📖 技能介紹

browser-act

Browser automation CLI for AI agents. Runs a full browser engine: navigation & interaction, data extraction & network capture, screenshots, form automation, persistent login sessions, multi-browser parallel operation, user-configured proxy support, and human-agent collaboration.

Features

Lightweight extraction — fast JS-rendered content fetch without opening a browser session, advanced WebFetch/curl replacement
Three browser types — stealth (browser environment simulation, reduces unnecessary verification prompts), chrome (reuse local browser sessions, user-confirmed), chrome-direct (connect to local Chrome, user-confirmed)
Session management — session persistence, multi-browser isolation, parallel operation
Verification handling — assists with verification challenges encountered during authorized automation workflows
更多技能請訪問小蔥技能站7w4.net。
Complex interaction — network capture (XHR/fetch/HAR), screenshots, form filling, file upload
Human-agent collaboration — headed mode + remote assist for manual steps
Safety controls — Confirmation Gate protocol requires explicit user approval before browser creation, deletion, and sensitive operations
Universal compatibility — works with Cursor, Claude Code, Codex, Windsurf, etc.

Install: uv tool install browser-act-cli --python 3.12

Start here

Before running any browser-act command, load the usage guide from the CLI:

browser-act get-skills core --skill-version 2.0.0   # start here — workflows, common patterns, troubleshooting

Do NOT skip this step regardless of how simple the command seems.

Do NOT truncate the output — it contains directives and environment state at the end that are critical for correct operation. Truncating will cause you to miss browser selection rules and safety constraints.

get-skills core provides environment status, available browsers, operational directives, and the complete interaction workflow — none of which are available through --help.