browser-cdp
Real Chrome browser automation via CDP Proxy — access pages with full user login state, bypass anti-bot detection, perform interactive operations (click/fill/scroll), extract dynamic JavaScript-rendered content, take screenshots. Triggers (satisfy ANY one): - Target URL is a search results page (Bing/Google/YouTube search) - Static fetch (agent-reach/WebFetch) is blocked by anti-bot (captcha/intercept/empty) - Need to read logged-in user's private content - YouTube, Twitter/X, Xiaohongshu, WeChat public accounts, etc. - Task involves "click", "fill form", "scroll", "drag" - Need screenshot or dynamic-rendered page capture
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/0xcjl/browser-cdpWhat This Skill Does
browser-cdp is a high-fidelity Chrome automation engine designed for the OpenClaw AI agent. By interfacing directly with the Chrome DevTools Protocol (CDP), it transforms your local Chrome instance into a programmable, intelligent assistant. Unlike standard scrapers, browser-cdp operates within your existing browser context, meaning it inherits your login sessions, cookies, and authentication tokens. This allows the AI to navigate gated content, perform complex multi-step workflows like filling out forms or uploading files, and interact with modern JavaScript-heavy web applications that defeat static HTML parsers.
Installation
Installation involves two primary steps: preparing the environment and deploying the proxy. First, launch Chrome with remote debugging enabled using the command provided in the documentation: "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome" --remote-debugging-port=9222. Next, start the CDP proxy service via Node.js using node ~/.openclaw/skills/browser-cdp/scripts/cdp-proxy.mjs. Once active, the proxy runs on port 3456, serving as the bridge between your agent and the browser.
Use Cases
browser-cdp is essential when standard fetching mechanisms fail due to anti-bot defenses. It is the primary tool for extracting data from search engines like Google and Bing, or social platforms like Twitter/X and Xiaohongshu. It is also the perfect solution for tasks requiring human-like interaction: navigating to a site, logging in, performing a search, scrolling through lazy-loaded content, and capturing a final screenshot for verification. If your task involves interacting with dynamic UI elements like buttons, dropdowns, or drag-and-drop zones, browser-cdp is the appropriate choice.
Example Prompts
- "Open my LinkedIn feed in the browser, scroll to the bottom, and take a screenshot of the latest updates."
- "Search for the latest AI research papers on Google, click on the top result, and extract the main article body text."
- "Log into my private dashboard at example.com, fill out the support form with the following details, and submit it."
Tips & Limitations
Use browser-cdp as a precision tool. It consumes more system resources and takes longer than static fetchers; therefore, prioritize it for gated or dynamic content. Remember to keep your Chrome instance running for the duration of your task. If you encounter rate-limiting on large-scale tasks, consider offloading public requests to agent-reach to preserve your access on critical platforms.
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-0xcjl-browser-cdp": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-write, file-read, code-execution
Related Skills
autoresearch-pro
Automatically improve OpenClaw skills, prompts, or articles through iterative mutation-testing loops. Inspired by Karpathy's autoresearch. Use when user says 'optimize [skill]', 'autoresearch [skill]', 'improve my skill', 'optimize this prompt', 'improve my prompt', 'polish this article', 'improve this article', or explicitly requests quality improvement for any text-based content. Supports three modes: skill (SKILL.md files), prompt (any prompt text), and article (any document).
cjl-slides
Create stunning HTML presentations in 24 international design styles with strict design rules. Export to .pptx for PowerPoint editing. ## Design Philosophy - Aesthetic-first: each style is a curated visual system, not just colors - Font whitelist enforcement: prevents AI-generic typography - Container ratio lock (16:9): ensures consistent rendering across devices - Zero external dependencies: pure HTML/CSS/JS, works offline ## Usage 1. Activate → Select style by name/number or browse 24 options 2. Provide content (topic, audience, key points) or upload .pptx for conversion 3. Review generated HTML slides → request modifications (color/font/layout) 4. Optionally export .pptx for manual editing in PowerPoint ## Precautions - Fonts are restricted to a whitelist; custom fonts require adding to the allowed list first - Chart.js CDN is used; if blocked, falls back to jsdelivr mirror - HTML files must retain their relative structure when shared - .pptx export preserves exact colors and fonts but layout uses pptx-native elements ## Credits Design rules adapted from "专精 HTML 演示文稿的顶级视觉设计师" (24 design styles reference). Base HTML structure and tooling inspired by zarazhangrui/frontend-slides.
Diagram Drawing
Skill by 0xcjl
anti-sycophancy
Three-layer sycophancy defense based on ArXiv 2602.23971. Use /anti-sycophancy install to deploy all layers, or manage individually via install-claude-code / install-openclaw / uninstall / status / verify. Layer 1: CC-only hook; Layer 2: SKILL (cross-platform); Layer 3: CLAUDE.md (CC) / SOUL.md (OC).
auto-diary
Automatically write daily/weekly/monthly diary summaries and extract insights to auto-learn.md for HexaLoop.