CtrlK
BlogDocsLog inGet started
Tessl Logo

chrome-devtools

Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).

90

1.59x
Quality

87%

Does it follow best practices?

Impact

94%

1.59x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Evaluation results

100%

9%

Automate a Web Checkout Flow Using Chrome DevTools MCP

Navigate-wait-snapshot-interact workflow

Criteria
Without context
With context

Navigate first

100%

100%

Wait after navigate

60%

100%

Snapshot before interact

100%

100%

UID-based interaction

100%

100%

take_snapshot for automation

100%

100%

includeSnapshot false

100%

100%

filePath for large outputs

100%

100%

Correct sequential order

66%

100%

Stale element recovery

100%

100%

95%

14%

Debug a Multi-Tab Web Application with Hidden State

Multi-page context and tool selection

Criteria
Without context
With context

list_pages for tab discovery

100%

100%

select_page to switch context

100%

100%

take_snapshot for DOM inspection

100%

100%

evaluate_script for JS state

100%

100%

take_screenshot scoped to visual

100%

100%

Pagination or type filtering

100%

100%

filePath for large outputs

20%

100%

Correct pre-interaction sequence

100%

100%

Stale element handling

40%

100%

includeSnapshot false on inputs

0%

0%

88%

83%

Test a Chrome Extension That Modifies Page Content

Chrome extension testing workflow

Criteria
Without context
With context

--categoryExtensions flag

0%

100%

install_extension with path

0%

100%

Extension ID retrieval

0%

100%

trigger_extension_action

0%

100%

evaluate_script with serviceWorkerId

0%

100%

take_snapshot for page verification

0%

100%

Correct step order

25%

40%

Repository
ChromeDevTools/chrome-devtools-mcp
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

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.