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.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bill492/browser-readWhat This Skill Does
The browser-read skill is a specialized utility for the OpenClaw AI agent designed to bridge the gap between headless web scraping and browser-based human interaction. When standard web fetching methods fail—often due to bot detection, aggressive CAPTCHAs, or the need for persistent session cookies—browser-read allows the agent to extract clean, readable text directly from the current view of the browser. By executing a refined extraction script within the DOM, it strips away non-essential elements like navigation bars, cookie banners, advertisements, and scripts, distilling the page into structured, content-focused Markdown. This ensures that the AI receives the most relevant information without the noise of the surrounding webpage structure, making it ideal for processing complex, dynamic, or protected web content.
Installation
To integrate this skill into your OpenClaw environment, use the OpenClaw CLI tool. Ensure you have the necessary environment permissions for browser automation, then execute the following command in your terminal:
clawhub install openclaw/skills/skills/bill492/browser-read
Once installed, the skill becomes available as a sub-skill under the browser automation suite. No additional configuration is required beyond ensuring your OpenClaw instance has an active browser target session.
Use Cases
This skill is highly effective for several common browsing challenges:
- Authenticated Content: Accessing premium newsletters, internal dashboards, or gated community forums where
web_fetchlacks the required session context. - Bot-Resistant Sites: Bypassing strict anti-scraping protections on sites that identify and block automated requests (like Twitter/X or LinkedIn) but allow human-simulated browser sessions.
- Content Curation: Converting cluttered, media-heavy articles into clean Markdown to summarize, archive, or analyze key data points without the visual bloat of headers and footers.
- Dynamic Web Apps: Capturing textual data that only loads after complex client-side JavaScript execution, which standard HTTP requests cannot trigger.
Example Prompts
- "Open the LinkedIn profile I just navigated to and summarize the professional experience into a bulleted list using the browser-read skill."
- "I am stuck at a login page on the research portal; please log in manually, navigate to the latest report, and then use browser-read to extract the full text so I can analyze the findings."
- "Navigate to this Twitter thread about AI regulations and use browser-read to save the content as a markdown file in my local directory."
Tips & Limitations
To get the most out of browser-read, always prioritize standard web_fetch for static, public pages, as it is significantly faster and more resource-efficient. browser-read is a power-user tool meant for edge cases where standard methods fail. Note that because this skill operates by injecting a script into the DOM, it requires an active, successful browser navigation session to function. If the page is still loading or the frame is unresponsive, the extraction may return empty content or fallback to the full raw text. Always ensure the page is fully rendered before triggering the extraction to achieve the best Markdown formatting results.
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": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: code-execution, data-collection
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".
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).
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.
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.