pdf-to-latex-mineru

Convert PDF documents to LaTeX source code using MinerU AI extraction. Designed for researchers, academics, and scientists who need to re-edit, re-typeset, o...

Security Scan

The skill's requirements and runtime instructions match its stated purpose (calling the mineru-open-api CLI with a MINERU_TOKEN to convert PDFs to LaTeX); there are no unexpected binaries, credentials, or install sources requested.

Purpose & Capability

Name/description (PDF→LaTeX) align with required binary (mineru-open-api) and required env var (MINERU_TOKEN). The declared install options (npm package and Go repo) are appropriate for a CLI integration.

Instruction Scope

SKILL.md only instructs using the mineru-open-api CLI and the MINERU_TOKEN, and references local files or URLs (e.g., arXiv). This is within scope, but the workflow implies sending PDFs to an external MinerU service/API for extraction — users should be aware their document contents will be uploaded/processed remotely.

Install Mechanism

Installers are standard package mechanisms (npm and go install from a GitHub repo). No opaque download URLs, extract operations, or custom installers are present.

Credentials

Only a single service credential (MINERU_TOKEN) is required and declared as the primary credential, consistent with the documented auth flow. No unrelated secrets or config paths are requested.

Persistence & Privilege

Skill is not configured always:true and does not request system-wide config changes. Autonomous invocation is enabled by default (normal); nothing else indicates elevated or persistent privileges.

Assessment

This skill appears coherent, but review these practical points before installing: 1) mineru-open-api will upload documents to MinerU (mineru.net) — do not send private/confidential PDFs unless you trust the service and token permissions; 2) verify the npm package and GitHub repo identities (package name and repo owner) before running install commands to avoid typosquatting; 3) MINERU_TOKEN grants access to the MinerU API—treat it like a secret and rotate or restrict it as needed; 4) if you need offline conversion or a privacy-preserving workflow, look for a local-only tool instead. If you want higher assurance, provide the exact npm package and GitHub repo checksums or URLs for manual review.

PDF to LaTeX

Convert PDF documents to LaTeX format using MinerU. Best suited for academic papers and documents with formulas or complex layouts.

Install

npm install -g mineru-open-api
go install github.com/opendatalab/MinerU-Ecosystem/cli/mineru-open-api@latest

Quick Start

mineru-open-api extract paper.pdf -f latex -o ./out/
mineru-open-api extract paper.pdf -f latex --model vlm -o ./out/
mineru-open-api extract https://arxiv.org/pdf/2309.10918 -f latex -o ./out/

Authentication

Token required:

mineru-open-api auth
export MINERU_TOKEN="your-token"

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

Capabilities

• Supported input: .pdf (local file or URL)
• Output format: LaTeX (-f latex)
• LaTeX output requires extract with token
• Use --model vlm for papers with complex math, tables, or multi-column layouts
• Language hint with --language (default: ch, use en for English)

Notes

• LaTeX output is only available via extract with token
• --model vlm gives higher accuracy; use pipeline for guaranteed fidelity
• Output goes to stdout by default; use -o <dir> to save to a file
• MinerU is open-source by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU