chrome-cdp

Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill attaches over CDP — no MCP server, no Puppeteer/Playwright needed to drive.

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An exemplar of a lean, executable skill body: every section is operational, the workflow includes validation and feedback loops, and detail is appropriately delegated to real referenced scripts. No meaningful weaknesses to address.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — it does not explain what CDP or a WebSocket is, and every line is operational guidance, matching the top anchor for assuming Claude's competence.	3 / 3
Actionability	Provides fully executable bash commands with concrete selectors (e.g. `input[name=email]`, `button[type=submit]`) and copy-paste-ready invocations of the CLI, hitting the top anchor.	3 / 3
Workflow Clarity	Clear numbered sequence (Launch → Drive → Record/Generate → Verify → Teardown) with an explicit validation feedback loop ("VERIFY with run_spec; fix the test ... until it exits 0") and re-record guidance for bad selectors.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview with well-signaled one-level-deep references to real bundle files (scripts/cdp.mjs, scripts/launch-chrome.sh, scripts/gen-test.mjs), all of which exist in the bundle.	3 / 3
	Total	12 / 12 Passed

Description

85%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly scopes both capability and trigger. It would benefit from a few more plain-language keywords users actually say ("automate browser", "test a website") to round out trigger coverage.

Suggestions

Add everyday user phrasings to the trigger clause, e.g. "Use when the user asks to automate a browser, test a website, or do headless browser QA."

Consider spelling out "Chrome DevTools Protocol (CDP)" only once and relying on plain terms afterward to reduce jargon load for the trigger.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert" — matching the top anchor for enumerating specific capabilities.	3 / 3
Completeness	Explicitly answers both what (drive headless Chrome for QA with enumerated actions) and when ("Use whenever a task requires loading a web page and interacting with it like a user"), satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Includes natural terms like "load a web page", "interacting with it like a user", and "browser QA", but leans on jargon ("CDP", "DevTools Protocol") and omits common user phrasings such as "automate the browser" or "test a website".	2 / 3
Distinctiveness Conflict Risk	The CDP-only, no-MCP, no-Puppeteer/Playwright framing carves a clear niche unlikely to fire for general browser or MCP skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mattzcarey/shippie
Path: src/skills/chrome-cdp/SKILL.md
Commit: 23e91d0

Reviewed: ~1 month ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.