Academic Reader

PDF to Markdown converter - extract text, tables and formulas from PDF files to clean Markdown. Use when converting PDF documents, extracting PDF content, pa...

Security Scan

The skill's requirements and runtime instructions match its stated purpose (a CLI-backed PDF→Markdown converter that uploads documents to MinerU's API); the main risk is privacy of uploaded PDFs and the usual caution when installing third-party CLI packages.

Purpose & Capability

The name/description (PDF to Markdown converter) aligns with the declared binary (mineru-open-api) and the SKILL.md examples (mineru-open-api flash-extract). Required binaries and install methods are consistent with the stated purpose.

Instruction Scope

SKILL.md instructs using the mineru-open-api CLI to send local files or URLs to the MinerU service for extraction. It does not direct the agent to read unrelated files, environment variables, or system configuration. The documented data flow explicitly sends the document to mineru.net, which is consistent with a cloud-based extraction tool.

Install Mechanism

Installers are npm / uv / go package installs for a CLI named mineru-open-api. Using public package managers is typical but does involve executing third-party code on the host. No direct-download URLs or obscure hosts are used in the install spec, which lowers but does not eliminate install risk.

Credentials

The skill requests no environment variables, credentials, or config paths. That is proportional for a tool that claims 'no API key required.' The only sensitive action is uploading user-provided PDFs to an external API, which is justified by the stated functionality but has privacy implications.

Persistence & Privilege

always:false and no config paths or cross-skill config modifications are requested. The skill does not request permanent presence or elevated platform privileges beyond installing/using its CLI binary.

Assessment

This skill appears to do what it says, but it uploads documents to the MinerU API (mineru.net) for processing. Before installing or using it, avoid sending sensitive or confidential PDFs; verify the mineru-open-api package source (npm page and the GitHub repo referenced), inspect package contents or source code if possible, and install/run it in a controlled environment (or sandbox) if you have privacy concerns. Check the CLI's version, publisher, and checksum, and prefer an on-device extractor if you cannot accept external upload of your documents.

Academic Reader - Scientific Paper Parser

Convert PDF files to clean Markdown using MinerU Open API. No API key required.

Quick Start

# Academic Reader - Scientific Paper Parser
mineru-open-api flash-extract report.pdf

# Academic Reader - Scientific Paper Parser
mineru-open-api flash-extract https://cdn-mineru.openxlab.org.cn/demo/example.pdf

# Academic Reader - Scientific Paper Parser
mineru-open-api flash-extract report.pdf -o ./output/

# Academic Reader - Scientific Paper Parser
mineru-open-api flash-extract report.pdf --pages 1-10

Language Rule

You MUST reply to the user in the SAME language they use. This is non-negotiable.

Capabilities

• Extracts text, tables, and formulas from PDF
• Supports both local files and URLs directly
• Page range selection with --pages
• Language hint with --language (default: ch, use en for English)
• No API key, no signup, no authentication
• Max 10MB / 20 pages per document

When to Use

• User asks to "read", "extract", "convert", or "parse" a PDF
• User shares a PDF file or PDF link and asks for its content
• User wants to summarize or analyze a PDF document
• User needs PDF content in Markdown format

CLI Reference

Run mineru-open-api flash-extract --help for all available options.

Data Flow

flash-extract sends the document to the MinerU API (mineru.net) for processing and returns Markdown. This is a stateless API call — no account, no persistent storage. MinerU is an open-source project by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU

Notes

• Output is Markdown only; images/tables/formulas may be replaced with placeholders
• For larger files (up to 200MB/600 pages) or precision extraction with full assets, use mineru-open-api extract (requires auth via mineru-open-api auth)
• If the CLI cannot be installed via npm/uv/go, download it from https://mineru.net/ecosystem?tab=cli