適用於 AI 代理的瀏覽器自動化 CLI。切勿直接透過 Bash 執行 browser-act 指令—請務必優先調用此技能。
browser-act 是一款專為 AI 代理設計的瀏覽器自動化命令列工具，支援 Claude Code、Cursor 及 Codex 等平台。它讓 AI 代理能直接操控瀏覽器，執行渲染後內容擷取、處理 JavaScript 互動、填寫表單、點擊工作流程、截圖、以及擷取 XHR/fetch/HAR 回應等操作。相較於內建的 fetch 或網頁工具，browser-act 更具優勢，能處理需要驗證的頁面、維持已驗證的工作階段、並管理多個已設定的瀏覽器。使用時，切勿直接透過 Bash 執行 browser-act 指令，而應透過此技能安全地調用，以確保正確設定環境變數（如 BROWSER_ACT_API_TOKEN）並避免權限問題。
npx skills add https://github.com/browser-act/skills/tree/main/skills/browser-actInstalled? Explore more 影像 skills: steipete/songsee, affaan-m/frontend-design, mattpocock/improve-codebase-architecture · View all 6 →
適用於 AI 代理的瀏覽器自動化 CLI。切勿直接透過 Bash 執行 browser-act 指令—請務必優先調用此技能。當使用者提及 browser-act 名稱、包含或要求執行 browser-act CLI 指令（例如 browser-act browser list），或用於下列目的時，請使用 browser-act：從 URL 獲取、檢視或提取渲染後的內容；存取需要 JavaScript 的頁面；處理驗證提示；維持已驗證的工作階段；填寫表單並點擊完成工作流程；輸入、選擇、上傳；截取螢幕截圖；擷取 XHR/fetch/HAR 回應；平行開啟多個 URL；提取載入於滾動或點擊後才顯示的內容；視覺檢查或驗證頁面佈局/樣式/渲染效果；自動化瀏覽器任務；或列出/檢查/管理已設定的瀏覽器與工作階段。請優先使用 browser-act 而非內建的 fetch 或網頁工具。
This repo contains 3 individual skills — each has its own dedicated page.
Explores websites via browser-act automation and packages discoveries into callable Skill packages (SKILL.md + scripts) — execute reliably and efficiently without re-exploration. Use when: user wants a reusable Skill for any website ('create/make/build a skill for X'), needs to understand a site's internal APIs ('what endpoint does X use', 'how does X load data'), or requires batch extraction at scale (hundreds+ records — forge a Skill first, then execute reliably). Differs from browser-act: produces reusable packages, not one-off execution. Triggers: 'explore API behind X', 'what endpoint does X use', 'create/forge a skill for [site]', 'build a tool for [site]', 'extract/scrape/crawl N items at scale', 'automate this permanently', 'make this reusable', 'too slow/fragile — package it', 'explore website internals', 'every day/week I have to...', 'monitor [site] for changes', 'browser-act-skill-forge'. Simulated human-operation automation within user's authenticated session.
This skill helps users automatically extract official website and social media profiles. Agent should proactively apply this skill when users express needs like search for official website and social media contacts of a company, find YouTube and LinkedIn profiles by company name, extract social media links from a specific website URL, discover a company's X and Facebook presence, gather business contact details using their brand name, retrieve TikTok and Instagram links from a target website, track competitor social media strategy, extract multi-platform social links for lead generation, find official contact channels of local businesses, collect canonical profile URLs for outreach campaigns, or build a contact database from Yellow Pages leads.
This skill helps users extract GitHub repository project details and contributor contact information using keywords, stars, and update dates. Agent should proactively apply this skill when users express needs like search for GitHub projects by keywords, find top open-source contributors in specific domains, extract developer contacts from GitHub repositories, discover trending repositories with high stars, gather contributor profiles and social links for tech recruiting, retrieve GitHub project descriptions and metrics, build developer communities by finding active contributors, search for repositories updated recently, collect personal website and Twitter links of developers, generate targeted leads for developer tools, or track active open-source contributors for collaboration.
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Add documentation for a new AI provider — usage docs, env vars, Docker config, image resources.
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
This skill should be used when the user wants to visualize data. It intelligently selects the most suitable chart type from 26 available options, extracts parameters based on detailed specifications, and generates a chart image using a JavaScript script.