Table Ocr

OCR and extract tables from scanned PDFs and images using MinerU. Recognizes table structures in image-based documents and converts them to structured Markdo...

Security Scan

The skill's requirements, instructions, and install steps align with its stated purpose (using the MinerU CLI and a MinerU API token to OCR and extract tables); nothing requested appears disproportionate.

Purpose & Capability

Name/description request OCR table extraction via MinerU; required binary (mineru-open-api) and the MINERU_TOKEN credential directly match that purpose and are expected.

Instruction Scope

SKILL.md only instructs the agent to run the MinerU CLI (extract, auth) against user-provided files or URLs and to set MINERU_TOKEN. It does not instruct reading unrelated system files or other environment variables.

Install Mechanism

Install options are standard: npm package and a go install from a GitHub repo. Both are typical for distributing a CLI; no arbitrary downloads or extract-from-unknown-URL steps are present.

Credentials

Only MINERU_TOKEN is required and is declared as the primary credential. That is proportional for a CLI that authenticates to a remote MinerU service.

Persistence & Privilege

Skill is not always-enabled and does not request system-wide persistence or access to other skills' configs. Autonomous invocation is allowed (platform default) but not combined with other concerning privileges.

Assessment

This skill appears coherent, but before installing: verify you trust mineru.net and the npm/GitHub packages (review package source if possible), because installing a global CLI runs third-party code on your system. The MINERU_TOKEN permits the MinerU service to process your files — avoid uploading sensitive documents unless you trust the service and its privacy policy. Use a limited/revocable token, rotate it if needed, and prefer running the CLI locally on non-sensitive data if you cannot confirm the provider's practices.

Convert and extract content from .pdf / images (.png/.jpg/.jpeg/.webp) 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 tables from PDF (requires token)
mineru-open-api extract report.pdf -o ./out/

# With explicit table flag and OCR for scanned docs
mineru-open-api extract scanned.pdf --ocr --table -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 / images (.png/.jpg/.jpeg/.webp)
• Language hint with --language (default: ch, use en for English)
• Page range with --pages (where applicable)

Notes

• Table recognition requires extract with token. Use --ocr for scanned content and --table for table detection (both enabled by default in extract).
• 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