Building AI-powered research assistants that can autonomously retrieve and interpret the latest arXiv submissions.
- Converting legacy PDF research libraries into clean, machine-readable Markdown for long-term knowledge management.
How Paper Parser Skill Works
- The user performs a keyword search via the CLI to identify relevant papers and their unique arXiv IDs.
- The skill downloads the PDF and extracts initial metadata, such as titles and summaries, into the local workspace.
- A parsing request is submitted to the MinerU API, which performs deep layout analysis on the document.
- Through an asynchronous workflow, the skill monitors the conversion status to avoid timeouts during intensive processing.
- Once complete, the tool automatically downloads and organizes the parsed Markdown files and extracted images into structured directories.
Paper Parser Skill Setup
To install the skill, use the following command:
pip install paper-parser-skill==v0.1.3
After installation, configure your MinerU API token in ~/.paper-parser/config.yaml to enable the parsing features:
PAPER_WORKSPACE: "~/paper-parser-workspace"
MINERU_API_TOKEN: "your_token_here"
MINERU_API_BASE_URL: "https://mineru.net/api/v4"
Paper Parser Skill Data Schema & Taxonomy
The skill organizes research data into a structured hierarchy within the defined workspace:
| Path | Component | Description |
|---|---|---|
<arxiv_id>/paper.pdf |
Source Document | The original PDF downloaded from arXiv. |
<arxiv_id>/title.md |
Metadata | The extracted title of the academic paper. |
<arxiv_id>/summary.md |
Abstract | The paper's summary or abstract in Markdown. |
<arxiv_id>/.parse_task.json |
State File | Tracking metadata for the asynchronous parsing task. |
<arxiv_id>/markdowns/ |
Parsed Content | The final converted Markdown files and associated images directory. |
Paper Parser Skill Advanced Features
- Asynchronous Workflow: Supports non-blocking
submitandcheckcommands, making it ideal for integration with autonomous agents. - Idempotent Operations: Built-in checks prevent redundant PDF uploads and minimize API consumption costs.
- Comprehensive Parsing: Beyond simple text extraction, it utilizes layout analysis to preserve the structure of complex academic documents.
- Local Workspace Management: Provides dedicated CLI commands to retrieve local paths, facilitating easy integration with other Openclaw Skills and pipelines.
SKILL.md
Loading
Related Openclaw Skills
emotion-switch
A sophisticated control layer that allows users to explicitly set and maintain a persistent emotional background for AI agents during long-form conversations.
NanoGPT Training
An advanced toolkit for training 124M parameter GPT models efficiently on a single GPU using modern optimization and architecture techniques.
Supapost
Supapost is an end-to-end AI content studio for creating consistent AI influencers, generating cinematic video, and automating social media distribution.
Modal GPU Training
A serverless cloud infrastructure skill for executing Python-based machine learning training jobs on high-performance GPUs like the A100 and T4.
gstack
A multi-role framework that transforms your AI agent into a structured engineering team including specialized roles for product, engineering, and security.
xx - Xpert Xchange
A specialized platform designed for the seamless exchange of expertise, knowledge, and skills between domain experts.
Featured*
