agent-browser

by @chuxiaoguo in Development

# Install this skill:

npx skills add chuxiaoguo/skills-repo

Or install specific skill: npx add-skill https://github.com/chuxiaoguo/skills-repo/tree/master/skills-collection/agent-browser

# Description

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

# SKILL.md

name: agent-browser
description: Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Browser Automation with agent-browser

Quick start

agent-browser open <url>        # Navigate to page
agent-browser snapshot -i       # Get interactive elements with refs
agent-browser click @e1         # Click element by ref
agent-browser fill @e2 "text"   # Fill input by ref
agent-browser close             # Close browser

Core workflow

Navigate: agent-browser open <url>
Snapshot: agent-browser snapshot -i (returns elements with refs like @e1, @e2)
Interact using refs from the snapshot
Re-snapshot after navigation or significant DOM changes

Commands

agent-browser open <url>      # Navigate to URL
agent-browser back            # Go back
agent-browser forward         # Go forward
agent-browser reload          # Reload page
agent-browser close           # Close browser

Snapshot (page analysis)

agent-browser snapshot            # Full accessibility tree
agent-browser snapshot -i         # Interactive elements only (recommended)
agent-browser snapshot -c         # Compact output
agent-browser snapshot -d 3       # Limit depth to 3
agent-browser snapshot -s "#main" # Scope to CSS selector

Interactions (use @refs from snapshot)

agent-browser click @e1           # Click
agent-browser dblclick @e1        # Double-click
agent-browser focus @e1           # Focus element
agent-browser fill @e2 "text"     # Clear and type
agent-browser type @e2 "text"     # Type without clearing
agent-browser press Enter         # Press key
agent-browser press Control+a     # Key combination
agent-browser keydown Shift       # Hold key down
agent-browser keyup Shift         # Release key
agent-browser hover @e1           # Hover
agent-browser check @e1           # Check checkbox
agent-browser uncheck @e1         # Uncheck checkbox
agent-browser select @e1 "value"  # Select dropdown
agent-browser scroll down 500     # Scroll page
agent-browser scrollintoview @e1  # Scroll element into view
agent-browser drag @e1 @e2        # Drag and drop
agent-browser upload @e1 file.pdf # Upload files

Get information

agent-browser get text @e1        # Get element text
agent-browser get html @e1        # Get innerHTML
agent-browser get value @e1       # Get input value
agent-browser get attr @e1 href   # Get attribute
agent-browser get title           # Get page title
agent-browser get url             # Get current URL
agent-browser get count ".item"   # Count matching elements
agent-browser get box @e1         # Get bounding box

Check state

agent-browser is visible @e1      # Check if visible
agent-browser is enabled @e1      # Check if enabled
agent-browser is checked @e1      # Check if checked

Screenshots & PDF

agent-browser screenshot          # Screenshot to stdout
agent-browser screenshot path.png # Save to file
agent-browser screenshot --full   # Full page
agent-browser pdf output.pdf      # Save as PDF

Video recording

agent-browser record start ./demo.webm    # Start recording (uses current URL + state)
agent-browser click @e1                   # Perform actions
agent-browser record stop                 # Stop and save video
agent-browser record restart ./take2.webm # Stop current + start new recording

Recording creates a fresh context but preserves cookies/storage from your session.

Wait

agent-browser wait @e1                     # Wait for element
agent-browser wait 2000                    # Wait milliseconds
agent-browser wait --text "Success"        # Wait for text
agent-browser wait --url "**/dashboard"    # Wait for URL pattern
agent-browser wait --load networkidle      # Wait for network idle
agent-browser wait --fn "window.ready"     # Wait for JS condition

Mouse control

agent-browser mouse move 100 200      # Move mouse
agent-browser mouse down left         # Press button
agent-browser mouse up left           # Release button
agent-browser mouse wheel 100         # Scroll wheel

Semantic locators (alternative to refs)

agent-browser find role button click --name "Submit"
agent-browser find text "Sign In" click
agent-browser find label "Email" fill "[email protected]"
agent-browser find first ".item" click
agent-browser find nth 2 "a" text

Browser settings

agent-browser set viewport 1920 1080      # Set viewport size
agent-browser set device "iPhone 14"      # Emulate device
agent-browser set geo 37.7749 -122.4194   # Set geolocation
agent-browser set offline on              # Toggle offline mode
agent-browser set headers '{"X-Key":"v"}' # Extra HTTP headers
agent-browser set credentials user pass   # HTTP basic auth
agent-browser set media dark              # Emulate color scheme

Cookies & Storage

agent-browser cookies                     # Get all cookies
agent-browser cookies set name value      # Set cookie
agent-browser cookies clear               # Clear cookies
agent-browser storage local               # Get all localStorage
agent-browser storage local key           # Get specific key
agent-browser storage local set k v       # Set value
agent-browser storage local clear         # Clear all
agent-browser storage session             # Get all sessionStorage
agent-browser storage session key         # Get specific key
agent-browser storage session set k v     # Set value
agent-browser storage session clear       # Clear all

Network

agent-browser network route <url>              # Intercept requests
agent-browser network route <url> --abort      # Block requests
agent-browser network route <url> --body '{}'  # Mock response
agent-browser network unroute [url]            # Remove routes
agent-browser network requests                 # View tracked requests
agent-browser network requests --filter api    # Filter requests

Tabs & Windows

agent-browser tab                 # List tabs
agent-browser tab new [url]       # New tab
agent-browser tab 2               # Switch to tab
agent-browser tab close           # Close tab
agent-browser window new          # New window

Frames

agent-browser frame "#iframe"     # Switch to iframe
agent-browser frame main          # Back to main frame

Dialogs

agent-browser dialog accept [text]  # Accept dialog
agent-browser dialog dismiss        # Dismiss dialog

JavaScript

agent-browser eval "document.title"   # Run JavaScript

Global Options

Option	Description
`--session <name>`	Isolated browser session (`AGENT_BROWSER_SESSION` env)
`--profile <path>`	Persistent browser profile (`AGENT_BROWSER_PROFILE` env)
`--headers <json>`	HTTP headers scoped to URL's origin
`--executable-path <path>`	Custom browser binary (`AGENT_BROWSER_EXECUTABLE_PATH` env)
`--args <args>`	Browser launch args (`AGENT_BROWSER_ARGS` env)
`--user-agent <ua>`	Custom User-Agent (`AGENT_BROWSER_USER_AGENT` env)
`--proxy <url>`	Proxy server (`AGENT_BROWSER_PROXY` env)
`--proxy-bypass <hosts>`	Hosts to bypass proxy (`AGENT_BROWSER_PROXY_BYPASS` env)
`-p, --provider <name>`	Cloud browser provider (`AGENT_BROWSER_PROVIDER` env)
`--json`	Machine-readable JSON output
`--headed`	Show browser window (not headless)
`--cdp <port\\|wss://url>`	Connect via Chrome DevTools Protocol
`--debug`	Debug output

Example: Form submission

agent-browser open https://example.com/form
agent-browser snapshot -i
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]

agent-browser fill @e1 "[email protected]"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait --load networkidle
agent-browser snapshot -i  # Check result

Example: Authentication with saved state

# Login once
agent-browser open https://app.example.com/login
agent-browser snapshot -i
agent-browser fill @e1 "username"
agent-browser fill @e2 "password"
agent-browser click @e3
agent-browser wait --url "**/dashboard"
agent-browser state save auth.json

# Later sessions: load saved state
agent-browser state load auth.json
agent-browser open https://app.example.com/dashboard

# Headers scoped to api.example.com only
agent-browser open api.example.com --headers '{"Authorization": "Bearer <token>"}'
# Navigate to another domain - headers NOT sent (safe)
agent-browser open other-site.com
# Global headers (all domains)
agent-browser set headers '{"X-Custom-Header": "value"}'

Sessions & Persistent Profiles

Sessions (parallel browsers)

agent-browser --session test1 open site-a.com
agent-browser --session test2 open site-b.com
agent-browser session list

Persistent Profiles

Persists cookies, localStorage, IndexedDB, service workers, cache, login sessions across browser restarts.

agent-browser --profile ~/.myapp-profile open myapp.com
# Or via env var
AGENT_BROWSER_PROFILE=~/.myapp-profile agent-browser open myapp.com

Use different profile paths for different projects
Login once → restart browser → still logged in
Stores: cookies, localStorage, IndexedDB, service workers, browser cache

JSON output (for parsing)

Add --json for machine-readable output:

agent-browser snapshot -i --json
agent-browser get text @e1 --json

Debugging

agent-browser open example.com --headed              # Show browser window
agent-browser console                                # View console messages
agent-browser errors                                 # View page errors
agent-browser record start ./debug.webm              # Record from current page
agent-browser record stop                            # Save recording
agent-browser connect 9222                           # Local CDP port
agent-browser --cdp "wss://browser-service.com/cdp?token=..." snapshot  # Remote via WebSocket
agent-browser console --clear                        # Clear console
agent-browser errors --clear                         # Clear errors
agent-browser highlight @e1                          # Highlight element
agent-browser trace start                            # Start recording trace
agent-browser trace stop trace.zip                   # Stop and save trace

Installation

Step 1: Install agent-browser CLI

bun add -g agent-browser

Step 2: Install Playwright browsers

IMPORTANT: agent-browser install may fail on some platforms (e.g., darwin-arm64) with "No binary found" error. In that case, install Playwright browsers directly:

# Create a temp project and install playwright
cd /tmp && bun init -y && bun add playwright

# Install Chromium browser
bun playwright install chromium

This downloads Chrome for Testing to ~/Library/Caches/ms-playwright/.

Verify installation

agent-browser open https://example.com --headed

If the browser opens successfully, installation is complete.

Troubleshooting

Error	Solution
`No binary found for darwin-arm64`	Run `bun playwright install chromium` in a project with playwright dependency
`Executable doesn't exist at .../chromium-XXXX`	Re-run `bun playwright install chromium`
Browser doesn't open	Ensure `--headed` flag is used for visible browser

Run agent-browser --help for all commands. Repo: https://github.com/vercel-labs/agent-browser

# README.md

Skills Repo - AI Agent Skills 同步管理系统

一个支持从 skillsmp.com API 同步、管理和合并 AI Agent Skills 的仓库管理系统。

功能特性

🔗 API 同步 - 从 skillsmp.com 自动同步热门 Skills
📝 单技能管理 - 每个技能独立的 JSON 文件，便于阅读和版本控制
🔄 增量更新 - 智能检测变更，避免不必要的同步
🏷️ 特征提取 - 自动从 SKILL.md 和 API 数据提取特征
🔀 合并输出 - 将分散的单技能 JSON 合并为统一的 skills.json
⚙️ 环境配置 - 支持 .env 文件管理敏感配置（API Token）
📦 模块化架构 - 清晰的代码分层，易于维护和扩展

项目结构

skills-repo/
├── .env                          # 环境变量（API Token）
├── .env.example                  # 环境变量示例
├── .gitignore                    # Git 忽略配置
├── package.json                  # 项目配置和脚本
├── README.md                     # 本文件
├── skills.json                   # 合并后的技能总索引
├── skills-json/                  # 单技能 JSON 目录
│   ├── cache-components.json
│   └── skill-lookup.json
├── scripts/                      # 脚本目录
│   ├── sync-skills.js            # 主同步脚本
│   ├── merge-skills.js           # 合并脚本
│   └── lib/                      # 功能模块
│       ├── adapters.js           # API 适配器
│       ├── config.js             # 配置管理
│       ├── extractors.js         # 特征提取器
│       ├── sync-controller.js    # 同步控制器
│       ├── utils.js              # 工具函数
│       └── writers.js            # 文件写入器
└── skills-collection/            # 技能内容目录
    └── [skill-name]/
        └── SKILL.md

快速开始

1. 安装依赖

npm install

2. 配置环境变量

# 复制示例文件
cp .env.example .env

# 编辑 .env，填写你的 API Token
SKILLSMP_API_TOKEN=sk_live_your_token_here

从 skillsmp.com/zh/docs/api 获取 API Token

3. 同步 Skills

# 批量同步热门 Skills（默认 20 个）
npm run skills:sync

# 同步指定数量的 Skills
npm run skills:sync -- --limit 50

# 按名字同步指定 Skills
npm run skills:sync -- --names "react" "vue" "nextjs"

# 使用 AI 语义搜索
npm run skills:sync -- --names "web scraping" --use-ai-search

4. 合并 Skills

# 合并所有单技能 JSON 到 skills.json
npm run skills:merge

# 显示详细信息
npm run skills:merge -- --verbose

技术架构

分层设计

┌─────────────────────────────────────────┐
│              CLI 层                      │
│   sync-skills.js / merge-skills.js      │
├─────────────────────────────────────────┤
│            控制层                        │
│      SyncController                     │
│   - 协调同步流程                         │
│   - 增量更新检测                         │
├─────────────────────────────────────────┤
│            业务逻辑层                    │
│  ┌──────────┐ ┌──────────┐ ┌─────────┐ │
│  │ Adapters │ │Extractors│ │ Writers │ │
│  └──────────┘ └──────────┘ └─────────┘ │
├─────────────────────────────────────────┤
│            配置层                        │
│      Config (环境变量管理)               │
└─────────────────────────────────────────┘

核心模块

1. Adapters（API 适配器）

封装 skillsmp.com REST API 调用：

class SkillsMPAdapter {
  async search(query, options)     // 关键字搜索
  async aiSearch(query)            // AI 语义搜索
  async getTopSkills(limit, sortBy) // 获取热门 Skills
}

API 端点：
- GET /api/v1/skills/search - 关键字搜索
- GET /api/v1/skills/ai-search - AI 语义搜索

2. Extractors（特征提取器）

从多种数据源提取 Skill 特征：

class FeatureExtractor {
  extract(content)                 // 从 SKILL.md 提取
  extractFromApiData(apiData)      // 从 API 响应提取
  inferTagsFromContent(content)    // 从内容推断标签
}

提取字段：
- name - 技能名称
- description - 描述
- tags - 标签数组
- version - 版本号
- author - 作者
- sourceUrl - GitHub 源地址
- stars - GitHub Stars

3. Writers（文件写入器）

处理文件系统操作：

class OutputWriter {
  async saveSkill(skillData, features)     // 保存技能
  async checkNeedsUpdate(name, newData)    // 检查是否需要更新
  async mergeSkillsFromDir()               // 合并所有技能
}

输出文件：
- skills-json/{name}.json - 单技能 JSON
- skills-collection/{name}/SKILL.md - Skill 文档
- skills.json - 合并后的索引

环境变量配置

变量名	必需	默认值	说明
`SKILLSMP_API_TOKEN`	✅	-	skillsmp.com API Token
`SKILLSMP_BASE_URL`	❌	`https://skillsmp.com/api/v1`	API 基础 URL

示例 .env 文件：

# SkillsMP API Token
SKILLSMP_API_TOKEN=sk_live_skillsmp_ViwcBS9cwEhzGtGcnec7faxtGkIsM9gxLowPmRShPHU

# 可选：API 基础 URL
# SKILLSMP_BASE_URL=https://skillsmp.com/api/v1

增量更新机制

系统会智能检测 Skill 是否需要更新：

检查流程

读取现有数据 - 从 skills-json/{name}.json 读取
字段对比 - 对比以下字段：
description
version
author
sourceUrl
tags（排序后比较）
决策输出：
新技能 → 创建
字段变化 → 更新
无变化 → 跳过

使用示例

# 第一次同步
npm run skills:sync -- --limit 2
# 输出:
#   ✅ 创建: skill-lookup (新技能)
#   ✅ 创建: cache-components (新技能)

# 第二次同步（相同 Skills）
npm run skills:sync -- --limit 2
# 输出:
#   ⏭️  跳过: skill-lookup (无变化)
#   ⏭️  跳过: cache-components (无变化)

命令行参数

sync-skills.js

参数	类型	默认值	说明
`--names`	string[]	-	指定要同步的 Skill 名称
`--mode`	string	`batch`	同步模式：`batch` / `names`
`--limit`	number	20	批量同步数量
`--sort`	string	`stars`	排序方式：`stars` / `recent`
`--use-ai-search`	boolean	false	使用 AI 语义搜索
`--force`	boolean	false	强制更新（忽略缓存）

merge-skills.js

参数	类型	说明
`--verbose` / `-v`	boolean	显示详细信息
`--dry-run` / `-d`	boolean	试运行（不写入文件）

Skills JSON 格式

单技能 JSON（skills-json/{name}.json）

{
  "name": "skill-lookup",
  "path": "skill-lookup",
  "description": "Activates when the user asks about Agent Skills...",
  "tags": ["skills", "lookup", "claude"],
  "version": "1.0.0",
  "author": "f",
  "sourceUrl": "https://github.com/f/awesome-chatgpt-prompts/...",
  "stars": 143926,
  "updatedAt": "2026-01-29T12:11:39.382Z"
}

合并后的 skills.json

{
  "meta": {
    "generatedAt": "2026-01-29T12:15:54.836Z",
    "total": 2
  },
  "skills": [
    {
      "name": "cache-components",
      "path": "cache-components",
      "description": "...",
      "tags": [],
      "version": "1.0.0",
      "author": "vercel"
    }
  ]
}

开发计划

[ ] 支持从 GitHub 直接克隆 Skill 仓库
[ ] 支持 skills.sh CLI 作为数据源
[ ] 添加 Skill 版本对比功能
[ ] 支持自定义 Skill 模板
[ ] 添加 Webhook 自动同步

许可证

MIT

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

⚡ Amp 🚀 Antigravity 🤖 Claude Code 🦀 Clawdbot 📝 Codex ▶️ Cursor 🤖 Droid 💎 Gemini CLI 🐙 GitHub Copilot 🪿 Goose 📊 Kilo Code 🔧 Kiro CLI 💻 OpenCode 🦘 Roo Code 🌲 Trae 🏄 Windsurf

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.