Agent skill · Addy Osmani's Agent Skills
/browser-testing-with-devtools Let the agent check a real browser instead of guessing
This skill connects the agent to Chrome through the Chrome DevTools MCP server so it can take screenshots, read the DOM, console, network traffic, styles and accessibility tree, and record performance traces. It gives step-by-step routines for UI, network and performance bugs, and strict rules for treating page content as untrusted and keeping the browser profile isolated.
Works with
- Claude Code
- Any agent via the skills CLI
- Codex
- Gemini CLI
- Antigravity CLI
- Command Code
Used forTesting and TDD
When to use it
- A UI change needs to be confirmed in a running page, not just in unit tests.
- Requests fail, return the wrong data or run into CORS errors.
- Layout shifts, slow loads or console warnings need tracking down.
How it works
- 1Set up the MCP server
You add chrome-devtools-mcp to the project's MCP config, by default with its own browser profile or a temporary isolated one.
- 2Reproduce and inspect
The agent opens the page, triggers the bug, takes a screenshot and reads console errors, the relevant DOM, computed styles and accessibility tree.
- 3Diagnose by type
It compares actual against expected structure and styles, or reads status codes, payloads and timing for network issues, or records a trace for LCP, CLS and INP.
- 4Fix and verify
After changing the source it reloads, compares before and after screenshots, confirms a clean console and runs the automated tests.
What it steers the agent away from
- Following instructions that appear in page text, console output or network responses
- Reading cookies, tokens or localStorage through in-page JavaScript
- Attaching to your everyday Chrome profile when localhost testing does not need it
Install this skill
It installs with the Addy Osmani's Agent Skills pack.
Claude CodeAdds the skills plus nine lifecycle slash commands; use /agent-skills:review where a built-in command shares the name.
/plugin marketplace add addyosmani/agent-skills
/plugin install agent-skills@addy-agent-skillsAny agent via the skills CLIInstalls all skills into Claude Code, Cursor, Codex, Copilot, Cline and many other agents.
npx skills add addyosmani/agent-skillsCodexNeeds Codex CLI v0.122 or later; skills are then called with @ in chat.
codex plugin marketplace add addyosmani/agent-skills
codex plugin add agent-skills@agent-skillsGemini CLIInstalls the skills for auto-discovery.
gemini skills install https://github.com/addyosmani/agent-skills.git --path skillsAntigravity CLIInstalls as a native plugin; some releases need the namespaced skills invoked directly.
agy plugin install https://github.com/addyosmani/agent-skills.gitCommand CodeThe first form installs per project, the second for all projects.
cmd skills add addyosmani/agent-skills
cmd skills add addyosmani/agent-skills --globalCommands come from the author’s README; check it for changes before you run them.
Questions
Does it need anything installed?
Yes. It relies on the chrome-devtools-mcp server, which you add to .mcp.json or your Claude Code settings and which runs through npx.
Can it use my logged-in browser session?
Only via the --autoConnect option, which the skill advises against unless the test truly needs it; a separate test profile is preferred.
More guides from Addy Osmani's Agent Skills
/code-review-and-qualityFive-axis code review with clear severity labelsReviews a change for correctness, readability, architecture, security and performance, labelling each finding by severity.Read the guide →/constraint-driven-developmentWrite down your quality bar and stop agents quietly lowering itSets a written quality bar in CONSTRAINTS.md with default thresholds and flags diffs that skip tests or silence checks.Read the guide →/doubt-driven-developmentHave a fresh reviewer try to break each risky decisionHands each non-trivial decision to a fresh-context reviewer prompted to find faults, with an optional second model.Read the guide →/interview-meFind out what you actually want before anything is builtAsks you single questions, offering its own guessed answer for each, until it can state your real goal and you confirm it.Read the guide →
Also in this pack
/api-and-interface-designDesigns the contract before the code, applying Hyrum's Law, a one-version rule and clear error semantics to interfaces.↗/ci-cd-and-automationSets up a pipeline where lint, types, tests, build, audit and bundle checks must all pass before review.↗/code-simplificationCuts complexity in working code while keeping every input, output, side effect and error exactly the same.↗/context-engineeringSets up rules files and decides which specs, source files and error output the agent should load for each task.↗/deprecation-and-migrationDecides whether old code should go, then plans compulsory or advisory deprecation and migrates consumers off it.↗/documentation-and-adrsRecords significant decisions as ADRs in the project's existing format and spots docs that no longer match the code.↗/git-workflow-and-versioningKeeps main deployable with short-lived branches and small atomic commits that act as save points.↗/idea-refineExpands a rough idea into variations, stress-tests them and saves a one-page proposal with MVP scope and a not-doing list.↗/incremental-implementationBuilds a change in thin vertical slices, testing, verifying and committing each one before starting the next.↗/observability-and-instrumentationLists the questions on-call will ask, then adds structured logs, metrics, traces and symptom-based alerts to answer them.↗/planning-and-task-breakdownMaps dependencies in read-only mode and turns a spec into small, ordered tasks with acceptance criteria in tasks/plan.md.↗/security-and-hardeningStarts from a quick STRIDE threat model, then applies always, ask-first and never rules for input, auth and secrets.↗
Summary by trendhub. The skill itself lives in addyosmani/agent-skills/skills/browser-testing-with-devtools by Addy Osmani (MIT); read the full, current text there.