⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
actionbook
This skill should be used when the user needs to automate multi-step website tasks. Activates for browser automation, web scraping, UI testing, or building AI agents. Provides complete action manuals with step-by-step instructions and verified selectors.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
goclaw (🐾 狗爪)
Go 语言版本的 OpenClaw - 一个功能强大的 AI Agent 框架。

功能特性
- 🛠️ 完整的工具系统:FileSystem、Shell、Web、Browser,支持 Docker 沙箱与权限控制
- 📚 技能系统 (Skills):兼容 OpenClaw 和 AgentSkills 规范,支持自动发现与环境准入控制 (Gating)
- 💾 持久化会话:基于 JSONL 的会话存储,支持完整的工具调用链 (Tool Calls) 记录与恢复
- 📢 多渠道支持:Telegram、WhatsApp、飞书 (Feishu)、QQ、企业微信 (WeWork)、钉钉 (DingTalk)、百度如流 (Infoflow)、Gotify、Slack、Discord、Google Chat、Microsoft Teams、微信 (Weixin)
- 🔧 灵活配置:支持 YAML/JSON 配置,热加载,环境变量支持
- 🎯 多 LLM 提供商:OpenAI、Qianfan(百度千帆,OpenAI-compatible)、Anthropic、OpenRouter,支持故障转移
- 🌐 WebSocket Gateway:内置网关服务,支持实时通信
- ⏰ Cron 调度:内置定时任务调度器
- 🖥️ Browser 自动化:基于 Chrome DevTools Protocol 的浏览器控制
- 🧠 记忆系统:支持内置向量数据库和 QMD (Quick Markdown Database)
- 👥 多账号支持:每个通道支持配置多个账号实例
- 🪟 跨平台:支持 Linux、macOS、Windows
技能系统 (New!)
goclaw 引入了先进的技能系统,允许用户通过编写 Markdown 文档 (SKILL.md) 来扩展 Agent 的能力。
特性
- Prompt-Driven: 技能本质上是注入到 System Prompt 中的指令集,指导 LLM 使用现有工具 (exec, read_file 等) 完成任务。
- OpenClaw 兼容: 完全兼容 OpenClaw 的技能生态。您可以直接将
openclaw/skills目录下的技能复制过来使用。 - 自动准入 (Gating): 智能检测系统环境。例如,只有当系统安装了
curl时,weather技能才会生效;只有安装了git时,git-helper才会加载。
使用方法
配置文件加载优先级
goclaw 按以下顺序查找配置文件(找到第一个即使用):
~/.goclaw/config.json(用户全局目录,最高优先级)./config.json(当前目录)- 环境变量
GOSKILLS_*前缀
可通过 --config 参数指定配置文件路径覆盖默认行为。支持 YAML 和 JSON 格式。
Skills 加载顺序
技能按以下顺序加载,同名技能后面的会覆盖前面的:
| 顺序 | 路径 | 说明 |
|---|---|---|
| 1 | ~/.goclaw/skills/ | 用户全局目录(最低优先级) |
| 2 | ${WORKSPACE}/skills/ | 工作区目录 |
| 3 | ./skills/ (当前目录) | 最后加载,优先级最高 |
默认 WORKSPACE 为 ~/.goclaw/workspace。
-
列出可用技能
./goclaw skills list -
安装技能 将技能文件夹放入以下任一位置:
~/.goclaw/skills/(用户全局目录)${WORKSPACE}/skills/(工作区目录)./skills/(当前目录,最高优先级,后加载会覆盖前面的)
-
编写技能 创建一个目录
my-skill,并在其中创建SKILL.md:--- name: my-skill description: A custom skill description. metadata: openclaw: requires: bins: ["python3"] # 仅当 python3 存在时加载 --- # My Skill Instructions When the user asks for X, use `exec` to run `python3 script.py`.
项目结构
goclaw/
├── agent/ # Agent 核心逻辑
│ ├── loop.go # Agent 循环
│ ├── context.go # 上下文构建器
│ ├── memory.go # 记忆系统
│ ├── skills.go # 技能加载器
│ ├── subagent.go # 子代理管理器
│ └── tools/ # 工具系统
│ ├── filesystem.go # 文件系统工具
│ ├── shell.go # Shell 工具
│ ├── web.go # Web 工具
│ ├── browser.go # 浏览器工具
│ └── message.go # 消息工具
├── channels/ # 消息通道
│ ├── base.go # 通道接口
│ ├── manager.go # 通道管理器
│ ├── telegram.go # Telegram 实现
│ ├── whatsapp.go # WhatsApp 实现
│ ├── feishu.go # 飞书实现
│ ├── qq.go # QQ 实现
│ ├── wework.go # 企业微信实现
│ ├── dingtalk.go # 钉钉实现
│ ├── infoflow.go # 百度如流实现
│ ├── gotify.go # Gotify 实现
│ ├── slack.go # Slack 实现
│ ├── discord.go # Discord 实现
│ ├── googlechat.go # Google Chat 实现
│ ├── teams.go # Microsoft Teams 实现
│ └── weixin.go # 微信实现
├── bus/ # 消息总线
│ ├── events.go # 消息事件
│ └── queue.go # 消息队列
├── config/ # 配置管理
│ ├── schema.go # 配置结构
│ └── loader.go # 配置加载器
├── providers/ # LLM 提供商
│ ├── base.go # 提供商接口
│ ├── factory.go # 提供商工厂
│ ├── openai.go # OpenAI 实现
│ ├── anthropic.go # Anthropic 实现
│ └── openrouter.go # OpenRouter 实现
├── gateway/ # WebSocket 网关
│ ├── server.go # 网关服务器
│ ├── handler.go # 消息处理器
│ └── protocol.go # 协议定义
├── cron/ # 定时任务调度
│ ├── scheduler.go # 调度器
│ └── cron.go # Cron 任务
├── session/ # 会话管理
│ └── manager.go # 会话管理器
├── cli/ # 命令行界面
│ ├── root.go # 根命令
│ ├── agent.go # Agent 命令
│ ├── agents.go # Agents 管理命令
│ ├── sessions.go # 会话命令
│ ├── cron_cli.go # Cron 命令
│ ├── approvals.go # 审批命令
│ ├── system.go # 系统命令
│ └── commands/ # 子命令
│ ├── tui.go # TUI 命令
│ ├── gateway.go # Gateway 命令
│ ├── browser.go # Browser 命令
│ ├── health.go # 健康检查
│ ├── status.go # 状态查询
│ ├── memory.go # 记忆管理
│ └── logs.go # 日志查询
├── internal/ # 内部包
│ ├── logger/ # 日志
│ └── utils/ # 工具函数
├── docs/ # 文档
│ ├── cli.md # CLI 详细文档
│ └── INTRODUCTION.md # 项目介绍
└── main.go # 主入口
快速开始
安装
# 克隆仓库
git clone https://github.com/smallnest/goclaw.git
cd goclaw
# 安装依赖
go mod tidy
# 仅编译 Go 程序
go build -o goclaw .
# 完整构建(包含 UI,推荐)
make build-full
# 或直接运行
go run main.go start
本地可以访问 dashboard:
http://localhost:28789/dashboard/
配置
goclaw 按以下顺序查找配置文件(找到第一个即使用):
~/.goclaw/config.json(用户全局目录,最高优先级)./config.json(当前目录)- 环境变量
GOSKILLS_*前缀
可通过 --config 参数指定配置文件路径覆盖默认行为。支持 YAML 和 JSON 格式。
创建 config.json (参考 internal/config.example.json):
{
"workspace": {
"path": ""
},
"agents": {
"defaults": {
"model": {
"primary": "qianfan/kimi-k2.5"
},
"max_iterations": 15,
"temperature": 0.7,
"max_tokens": 4096
}
},
"models": {
"mode": "merge",
"providers": {
"qianfan": {
"baseUrl": "https://qianfan.baidubce.com/v2",
"apiKey": "${QIANFAN_API_KEY}",
"api": "openai-completions",
"models": [
{
"id": "kimi-k2.5",
"name": "Kimi K2.5",
"contextWindow": 131072,
"maxTokens": 8192,
"input": ["text", "image"]
}
]
},
"openai": {
"baseUrl": "https://api.openai.com/v1",
"apiKey": "${OPENAI_API_KEY}",
"api": "openai-completions",
"models": [
{
"id": "gpt-4o",
"name": "GPT-4o",
"contextWindow": 128000,
"maxTokens": 16384,
"input": ["text", "image"]
}
]
}
}
},
"channels": {
"telegram": {
"enabled": false,
"token": "your-telegram-bot-token",
"allowed_ids": []
},
"feishu": {
"enabled": false,
"app_id": "",
"app_secret": "",
"domain": "feishu",
"group_policy": "open"
},
"dingtalk": {
"enabled": false,
"client_id": "",
"secret": "",
"allowed_ids": []
}
},
"tools": {
"filesystem": {
"allowed_paths": [],
"denied_paths": []
},
"shell": {
"enabled": true,
"allowed_cmds": [],
"denied_cmds": ["rm -rf", "dd", "mkfs", "format"],
"timeout": 30,
"working_dir": ""
},
"browser": {
"enabled": true,
"headless": true,
"timeout": 30,
"relay_url": "ws://127.0.0.1:18789",
"relay_mode": "auto"
}
},
"memory": {
"backend": "builtin",
"builtin": {
"enabled": true,
"database_path": "",
"auto_index": true
}
}
}
运行
# 启动 Agent 服务
./goclaw start
# 交互式 TUI
// HOW IT'S BUILT
// FILES
5 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
internal/builtin_skills/actionbook/SKILL.md16 KB82ceb3b35430upstream ↗
--- name: actionbook description: This skill should be used when the user needs to automate multi-step website tasks. Activates for browser automation, web scraping, UI testing, or building AI agents. Provides complete action manuals with step-by-step instructions and verified selectors. --- ## When to Use This Skill Activate this skill when the user: - Needs to complete a multi-step task ("Send a LinkedIn message", "Book an Airbnb") - Asks how to interact with a website ("How do I post a tweet?") - Builds browser-based AI agents or web scrapers - Writes E2E tests for external websites - Navigates to any new page during browser automation - Wants to control their existing Chrome browser (Extension mode) ## Browser Modes Actionbook supports two browser control modes: | Mode | Flag | Use Case | |------|------|----------| | **CDP** (default) | (none) | Launches a dedicated browser instance via Chrome DevTools Protocol | | **Extension** | `--extension` | Controls the user's existing Chrome browser via a Chrome Extension + WebSocket bridge | **When to use Extension mode:** - The user wants to operate on their already-open Chrome (with existing logins, cookies, tabs) - The task requires interacting with pages that need the user's real session state - The user explicitly mentions their Chrome browser, extension, or existing tabs **When to use CDP mode (default):** - Clean browser environment is preferred - Headless automation or CI/CD - Profile-based session isolation is needed All `actionbook browser` commands work identically in both modes. The only difference is adding `--extension` flag (or setting `ACTIONBOOK_EXTENSION=1`). ## How to Use ### Phase 1: Get Action Manual ```bash # Step 1: Search for action manuals actionbook search "arxiv search papers" # Returns: area IDs with descriptions # Step 2: Get the full manual (use area_id from search results) actionbook get "arxiv.org:/search/advanced:default" # Returns: Page structure, UI Elements with CSS/XPath selectors ``` ### Phase 2: Execute with Browser (CDP mode — default) ```bash # Step 3: Open browser actionbook browser open "https://arxiv.org/search/advanced" # Step 4: Use CSS selectors from Action Manual directly actionbook browser fill "#terms-0-term" "Neural Network" actionbook browser select "#terms-0-field" "title" actionbook browser click "#date-filter_by-2" actionbook browser fill "#date-year" "2025" actionbook browser click "form[action='/search/advanced'] button.is-link" # Step 5: Wait for results actionbook browser wait-nav # Step 6: Extract data actionbook browser text # Step 7: Close browser actionbook browser close ``` ### Phase 2 (alt): Execute with Extension mode Extension mode uses identical browser commands — just add `--extension`. But you **must** follow the full lifecycle below. ```bash # Step 3: Open URL in user's Chrome actionbook --extension browser open "https://arxiv.org/search/advanced" # Step 4-7: Same commands, just add --extension actionbook --extension browser fill "#terms-0-term" "Neural Network" actionbook --extension browser select "#terms-0-field" "title" actionbook --extension browser click "#date-filter_by-2" actionbook --extension browser fill "#date-year" "2025" actionbook --extension browser click "form[action='/search/advanced'] button.is-link" actionbook --extension browser wait-nav actionbook --extension browser text # Step 8: Cleanup (CRITICAL — see Extension Mode Lifecycle below) actionbook --extension browser close # release debug connection FIRST actionbook extension stop # then stop bridge server ``` ## Action Manual Format Action manuals return: - **Page URL** - Target page address - **Page Structure** - DOM hierarchy and key sections - **UI Elements** - CSS/XPath selectors with element metadata ```yaml ### button_advanced_search - ID: button_advanced_search - Description: Advanced search navigation button - Type: link - Allow Methods: click - Selectors: - role: getByRole('link', { name: 'Advanced Search' }) (confidence: 0.9) - css: button.button.is-small.is-cul-darker (confidence: 0.65) - xpath: //button[contains(@class, 'button')] (confidence: 0.55) ``` ## Action Search Commands ```bash actionbook search "<query>" # Basic search actionbook search "<query>" --domain site.com # Filter by domain actionbook search "<query>" --url <url> # Filter by URL actionbook search "<query>" -p 2 -s 20 # Page 2, 20 results actionbook get "<area_id>" # Full details with selectors # area_id format: "site.com:/path:area_name" actionbook sources list # List available sources actionbook sources search "<query>" # Search sources by keyword ``` ## Extension Setup & Management Commands for managing the Chrome Extension bridge: ```bash actionbook extension install # Install extension files to local config dir actionbook extension path # Show extension directory (for Chrome "Load unpacked") actionbook extension serve # Start WebSocket bridge (keep running in background) actionbook extension stop # Stop the running bridge server (sends SIGTERM) actionbook extension status # Check bridge and extension connection status actionbook extension ping # Ping the extension to verify link is alive ``` **Setup flow (one-time):** 1. `actionbook extension install` — extract extension files and register native messaging host 2. Open `chrome://extensions` → enable Developer mode → Load unpacked → select the path from `actionbook extension path` 3. `actionbook extension serve` — start bridge (keep running) 4. Extension auto-connects via native messaging (no manual token needed in most cases). If auto-pairing fails: copy token from `serve` output → paste in extension popup → Save **Connection check before automation:** ```bash actionbook extension status # should show "running" actionbook extension ping # should show "responded" ``` ## Browser Commands > All browser commands below work in both CDP and Extension mode. > For Extension mode, add `--extension` flag or set `ACTIONBOOK_EXTENSION=1`. ### Navigation ```bash actionbook browser open <url> # Open URL in new tab actionbook browser goto <url> # Navigate current page actionbook browser back # Go back actionbook browser forward # Go forward actionbook browser reload # Reload page actionbook browser pages # List open tabs actionbook browser switch <page_id> # Switch tab actionbook browser close # Close browser actionbook browser restart # Restart browser actionbook browser connect <endpoint> # Connect to existing browser (CDP port or URL) ``` ### Interactions (use CSS selectors from Action Manual) ```bash actionbook browser click "<selector>" # Click element actionbook browser click "<selector>" --wait 1000 # Wait then click actionbook browser fill "<selector>" "text" # Clear and type actionbook browser type "<selector>" "text" # Append text actionbook browser select "<selector>" "value" # Select dropdown actionbook browser hover "<selector>" # Hover actionbook browser focus "<selector>" # Focus actionbook browser press Enter # Press key ``` ### Get Information ```bash actionbook browser text # Full page text actionbook browser text "<selector>" # Element text actionbook browser html # Full page HTML actionbook browser html "<selector>" # Element HTML actionbook browser snapshot # Accessibility tree actionbook browser viewport # Viewport dimensions actionbook browser status # Browser detection info ``` ### Wait ```bash actionbook browser wait "<selector>" # Wait for element actionbook browser wait "<selector>" --timeout 5000 # Custom timeout actionbook browser wait-nav # Wait for navigation ``` ### Screenshots & Export ```bash # Ensure target directory exists before saving screenshots actionbook browser screenshot # Save screenshot.png actionbook browser screenshot output.png # Custom path actionbook browser screenshot --full-page # Full page actionbook browser pdf output.pdf # Export as PDF ``` ### JavaScript & Inspection ```bash actionbook browser eval "document.title" # Execute JS actionbook browser inspect 100 200 # Inspect at coordinates actionbook browser inspect 100 200 --desc "login btn" # With description ``` ### Cookies ```bash actionbook browser cookies list # List all cookies actionbook browser cookies get "name" # Get cookie actionbook browser cookies set "name" "value" # Set cookie actionbook browser cookies set "name" "value" --domain ".example.com" actionbook browser cookies delete "name" # Delete cookie actionbook browser cookies clear # Clear all ``` ## Global Flags ```bash actionbook --json <command> # JSON output actionbook --headless <command> # Headless mode (CDP only) actionbook --verbose <command> # Verbose logging actionbook -P <profile> <command> # Use specific profile (CDP only) actionbook --cdp <port|url> <command> # CDP connection actionbook --extension <command> # Use Chrome Extension mode # or: ACTIONBOOK_EXTENSION=1 actionbook <command> ``` ## Guidelines - Search by task description, not element name ("arxiv search papers" not "search button") - **Use Action Manual selectors first** - they are pre-verified and don't require snapshot - Prefer CSS ID selectors (`#id`) over XPath when both are provided - **Fallback to snapshot when selectors fail** - use `actionbook browser snapshot` then CSS selectors from the output - Re-snapshot after navigation - DOM changes invalidate previous state - **Extension mode**: follow the full lifecycle — pre-flight → connect → execute → cleanup (see [Extension Mode Lifecycle](#extension-mode-lifecycle-critical)) - **Extension mode**: verify extension is installed before starting bridge; prefer auto-pair over manual token - **Extension mode**: always run `browser close` before stopping the bridge to release the debug connection - **Extension mode**: the user's real browser is being controlled — avoid destructive actions (clearing all cookies, closing all tabs) without confirmation - **Extension mode**: L3 operations (some cookie/storage modifications) may require manual approval in the extension popup ## Fallback Strategy ### When Fallback is Needed Actionbook stores pre-computed page data captured at indexing time. This data may become outdated as websites evolve: - **Selector execution failure** - The returned CSS/XPath selector does not match any element - **Element mismatch** - The selector matches an element with unexpected type or behavior - **Multiple selector failures** - Several selectors from the same action fail consecutively ### Fallback Approaches When Action Manual selectors don't work: 1. **Snapshot the page** - `actionbook browser snapshot` to get the current accessibility tree 2. **Inspect visually** - `actionbook browser screenshot` to see the current state 3. **Inspect by coordinates** - `actionbook browser inspect <x> <y>` to find elements 4. **Execute JS** - `actionbook browser eval "document.querySelector(...)"` for dynamic queries ### When to Exit If actionbook search returns no results or action fails unexpectedly, use other available tools to continue the task. ## Examples ### End-to-end with Action Manual ```bash # 1. Find selectors actionbook search "airbnb search" --domain airbnb.com # 2. Get detailed selectors (area_id from search results) actionbook get "airbnb.com:/:default" # 3. Automate using pre-verified selectors actionbook browser open "https://www.airbnb.com" actionbook browser fill "input[data-testid='structured-search-input-field-query']" "Tokyo" actionbook browser click "button[data-testid='structured-search-input-search-button']" actionbook browser wait-nav actionbook browser text actionbook browser close ``` ### Extension mode: Operate on user's Chrome ```bash # Verify bridge is running actionbook extension status # Use the user's existing logged-in session actionbook --extension browser open "https://github.com/notifications" actionbook --extension browser wait-nav actionbook --extension browser text ".notifications-list" actionbook --extension browser screenshot notifications.png ``` ### Extension Mode Lifecycle (CRITICAL) When using Extension mode, **always** follow this complete lifecycle: pre-flight → connect → execute → cleanup. #### 1. Pre-flight: Ask user about extension installation Before any technical checks, **ask the user** whether they have the Actionbook Chrome Extension installed. - **User confirms installed** → proceed to Step 2 (Connect). - **User says not installed** → run the installation flow: ```bash # Install extension files locally actionbook extension install actionbook extension path # → On macOS, copy to visible dir if needed: # cp -r "$(actionbook extension path)" ~/Document/actionbook-extension ``` Then guide the user to load it in Chrome: 1. Open `chrome://extensions` → enable Developer mode 2. Click "Load unpacked" → select the extension directory 3. After user confirms loaded → proceed to Step 2 > **Limitation:** The CLI can only verify that extension files exist locally. There is no way to detect whether Chrome has actually loaded the extension until a connection is attempted in Step 2. #### 2. Connect: Start bridge, auto-pair with retry Start the bridge server and attempt auto-pairing. **Retry up to 3 times** before considering manual fallback. ```bash # Start bridge (run in background) actionbook extension serve # Attempt 1: Wait for auto-pairing via Native Messaging sleep 3 actionbook extension ping # → If ping succeeds → proceed to Step 3 (Execute) # Attempt 2: If ping fails, wait longer and retry sleep 5 actionbook extension ping # → If ping succeeds → proceed to Step 3 (Execute) # Attempt 3: Final retry sleep 5 actionbook extension ping # → If ping succeeds → proceed to Step 3 (Execute) ``` **Only after all 3 auto-pair attempts fail**, escalate based on the error: - **"Extension not connected"** → Ask user to verify the extension is enabled in `chrome://extensions` and retry - **"Invalid token"** → Only now provide the token from `serve` output for manual paste in the extension popup - **Other errors** → Check `actionbook extension status` for diagnostics **IMPORTANT:** Do NOT expose the session token prematurely. The token is a last-resort fallback — most users will connect successfully via auto-pair within 3 attempts. #### 3. Execute: Browser automation ```bash actionbook --extension browser open "https://example.com" # ... perform browser operations ... ``` #### 4. Cleanup: Release debug connection, THEN stop bridge ```bash # Step 1: Release the debugging connection (MUST come first) actionbook --extension browser close # Step 2: Stop the bridge server actionbook extension stop # Step 3: Verify Chrome no longer shows "debugging" banner actionbook extension status # should show "not running" ``` **WARNING:** Skipping Step 1 and directly killing the bridge process will leave Chrome showing "Actionbook is debugging this browser". Always release the debug connection before stopping the bridge. ### Extension mode: Troubleshooting ```bash # Bridge not running? actionbook extension serve # Start it # Extension not responding? actionbook extension ping # Check connectivity # Token expired? (idle > 30 min) # Restart serve and re-pair in extension popup actionbook extension serve # Prints new token ``` ### Deep-Dive Documentation For detailed patterns and best practices: | Reference | Description | |-----------|-------------| | [references/command-reference.md](references/command-reference.md) | Complete command reference with all features | | [references/authentication.md](references/authentication.md) | Login flows, OAuth, 2FA handling, state reuse |internal/builtin_skills/actionbook/references/authentication.md5.3 KBa98daec88c41upstream ↗
# Authentication Patterns Patterns for handling login flows, session persistence, and authenticated browsing using the Actionbook Rust CLI. ## Basic Login Flow ```bash # Open login page actionbook browser open "https://app.example.com/login" actionbook browser wait-nav # Take snapshot to identify form elements actionbook browser snapshot # Fill credentials using CSS selectors from snapshot actionbook browser fill "#email" "$APP_USERNAME" actionbook browser fill "#password" "$APP_PASSWORD" # Submit actionbook browser click "button[type=submit]" actionbook browser wait-nav # Verify login succeeded by checking the current URL actionbook browser eval "window.location.href" ``` ## Profile-Based Session Persistence Profiles provide isolated browser sessions with separate cookies and storage. Use profiles to persist authentication across CLI invocations. ```bash # Create a dedicated profile for the target site actionbook profile create myapp # Login using that profile actionbook -P myapp browser open "https://app.example.com/login" actionbook -P myapp browser wait-nav actionbook -P myapp browser snapshot actionbook -P myapp browser fill "#email" "$APP_USERNAME" actionbook -P myapp browser fill "#password" "$APP_PASSWORD" actionbook -P myapp browser click "button[type=submit]" actionbook -P myapp browser wait-nav # Later: reuse the profile — session cookies are preserved actionbook -P myapp browser open "https://app.example.com/dashboard" actionbook -P myapp browser wait-nav actionbook -P myapp browser text "h1" # Should show dashboard content # List and inspect profiles actionbook profile list actionbook profile show myapp ``` ## OAuth / SSO Flows For OAuth redirects, use snapshot at each step to identify form elements: ```bash # Start OAuth flow actionbook browser open "https://app.example.com/auth/google" actionbook browser wait-nav # Google sign-in page — snapshot to find form elements actionbook browser snapshot actionbook browser fill "input[type=email]" "$GOOGLE_EMAIL" actionbook browser click "#identifierNext" actionbook browser wait-nav # Password step actionbook browser snapshot actionbook browser fill "input[type=password]" "$GOOGLE_PASSWORD" actionbook browser click "#passwordNext" actionbook browser wait-nav # Wait for redirect back to app (OAuth redirects can be slow) actionbook browser eval "window.location.href" # Should be app.example.com ``` ## Two-Factor Authentication Handle 2FA by running in headed mode (the default) and waiting for manual input: ```bash # Login with credentials (browser is visible by default) actionbook browser open "https://app.example.com/login" actionbook browser wait-nav actionbook browser snapshot actionbook browser fill "#email" "$APP_USERNAME" actionbook browser fill "#password" "$APP_PASSWORD" actionbook browser click "button[type=submit]" actionbook browser wait-nav # Wait for user to complete 2FA manually # Use a long timeout and wait for an element only present after 2FA actionbook browser wait ".dashboard-header" --timeout 120000 ``` ## Cookie-Based Auth Manually set authentication cookies: ```bash # Open the target domain first (cookies need a page context) actionbook browser open "https://app.example.com" actionbook browser wait-nav # Set auth cookie (use environment variable for the token value) actionbook browser cookies set "session_token" "$SESSION_TOKEN" --domain ".example.com" # Navigate to protected page actionbook browser goto "https://app.example.com/dashboard" actionbook browser wait-nav ``` ## Token Refresh Handling For sessions with expiring tokens: ```bash #!/bin/bash # Wrapper that handles token refresh using profiles PROFILE="myapp" # Try navigating directly with existing profile session actionbook -P "$PROFILE" browser open "https://app.example.com/dashboard" actionbook -P "$PROFILE" browser wait-nav # Check if session is still valid via URL URL=$(actionbook -P "$PROFILE" browser eval "window.location.href") if [[ "$URL" == *"/login"* ]]; then echo "Session expired, re-authenticating..." # Perform fresh login actionbook -P "$PROFILE" browser snapshot actionbook -P "$PROFILE" browser fill "#email" "$APP_USERNAME" actionbook -P "$PROFILE" browser fill "#password" "$APP_PASSWORD" actionbook -P "$PROFILE" browser click "button[type=submit]" actionbook -P "$PROFILE" browser wait-nav fi ``` ## Security Best Practices 1. **Use environment variables for credentials** — source from a `.env` file, not inline ```bash # Load from .env file (avoid typing secrets in the terminal) source .env # contains APP_USERNAME, APP_PASSWORD actionbook browser fill "#email" "$APP_USERNAME" actionbook browser fill "#password" "$APP_PASSWORD" ``` 2. **Protect profile directories** — profiles store cookies and session data on disk ```bash # Profile data is equivalent to passwords — restrict access chmod 700 ~/.config/actionbook/ ``` 3. **Clean up sessions after automation** ```bash actionbook browser cookies clear actionbook browser close ``` 4. **Delete profiles when no longer needed** ```bash actionbook profile delete myapp ``` 5. **Use headless mode for CI/CD** (no visible browser) ```bash actionbook --headless browser open "https://app.example.com/login" # ... login and perform actions ... actionbook browser close ```internal/builtin_skills/actionbook/references/command-reference.md8.6 KB613aa1e500b8upstream ↗
# actionbook Command Reference Complete reference for all `actionbook` CLI commands. ## Action Search & Retrieval ### search - Search for action manuals ```bash actionbook search "<query>" # Basic keyword search actionbook search "<query>" --domain site.com # Filter by domain actionbook search "<query>" --url <url> # Filter by specific URL actionbook search "<query>" -p 2 # Page 2 (default: 1) actionbook search "<query>" -s 20 # 20 results per page (default: 10, max: 100) actionbook search "<query>" --domain site.com --url <url> -p 1 -s 5 # Combined ``` Returns area IDs with descriptions and relevance scores. Use the area_id with `actionbook get` to fetch full details. ### get - Get action details by area ID ```bash actionbook get "<area_id>" # area_id format: "site.com:/path:area_name" # Examples: # actionbook get "airbnb.com:/:default" # actionbook get "github.com:/login:form" # actionbook get "arxiv.org:/search/advanced:default" ``` Returns complete action manual with CSS/XPath selectors, element types, and allowed methods. ### sources - List and search sources ```bash actionbook sources list # List all available sources actionbook sources search "<query>" # Search sources by keyword ``` ## Browser Automation ### Navigation ```bash actionbook browser open <url> # Open URL in new tab actionbook browser goto <url> # Navigate current page to URL actionbook browser goto <url> --timeout 5000 # Custom navigation timeout (default: 30000ms) actionbook browser back # Go back in history actionbook browser forward # Go forward in history actionbook browser reload # Reload current page actionbook browser pages # List all open pages/tabs actionbook browser switch <page_id> # Switch to specific page by ID actionbook browser close # Close the browser actionbook browser restart # Restart the browser actionbook browser connect <endpoint> # Connect to existing browser (CDP port or ws:// URL) actionbook browser status # Show detected browsers and session status ``` ### Element Interactions All interaction commands take CSS selectors. Use selectors from Action Manuals or from `snapshot` output. ```bash actionbook browser click "<selector>" # Click element actionbook browser click "<selector>" --wait 1000 # Wait 1s for element, then click actionbook browser fill "<selector>" "text" # Clear element, then type text actionbook browser fill "<selector>" "text" --wait 500 # Wait for element, then fill actionbook browser type "<selector>" "text" # Type text (append, no clear) actionbook browser type "<selector>" "text" --wait 500 # Wait for element, then type actionbook browser select "<selector>" "value" # Select dropdown option by value actionbook browser hover "<selector>" # Hover over element actionbook browser focus "<selector>" # Focus on element actionbook browser press <key> # Press keyboard key # Key examples: Enter, Tab, Escape, ArrowDown, ArrowUp, Backspace, Delete, Space ``` ### Information Retrieval ```bash actionbook browser text # Get full page text content actionbook browser text "<selector>" # Get text of specific element actionbook browser html # Get full page HTML actionbook browser html "<selector>" # Get outer HTML of specific element actionbook browser snapshot # Get accessibility snapshot (tree structure) actionbook browser viewport # Get viewport dimensions ``` ### Wait Conditions ```bash actionbook browser wait "<selector>" # Wait for element to appear actionbook browser wait "<selector>" --timeout 5000 # Custom timeout (default: 30000ms) actionbook browser wait-nav # Wait for navigation to complete actionbook browser wait-nav --timeout 10000 # Custom navigation timeout ``` ### Screenshots & Export ```bash actionbook browser screenshot # Save as screenshot.png actionbook browser screenshot output.png # Save to custom path actionbook browser screenshot --full-page # Full page screenshot actionbook browser pdf output.pdf # Export page as PDF ``` ### JavaScript & DOM Inspection ```bash actionbook browser eval "document.title" # Execute JavaScript, return result actionbook browser eval "document.querySelectorAll('a').length" actionbook browser inspect <x> <y> # Inspect DOM element at viewport coordinates actionbook browser inspect <x> <y> --desc "login btn" # With description hint ``` ### Cookie Management ```bash actionbook browser cookies # List all cookies (default) actionbook browser cookies list # List all cookies actionbook browser cookies get "<name>" # Get specific cookie by name actionbook browser cookies set "<name>" "<value>" # Set cookie actionbook browser cookies set "<name>" "<value>" --domain ".example.com" # Set with domain actionbook browser cookies delete "<name>" # Delete specific cookie actionbook browser cookies clear # Clear all cookies ``` ## Configuration ### config - Manage settings ```bash actionbook config show # Display full configuration actionbook config get <key> # Get specific config value actionbook config set <key> <value> # Set config value actionbook config edit # Open config in $EDITOR actionbook config path # Show config file location ``` **Config keys:** - `api.base_url` - API endpoint (default: https://api.actionbook.dev) - `api.api_key` - API authentication key - `browser.executable` - Browser path override - `browser.default_profile` - Default profile name - `browser.headless` - Headless mode (true/false) ### profile - Manage browser profiles ```bash actionbook profile list # List all profiles actionbook profile create <name> # Create new profile actionbook profile create <name> --cdp-port 9222 # With specific CDP port actionbook profile delete <name> # Delete profile actionbook profile show <name> # Show profile details ``` ## Global Flags These flags can be used with any command: ```bash actionbook --json <command> # Output in JSON format actionbook --headless <command> # Run browser in headless mode actionbook --verbose <command> # Enable verbose logging actionbook -P <profile> <command> # Use specific browser profile actionbook --cdp <port|url> <command> # Connect via CDP port or WebSocket URL actionbook --browser-path <path> <command> # Override browser executable path ``` ## Environment Variables ```bash ACTIONBOOK_API_URL="https://api.actionbook.dev" # API endpoint ACTIONBOOK_API_KEY="your-key" # API authentication key ACTIONBOOK_BROWSER_PATH="/path/to/chrome" # Browser executable ACTIONBOOK_CDP="9222" # CDP port or WebSocket URL ACTIONBOOK_PROFILE="default" # Default profile name ACTIONBOOK_HEADLESS="true" # Headless mode ``` ## Practical Examples ### Form Submission ```bash actionbook browser open "https://example.com/form" actionbook browser snapshot # Read the snapshot to find selectors actionbook browser fill "#email" "[email protected]" actionbook browser fill "#password" "password123" actionbook browser click "button[type=submit]" actionbook browser wait-nav actionbook browser text "h1" # Check result ``` ### Multi-page Navigation ```bash actionbook browser open "https://example.com" actionbook browser click "a[href='/products']" actionbook browser wait-nav actionbook browser click ".product-card:first-child a" actionbook browser wait-nav actionbook browser text ".product-details" actionbook browser screenshot product.png ``` ### Data Extraction ```bash actionbook browser open "https://example.com/data" actionbook browser wait-nav actionbook browser text ".results-table" # Get table text actionbook browser eval "JSON.stringify([...document.querySelectorAll('.item')].map(e => e.textContent))" actionbook browser close ``` ### Connect to Existing Browser ```bash # Start Chrome with debugging port # google-chrome --remote-debugging-port=9222 actionbook browser connect 9222 actionbook browser pages actionbook browser snapshot ```internal/builtin_skills/actionbook/references/extension-troubleshooting.md1.4 KB91dc30e7bd02upstream ↗
# Extension Troubleshooting Common issues and fixes for the Chrome Extension bridge. ## Bridge not running ```bash actionbook extension serve # Start the bridge ``` Keep `serve` running in a separate terminal — it is a foreground process. ## Extension not responding ```bash actionbook extension ping # Check connectivity ``` If ping fails, verify the extension is loaded in Chrome (`chrome://extensions`) and enabled. ## Token expired (idle > 30 min) Restart the bridge and re-pair in the extension popup: ```bash actionbook extension serve # Prints new token ``` Copy the token from output → paste in extension popup → Save. ## Stale port/token files **Symptoms:** bridge running but extension connects to wrong port, or "WebSocket handshake failed" errors in bridge output. **Cause:** previous `serve` process was killed ungracefully. **Fix:** restart `serve` — it auto-cleans stale files on startup: ```bash actionbook extension serve ``` ## Extension not installed ```bash actionbook extension install # Install extension files actionbook extension path # Get directory for Chrome "Load unpacked" ``` Then load in Chrome: `chrome://extensions` → Developer mode → Load unpacked → select the path. ## Uninstall extension ```bash actionbook extension uninstall # Remove extension files and native host registration ```README.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/smallnest-goclaw-internal-builtin-skills-actionbook.md