Markdown Extract

What This Skill Does

The Markdown Extract skill by aviclaw is a powerful utility designed to bridge the gap between unstructured web content and actionable data. At its core, it leverages the markdown.new API to transform cluttered, advertisement-heavy, or layout-complex web pages into clean, structured Markdown. This process strips away unnecessary HTML tags, navigation bars, and footer clutter, leaving only the readable content. It is an essential tool for AI agents that need to consume web-based information, such as research articles, documentation pages, or blog posts, to synthesize knowledge or perform analytical tasks.

Installation

To integrate this skill into your OpenClaw environment, execute the following command in your terminal or command-line interface:

clawhub install openclaw/skills/skills/aviclaw/markdown-extract

Ensure that you have the latest version of the OpenClaw agent installed and that your API connectivity settings are configured to allow requests to the markdown.new service.

Use Cases

This skill is ideal for several professional scenarios:

1. Research Synthesis: Quickly convert long-form web articles into Markdown for ingestion into local LLMs or note-taking apps like Obsidian.
2. Documentation Ingestion: Automate the process of converting fragmented online documentation into a single, clean file format for easier reference.
3. Content Aggregation: Collect text from various sources into a unified Markdown repository without worrying about divergent HTML structures.
4. Accessibility: Transform complex or inaccessible web layouts into simplified, readable text content for improved clarity.

Example Prompts

1. "!markdown-extract https://docs.python.org/3/library/functions.html"
2. "!markdown-extract https://techcrunch.com/2023/10/25/latest-ai-update/ ai"
3. "!markdown-extract https://complex-js-rendered-site.com browser"

Tips & Limitations

The auto method is the default and should be your primary choice for speed and efficiency. Use the ai method when dealing with content that requires intelligent parsing or filtering. Reserve the browser method for websites that rely heavily on JavaScript for content generation, as it involves a headless browser rendering process that is significantly slower and resource-intensive. Always verify the resulting Markdown, as complex CSS grid or flexbox layouts might occasionally cause minor reordering of text elements during the conversion process.