HTML Analysis for Openclaw

A document intelligence skill powered by MinerU for transforming complex HTML files into structured, hierarchical Markdown content.

mzlzyca
v0.4.0
Apr 3, 2026
0
796
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install html-analysis

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install html-analysis using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is HTML Analysis?

The html-analysis skill is a specialized tool for developers and researchers who need to parse local or remote HTML documents without losing structural integrity. By utilizing the MinerU engine from OpenDataLab, this skill excels at identifying content sections, headings, tables, and lists within a web page, converting them into clean Markdown while preserving the original layout logic.

Unlike basic scrapers, this Openclaw Skills integration focuses on document intelligence. It allows AI agents to effectively read and understand web page layouts, making it an essential utility for content auditing, SEO analysis, and feeding high-quality structured data into LLM workflows.

HTML Analysis Use Cases

  • Extracting structured data from local HTML documentation for RAG pipelines.
  • Analyzing the heading hierarchy and content layout of existing web pages for SEO audits.
  • Converting legacy HTML content into clean, readable Markdown for CMS migrations.
  • Enabling AI agents to interpret complex web structures and data tables accurately.

How HTML Analysis Works

  1. The user provides a local path to an HTML file or a URL to a remote document.
  2. The skill triggers the MinerU extract command, utilizing the authenticated API token.
  3. MinerU parses the HTML tags to identify semantic blocks such as headers, lists, and tabular data.
  4. The document intelligence engine processes the layout to ensure the reading order and hierarchy are maintained.
  5. The skill outputs the final structured Markdown to the specified directory or stdout for agent consumption.

HTML Analysis Setup

First, install the necessary CLI tool globally via npm or Go:


HTML Analysis Data Schema & Taxonomy

The skill organizes extracted data to maximize readability and machine-parsing efficiency:

Component Format Description
Content Markdown Preserved headings, bold/italic text, and links
Tables GFM Tables Standardized Markdown table syntax for data extraction
Metadata YAML/JSON Layout information and document hierarchy data
Output File/Stdout Supports direct file saving with the -o flag

HTML Analysis Advanced Features

  • Multi-language support using the --language flag (e.g., English, Chinese).
  • Full web crawling capabilities via the crawl command for JavaScript-rendered pages.
  • Deep structural analysis that identifies semantic sections rather than just raw tags.
  • Seamless integration with Openclaw Skills workflows for multi-agent document processing.
  • Support for remote URL extraction directly into local processing pipelines.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Requires
Bins mineru-open-api
Github Stars: 0
forks: 0

Featured*