Extract Formulas From Pdf

Extract mathematical formulas and equations from PDF documents using MinerU. Identifies and converts formula content from academic papers, textbooks, and tec...

Security Scan

The skill is internally consistent: it wraps the MinerU CLI to extract formulas from PDFs, requires the MinerU binary and a MINERU_TOKEN, and the install and instructions match that purpose.

Purpose & Capability

Name/description, required binary (mineru-open-api), and required env var (MINERU_TOKEN) all align with a MinerU-based PDF formula extraction tool. Nothing requested is unrelated to the stated purpose.

Instruction Scope

SKILL.md only instructs using the mineru-open-api CLI (extract/auth), exporting MINERU_TOKEN, and CLI flags. It does not ask the agent to read unrelated files, other environment variables, or modify system configuration.

Install Mechanism

Install uses npm (mineru-open-api) or go install from the GitHub repo — both are common and expected for a CLI. Recommend verifying the npm package and GitHub repo are the official MinerU releases before installing globally.

Credentials

Only MINERU_TOKEN is required and is the primary credential — this is proportionate. However, the token grants access to the MinerU service and the CLI likely uploads PDF content to that service for processing, so treat the token and any uploaded documents as sensitive.

Persistence & Privilege

Skill does not request always:true, does not require system config paths, and is not installing any persistent agent-wide configuration. Autonomous invocation is allowed (platform default) but not a special privilege here.

Assessment

This skill appears to do what it says: it calls the mineru-open-api CLI and requires a MINERU_TOKEN. Before installing, verify the npm package and the GitHub repo are the official MinerU sources, and prefer installing in a sandboxed environment if you are unsure. Understand that using the service will likely upload PDF contents to MinerU's servers — avoid sending confidential documents unless you trust the vendor and have reviewed their privacy/security policy. Keep the MINERU_TOKEN secret, revoke it if compromised, and consider limiting global installs (use a local or containerized install) and pinning to a specific release.

Convert and extract content from .pdf using MinerU (mineru-open-api).

Install

npm install -g mineru-open-api
# or via Go (macOS/Linux):
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Quick Start

# Extract formulas from PDF (requires token)
mineru-open-api extract paper.pdf -o ./out/

# With VLM for better formula accuracy
mineru-open-api extract paper.pdf --model vlm -o ./out/

Authentication

Token required for extract and crawl:

mineru-open-api auth            # Interactive token setup
export MINERU_TOKEN="your-token" # Or via environment variable

Create token at: https://mineru.net/apiManage/token

Capabilities

• Supports local files and URLs
• Requires token (mineru-open-api auth or MINERU_TOKEN env)
• Supported input: .pdf
• Language hint with --language (default: ch, use en for English)
• Page range with --pages (where applicable)

Notes

• Formula recognition requires extract with token. Use --formula flag (enabled by default). Output is Markdown with LaTeX inline.
• Output goes to stdout by default; use -o <dir> to save to file
• Binary formats (docx) require -o flag (cannot stream to stdout)
• All progress/status messages go to stderr
• MinerU is an open-source project by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU