x-extract

What This Skill Does

The x-extract skill enables the OpenClaw AI agent to seamlessly navigate and parse content from X (formerly Twitter) without the need for personal credentials. By leveraging OpenClaw’s built-in browser automation capabilities, the skill visits the provided URL, renders the page, and extracts essential components including the tweet author, primary text, timestamps, engagement metrics, and embedded media. It transforms raw, complex HTML into a structured, human-readable markdown format, making it ideal for researchers, content curators, and casual users who want to save or reference tweet content reliably.

Installation

You can integrate this skill into your local OpenClaw environment by running the following command in your terminal: clawhub install openclaw/skills/skills/chunhualiao/x-extract Ensure you have browser automation dependencies configured as per the core OpenClaw documentation to ensure the snapshot and rendering features function correctly.

Use Cases

• Content Archiving: Automatically save significant tweets, threads, or news updates into your local notes or knowledge base in markdown format.
• Data Collection: Gather engagement metrics and text content from viral threads to analyze trends without manual copy-pasting.
• Offline Reference: Extract media content and thread text to view them later when not connected to the internet, or to avoid the cluttered X interface.
• Workflow Automation: Build pipelines where an AI agent monitors specific discussions and reports back summaries of the latest tweets.

Example Prompts

1. "Extract the content from this tweet and let me know how many likes it has: https://x.com/username/status/123456789"
2. "Download the media from this thread and save the text to a file: https://x.com/official_handle/status/987654321 --download-media"
3. "Get the full text and author details for this tweet link: https://twitter.com/news_source/status/555555555"

Tips & Limitations

To ensure consistent performance, keep in mind that this tool relies on non-authenticated browser access. Because X (formerly Twitter) frequently updates its DOM structure, the extraction logic may occasionally break; if this happens, ensure your skill is up-to-date by checking the source repository. Note that protected tweets, age-restricted content, or content behind a login wall cannot be accessed. For high-volume extraction, be mindful of X’s rate-limiting policies, which may temporarily block IP addresses. If you encounter issues with specific links, try swapping the URL prefix between 'x.com' and 'twitter.com' to trigger different routing behaviors.