Connect Claude Code to an existing Chrome browser via CDP (Chrome DevTools Protocol). Zero dependencies — uses Node 22 built-in WebSocket. Attach to any Chrome running with --remote-debugging-port, then navigate, click, type, screenshot, evaluate JS, read accessibility tree, and monitor console/network. Use when you need to interact with a browser the agent already started, control an existing Chrome instance, or drive browser automation without Playwright MCP. Triggers on: cdp connect, connect to browser, connect to chrome, attach to browser, interact with browser, drive browser, browser automation, control chrome, connect 9222.
79
99%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that covers all dimensions thoroughly. It provides specific concrete actions, comprehensive trigger terms, explicit 'Use when' guidance with differentiation from similar tools (Playwright MCP), and a clear technical niche (CDP protocol). The description is well-structured and informative without being unnecessarily verbose.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'navigate, click, type, screenshot, evaluate JS, read accessibility tree, and monitor console/network.' Also specifies technical details like 'Node 22 built-in WebSocket' and '--remote-debugging-port'. | 3 / 3 |
Completeness | Clearly answers both 'what' (connect to Chrome via CDP, navigate, click, type, screenshot, etc.) and 'when' (explicit 'Use when...' clause with specific scenarios plus a 'Triggers on:' list of keywords). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'cdp connect', 'connect to browser', 'connect to chrome', 'attach to browser', 'browser automation', 'control chrome', 'connect 9222'. These cover many natural phrasings a user might use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — specifically targets CDP/Chrome DevTools Protocol connection to an existing browser, and explicitly differentiates from Playwright MCP ('drive browser automation without Playwright MCP'). The port 9222 reference and CDP focus create a clear niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that is concise, actionable, and well-structured. The command reference is comprehensive and copy-paste ready, the workflow provides clear sequencing with verification steps, and the tips section adds genuinely useful agent-specific guidance like preferring ax-tree over DOM and the external content warning. The only weakness is that the referenced cdp.js script bundle file wasn't provided for evaluation, making it impossible to verify the progressive disclosure structure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what CDP is or how WebSockets work. The prerequisites, commands, and workflow are all tightly written with no padding. | 3 / 3 |
Actionability | Provides fully executable bash commands for every operation, a concrete script block for locating the cdp.js file, and specific examples including eval with promises. The command reference is copy-paste ready with clear argument syntax. | 3 / 3 |
Workflow Clarity | The 5-step workflow (Discover → Understand → Interact → Verify → Debug) is clearly sequenced with explicit verification via screenshot + Read tool. The tips section adds important validation guidance like always listing tabs first when multiple are open. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections, but the bundle files note says no bundle files were provided, yet the skill references `scripts/cdp.js` which should exist as a bundle file. Without the actual bundle, we can't verify the reference. The skill itself is appropriately sized for a single file but the missing bundle is a concern. | 2 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents