chrome-devtools-axi-browser-automation

Official

Automate Chrome with token-efficient snapshots.

AuthorAradotso
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill eliminates slow, brittle browser automation by giving agents a compact, consistent view of the page through accessibility tree snapshots and reliable element targeting.

Core Features & Use Cases

  • Token-efficient accessibility snapshots that let agents reference elements using uid refs (uid=g<N>:<id>) for precise actions.
  • Combined operations that reduce round-trips, such as navigating while capturing snapshot state and offering contextual next-step hints.
  • Robust workflow support including staleness detection (STALE_REF prevention), screenshots, JS evaluation, and end-to-end flows for testing.
  • Use Case: An agent can log into a web app, navigate to a feature page, submit a form, take a verification screenshot, and run Lighthouse to collect performance audit results—all while re-snapshotting safely when the DOM changes.

Quick Start

Tell your agent to run npx -y chrome-devtools-axi to get accessibility-tree-based Chrome automation tools it can use to navigate, snapshot, and interact with page elements by uid references.

Dependency Matrix

Required Modules

None required

Components

Standard package

đź’» Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: chrome-devtools-axi-browser-automation
Download link: https://github.com/Aradotso/devtools-skills/archive/main.zip#chrome-devtools-axi-browser-automation

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.