browser-read-x
Extract the main X/Twitter post or article content from a page that is already open in the browser (using browser act evaluate).
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bill492/browser-read-xWhat This Skill Does
The browser-read-x skill is a specialized, targeted extraction utility designed for the OpenClaw AI agent to parse content from X (formerly Twitter). Unlike generic web scrapers that often capture overwhelming amounts of UI noise—such as navigation sidebars, trending hashtags, login prompts, and engagement metrics—browser-read-x is specifically engineered to target the core content of a tweet or X article. It performs a DOM-level evaluation to isolate the primary status body, ensuring the extracted output is clean, readable, and structured, effectively transforming complex X layouts into a streamlined markdown format.
Installation
To integrate this skill into your OpenClaw environment, use the CLI provided by the platform. Execute the following command in your terminal:
clawhub install openclaw/skills/skills/bill492/browser-read-x
This command pulls the source directly from the openclaw/skills repository, automatically handling the dependency chain and preparing the JavaScript evaluation function for immediate use by your agent.
Use Cases
This skill is indispensable in several common automation scenarios:
- Content Aggregation: Automate the collection of threads or long-form posts from researchers or news outlets on X without needing to bypass aggressive rate-limiting on third-party APIs.
- Agent Research: When an agent navigates to a URL as part of a research workflow, it may encounter a gated view. By utilizing the browser session, the agent avoids re-authenticating repeatedly, using browser-read-x to ingest the page content already present in the DOM.
- Data Cleaning: Ideal for developers building training datasets who need text-only representations of posts, stripped of irrelevant visual clutter.
Example Prompts
- "Open https://x.com/official_account/status/123456789 and use browser-read-x to summarize the main argument in the post."
- "I have an X thread open in my active browser tab. Please run browser-read-x and save the extracted text to my knowledge base."
- "Navigate to this Twitter profile link, find the pinned post, and use browser-read-x to extract the content for me."
Tips & Limitations
- Contextual Reliability: Since this skill relies on
browser act evaluate, it requires the target page to be fully loaded and rendered. If the content is behind a dynamic "Show more" button, ensure your agent performs a click interaction first. - Fallback Logic: If the script fails to identify a specific X status container, it defaults to a general-purpose article extraction. This ensures that even on non-X pages, you still receive a cleaned-up text extraction, making it highly robust for general web browsing.
- Performance: For high-volume scraping, always implement pauses to avoid triggering platform-side rate limits.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-bill492-browser-read-x": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: code-execution
Related Skills
skill-audit
Audit all installed skills for quality, duplicates, structural issues, and best-practice compliance. Use when asked to review, audit, lint, or check skills for problems. Triggers on "audit skills", "skill quality", "check my skills", "skill duplicates", "skill hygiene".
cf-crawl
Crawl websites using Cloudflare Browser Rendering /crawl API. Async multi-page crawl with markdown/HTML/JSON output, link following, pattern filtering, and AI-powered structured data extraction. Use when crawling entire sites or multiple pages, building knowledge bases, extracting structured data from websites, or when web_fetch is insufficient (JS rendering, multi-page, authenticated crawls).
sub-agents
Spawn and coordinate sub-agent sessions for parallel work. Use when delegating tasks (research, code, analysis), routing to appropriate models, or managing multi-agent workflows. Trigger on "spawn", "sub-agent", "delegate", "parallel tasks", or when a task would benefit from a different model.
browser-read
Extract readable content from browser pages as markdown. Use when web_fetch fails (bot protection, auth-required pages, Twitter/X, LinkedIn) and you already have the page open in the browser.
slack-block-kit
Send rich Slack Block Kit messages — native tables, structured layouts. Use when formatting tabular data for Slack, sending Block Kit payloads, or when markdown tables render poorly in Slack.