Docx Analysis

Analyze the structure and content of .docx (Word) files using MinerU. Returns structured Markdown preserving headings, tables, lists, and layout for content...

Security Scan

The skill is internally consistent: it wraps the MinerU CLI, asks only for the MinerU token and the mineru-open-api binary it needs, and its instructions align with the stated purpose.

Purpose & Capability

Name/description, required binary (mineru-open-api), install instructions (npm/go), and required env var (MINERU_TOKEN) all align with a MinerU-based .docx analysis tool.

Instruction Scope

SKILL.md only instructs running mineru-open-api commands against local files or URLs and setting MINERU_TOKEN for full extraction. It does not instruct reading unrelated files or extra env vars. One caveat: the docs imply a remote service (token, token creation page) so documents may be uploaded to mineru.net during extraction — the SKILL.md does not explicitly state whether processing is local or cloud-based.

Install Mechanism

Install uses npm package name mineru-open-api or a Go module path to GitHub; both are normal package install mechanisms and create the expected binary. No arbitrary URL downloads or archive extraction are used.

Credentials

Only MINERU_TOKEN is required and declared as the primary credential, which is proportionate for a CLI that can use a cloud API; no unrelated secrets or config paths are requested.

Persistence & Privilege

Skill is not always-enabled and does not request persistent or cross-skill configuration changes; autonomous invocation is allowed by default (normal).

Assessment

This skill appears to be a thin wrapper for the MinerU CLI and is internally consistent. Before installing: verify the mineru-open-api package source (npm package page or the GitHub repo linked in SKILL.md), and review what the CLI does (whether it uploads files to mineru.net). Treat MINERU_TOKEN as sensitive: only provide it if you trust the MinerU service, and test the tool first with non-sensitive documents. If you need strictly local processing, confirm the CLI can run fully offline for your use cases (flash-extract may be limited).

Analyze the structure and content of Word (.docx) files using MinerU. Returns structured Markdown with headings, tables, and layout preserved.

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

# Quick analysis (no token required)
mineru-open-api flash-extract report.docx

# Save to directory
mineru-open-api flash-extract report.docx -o ./out/

# Full analysis with tables and formulas (requires token)
mineru-open-api extract report.docx -o ./out/

# With language hint
mineru-open-api flash-extract report.docx --language en

Authentication

No token needed for flash-extract. Token required for extract:

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

• Supported input: .docx (local file or URL)
• flash-extract: no token, max 10 MB / 20 pages, Markdown output
• extract: token required, full features (tables, formulas, multi-format output)
• Language hint with --language (default: ch, use en for English)
• Page range with --pages (e.g. 1-10)

Notes

• For .doc (legacy format), use doc-analysis skill instead
• Output goes to stdout by default; use -o <dir> to save to a file or directory
• All progress/status messages go to stderr; document content goes to stdout
• MinerU is open-source by OpenDataLab (Shanghai AI Lab): https://github.com/opendatalab/MinerU