HTML to Markdown

Convert HTML to Markdown using MinerU. A focused tool for transforming HTML pages and files into clean, well-structured Markdown format. Features: HTML to Ma...

Security Scan

The skill's requirements and runtime instructions match its stated purpose (a CLI wrapper around MinerU for converting HTML to Markdown); nothing requested appears disproportionate or unrelated.

Purpose & Capability

Name/description (HTML → Markdown) aligns with required binary (mineru-open-api) and the single required env var (MINERU_TOKEN). The declared install methods (npm or go) correspond to the mineru CLI referenced in the docs.

Instruction Scope

SKILL.md only instructs the agent to run the mineru-open-api CLI against URLs or local HTML files and to set MINERU_TOKEN; it does not ask the agent to read unrelated system files, other environment variables, or exfiltrate data to unexpected endpoints. Local file access is within the stated purpose (converting local HTML).

Install Mechanism

Installs are via npm (mineru-open-api) or go install from a GitHub repo (opendatalab). These are standard package sources and appropriate for a CLI tool, but global npm/go installs execute third-party code on the host—review the package/repo if you need to be cautious.

Credentials

Only MINERU_TOKEN is required and is the primary credential; this is proportional because the CLI communicates with the MinerU service. No unrelated credentials or config paths are requested.

Persistence & Privilege

always is false, and the skill is user-invocable with normal autonomous-invocation allowed. The skill does not request system-wide persistence or modification of other skills' configs.

Assessment

This skill appears to do exactly what it says: it calls the MinerU CLI to convert HTML to Markdown and requires a MinerU token. Before installing, verify the mineru-open-api npm package and the GitHub repo (opendatalab/MinerU-Ecosystem) to ensure you trust the publisher. Be aware that a global npm or go install runs third‑party code on your machine—if you're cautious, install in an isolated environment (container/VM) or inspect the repo first. Treat your MINERU_TOKEN like any API secret: create it on the MinerU site, grant only necessary permissions, avoid exposing it in shared shells/scripts, and rotate it if needed. If you expect to convert highly sensitive local HTML, confirm MinerU's handling of uploaded content (privacy/retention) before using the remote crawl/extract features.

Convert HTML files or web page URLs to clean Markdown using MinerU. Removes navigation, ads, and clutter — keeps the readable content.

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

# Convert a web page URL to Markdown (requires token)
mineru-open-api crawl https://example.com/article -o ./out/

# Convert a local HTML file to Markdown (requires token)
mineru-open-api extract page.html -o ./out/

# Output to stdout (requires token)
mineru-open-api crawl https://example.com/article

Authentication

Token required:

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

• Input: remote web page URL or local .html file
• Output: Markdown
• For remote URLs: use crawl (token required)
• For local HTML files: use extract (token required)
• HTML is NOT supported by flash-extract

Notes

• Always requires token (no flash-extract support for HTML)
• 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