ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified data analysis Safety 4/5

extract

Extract content from specific URLs using Tavily's extraction API. Returns clean markdown/text from web pages. Use when you have specific URLs and need their content without writing code.

Why use this skill?

Use the OpenClaw extract skill to pull clean markdown and text from any URL using the Tavily API. Automate data retrieval for research and analysis tasks.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/barneyjm/extract
Or

What This Skill Does

The Extract skill for OpenClaw is a powerful utility designed to pull clean, structured content from web pages. By leveraging the Tavily API, it enables the agent to navigate to specific URLs and retrieve the text or markdown content immediately. This eliminates the need for complex web scraping scripts or manual browsing, providing a streamlined pathway to ingest information from documentation, articles, or dynamic websites directly into your AI workflow.

Installation

To use this skill, ensure you have an active account at Tavily. Once you have your API key, add it to your environment settings in ~/.claude/settings.json under the TAVILY_API_KEY field. Finally, install the skill into your OpenClaw environment using the command: clawhub install openclaw/skills/skills/barneyjm/extract.

Use Cases

This skill is perfect for researchers, developers, and content creators. Typical use cases include:

  • Aggregating data from multiple documentation pages to generate a summary.
  • Converting complex or JavaScript-heavy websites into clean, readable Markdown.
  • Automating the gathering of information from competitive analysis articles.
  • Extracting specific text from long-form content to feed into LLM analysis.

Example Prompts

  1. "Go to these three URLs [URL1], [URL2], and [URL3], extract the content, and give me a summary of their shared points regarding climate data."
  2. "Extract the documentation for the API found at [URL] using advanced depth, and output the result in clean markdown format."
  3. "Visit [URL] and extract the main technical specifications from the table, focusing on the latest model releases."

Tips & Limitations

  • Depth Matters: Use basic mode for standard static HTML pages as it is faster. Switch to advanced if the page relies heavily on JavaScript rendering or dynamic content loading.
  • Rate Limits: You are limited to extracting a maximum of 20 URLs per request. If you need more, batch your operations.
  • Query Focus: Using a query parameter helps the model prioritize the most relevant information within the extracted chunks, significantly improving the quality of the output.
  • Timeout Considerations: For larger pages or advanced JS rendering, increase your timeout to ensure the extraction completes successfully.

Metadata

Author@barneyjm
Stars1100
Views1
Updated2026-02-17
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-barneyjm-extract": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#scraping#web-extraction#tavily#research#automation
Safety Score: 4/5

Flags: network-access, external-api