Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
cdp-browser v2.0.1 (Security + Reliability Patch) Security hardening: - Blocked unsafe URL schemes in browser navigation (javascript:, data:, file:) - Strict URL validation (http/https only) in pw.js goto, cdp.js newTab/gotoTab Post confirmation safety: - tweet-post requires explicit --confirm, fails fast without it X compose/post flow: - Updated selectors for current X UI, tweetButton/tweetButtonInline preference Command improvements: - query ops: getUrl, getText, getHtml - tweet-draft --save-pending for confirm-button workflows
What This Skill Does
CLI tool for controlling Chrome/Chromium via the Chrome DevTools Protocol (CDP) at localhost:9222. Supports tab inspection, navigation, screenshots, scrolling, JS execution, and posting to X in a persistent browser session.
Reuses an already-authenticated browser session instead of requiring login automation or stored credentials in each script.
When to use it
- Taking a full-page screenshot of a logged-in dashboard
- Posting a tweet from a pre-authenticated X session
- Navigating to a URL and extracting element text
- Scrolling a page to trigger lazy-loaded content
- Dismissing popups blocking automated page interaction
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: take a screenshot of my current Gmail tab
- 1Run `status` to list all open tabs and identify the Gmail tab ID
- 2Run `snapshot <tabId>` to capture a full-page PNG of that tab
- 3Return the screenshot file path to the user
Full-page PNG screenshot of the Gmail tab saved locally
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.