wimi321/chrome-web-automation-skill

Latest recorded source activity: April 2, 2026 at 13:20

SkillsMP catalog refreshed: November 12, 2026 at 12:52

skills collected: 1

GitHub stars: 1
GitHub forks: 0

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/wimi321/chrome-web-automation-skill.

Repository README

Repository README source: README.md

Read the source README

Expand full README

# Chrome Web Automation [![Repo](https://img.shields.io/badge/github-chrome-web-automation-skill-181717?logo=github)](https://github.com/wimi321/chrome-web-automation-skill) [![License](https://img.shields.io/badge/license-MIT-green.svg)](./LICENSE) [![Collection](https://img.shields.io/badge/collection-claude--code--skills--extract-blue)](https://github.com/wimi321/claude-code-skills-extract) Use when the user wants browser automation in an existing Chrome session: click, fill, inspect tabs, capture screenshots, or debug web flows. English | [简体中文](./README.zh-CN.md) ## Why This Skill Exists Chrome Web Automation packages a reusable Claude Code workflow as a standalone public skill repository. It is designed for agent teams that want a well-documented, installable, and maintainable capability rather than an internal prompt fragment. ## Highlights - Focused, reusable workflow with a clear trigger boundary - Standalone skill root that works well in agent workspaces - Agent metadata in `agents/openai.yaml` - Public provenance back to the extracted Claude Code source - Bilingual documentation for English and Chinese readers ## What It Is Good At - Drive Chrome for browser-based tasks - Running the workflow described in `SKILL.md` with explicit boundaries - Producing repeatable outputs for operators and agent runtimes ## Example Requests - Open the current Chrome session and reproduce this checkout bug. - Fill the form, capture screenshots, and show me where validation breaks. ## Workflow 1. Start by inspecting current tabs and browser context. 2. Navigate or select the right tab. 3. Snapshot the page before interacting. 4. Click, type, submit, and screenshot using stable references. 5. Re-snapshot after navigation or large DOM updates. ## Inputs - Target site or current tab context - Desired browser actions - Artifacts to capture ## Outputs - Browser interaction transcript - Screenshots or evidence - Reproduction notes ## Success Criteria - The correct tab or page was inspected. - Interactions were completed against fresh page state. - Useful artifacts were captured when needed. ## Non-Goals - Synthetic browser testing unrelated to the user browser context ## Installation ### Use as a standalone skill Clone this repository and place the repository root in a compatible skill directory. ### Use from a larger collection This skill is also included in the parent collection: - [claude-code-skills-extract](https://github.com/wimi321/claude-code-skills-extract) ## Repository Layout - `SKILL.md`: canonical skill instructions - `README.md`: English project overview - `README.zh-CN.md`: Simplified Chinese project overview - `agents/openai.yaml`: UI-facing metadata for agent runtimes - `references/`: provenance and support notes - `LICENSE`: repository license ## Provenance Derived from `src/skills/bundled/claudeInChrome.ts`. ## Related Projects - Parent collection: [claude-code-skills-extract](https://github.com/wimi321/claude-code-skills-extract) - GitHub repository: [chrome-web-automation-skill](https://github.com/wimi321/chrome-web-automation-skill)

Loading the repository README…

Skills in this repository

Software Developers

1 occupation category · 100% classified

skill

occupation

description

updated

chrome-web-automation

Software Developers

Use when the user wants browser automation in an existing Chrome session: click, fill, inspect tabs, capture screenshots, or debug web flows.

2026-04-02

Showing 1 of 1 collected skill.