Agent Skills › pierrecomputer/pierre › browser-automation

browser-automation

GitHub

用于自动化操作网页，包括打开页面、点击、填写表单及获取快照。适用于需要渲染页面、真实 DOM 状态或交互式验证的场景，如本地开发服务器测试和浏览器端验证。

.agents/skills/browser-automation/SKILL.md pierrecomputer/pierre

Trigger Scenarios

需要自动化操作网页元素进行浏览器端的交互验证获取实时 DOM 快照

Install

npx skills add pierrecomputer/pierre --skill browser-automation -g -y

More Options

Non-standard path

npx skills add https://github.com/pierrecomputer/pierre/tree/main/.agents/skills/browser-automation -g -y

Use without installing

npx skills use pierrecomputer/pierre@browser-automation

指定 Agent (Claude Code)

npx skills add pierrecomputer/pierre --skill browser-automation -a claude-code -g -y

安装 repo 全部 skill

npx skills add pierrecomputer/pierre --all -g -y

预览 repo 内 skill

npx skills add pierrecomputer/pierre --list

SKILL.md

Frontmatter

{
    "name": "browser-automation",
    "description": "Use when opening, inspecting, clicking, filling, snapshotting, or otherwise automating web pages for this repo, including local dev servers and browser-based verification."
}

Browser Automation

Use agent-browser for web automation in this repo. Run:

agent-browser --help

Core workflow:

agent-browser open <url>
agent-browser snapshot -i
agent-browser click @e1
agent-browser fill @e2 "text"

Re-run agent-browser snapshot -i after page changes so element refs stay current.

Use browser automation for behavior that needs a rendered page, real DOM state, or interactive verification. Prefer focused Bun tests for pure logic and non-browser integration behavior.