Skip to content
SkillModel-led2,987 tokens in use

browser-testing-with-devtools

Give an agent live browser data through Chrome DevTools MCP: DOM, console, network and performance traces, with safety rules.

119,377 stars on the repository MIT Licenseaddyosmani/agent-skills · skills/browser-testing-with-devtools
npx skills add addyosmani/agent-skills --skill browser-testing-with-devtools
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing browser-testing-with-devtools costs

68tokens idle
2,987tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

Browser Testing with DevTools shows an agent how to use the Chrome DevTools MCP server to see what a page does at runtime. It covers screenshots, DOM and style inspection, console logs, network requests, accessibility tree reads and performance traces.

The skill sets security boundaries around that access: an isolated browser profile, browser content treated as untrusted data and read-only JavaScript execution.

What You Get

  • An MCP configuration snippet for chrome-devtools-mcp
  • A table of DevTools capabilities and when to use each
  • Debugging workflows for UI bugs, network issues and performance
  • Security rules for profile isolation, untrusted content and JavaScript execution

Common Use Cases

  • Verifying a UI change in a real browser
  • Diagnosing console errors and failed requests
  • Profiling Core Web Vitals before and after a fix
  • Checking the accessibility tree and focus order

What Makes It Unique

Most of the skill’s length goes to safety. It tells the agent to default to a dedicated or temporary browser profile, to treat DOM text, console output and network responses as data and never as instructions, and to keep JavaScript execution read-only and free of credential access.

Under The Hood

The skill is a single SKILL.md of instructions. It asks you to add an npx command to your MCP configuration that downloads and runs chrome-devtools-mcp, which launches Chrome and exposes its pages to the agent. The agent then uses the server’s tools and reaches local dev servers and whatever pages it is pointed at. The skill ships no scripts of its own.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers