PDF to Markdown - Extract Text, Tables, Formulas from PDF

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 instructions are internally consistent for a PDF→Markdown CLI wrapper, but it sends uploaded PDFs to an external MinerU API (no auth) so you should consider privacy and package provenance before installing.

Purpose & Capability

The skill is a PDF→Markdown converter and declares/uses a single CLI binary (mineru-open-api) and CLI commands that match that purpose. The install options (npm/uv/go) and referenced repo align with the MinerU project named in the README.

Instruction Scope

SKILL.md's runtime instructions are narrow and restricted to invoking mineru-open-api on local files or URLs. However, the instructions explicitly send documents to an external MinerU API (mineru.net). That is coherent with the described capability but has privacy implications: any PDF you convert is uploaded to a remote service.

Install Mechanism

Installation is via standard package ecosystems (npm, uv, go install) which is reasonable for a CLI. This is moderate-risk compared to an arbitrary download because packages come from registries and a GitHub path is provided; you should still verify the package source, version, and code before installing.

Credentials

The skill requests no environment variables, credentials, or config paths. That is proportionate to the stated functionality. The lack of auth is consistent with the claim that small files require no API key, but means uploads are unauthenticated.

Persistence & Privilege

The skill does not request persistent/always-on privileges, does not modify other skills, and has no special system path requirements. It installs a single CLI binary into the environment, which is expected behavior.

Assessment

This skill appears to do what it claims (call the mineru-open-api CLI to convert PDFs to Markdown), but it uploads the PDFs to an external MinerU API without authentication. Before installing or using it: 1) Do not send sensitive or confidential PDFs unless you trust mineru.net and understand its retention/privacy policy. 2) Verify the mineru-open-api package source (npm/uv) or the GitHub repo referenced in the SKILL.md to ensure you install the official CLI and not a malicious package. 3) If you need offline/local processing for privacy, prefer local extraction tools instead. 4) Test with non-sensitive sample documents first, and inspect the installed binary (or its source) if you require higher assurance.

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

Quick Start

# Convert a local PDF to Markdown
mineru-open-api flash-extract report.pdf

# Convert a PDF from URL (no download needed)
mineru-open-api flash-extract https://cdn-mineru.openxlab.org.cn/demo/example.pdf

# Save to file
mineru-open-api flash-extract report.pdf -o ./output/

# Convert specific pages
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