Agent Skills › actionbook/actionbook › actionbook

actionbook

GitHub

提供预计算的网站操作手册，包含页面描述、DOM结构和元素选择器。用于辅助浏览器自动化，快速获取CSS/XPath选择器以构建AI代理或执行UI交互任务。

playground/rust-learner/skills/actionbook/SKILL.md actionbook/actionbook

Trigger Scenarios

需要获取网页元素的CSS或XPath选择器构建基于浏览器的AI代理查找如何与特定网站UI进行交互

Install

npx skills add actionbook/actionbook --skill actionbook -g -y

More Options

Non-standard path

npx skills add https://github.com/actionbook/actionbook/tree/main/playground/rust-learner/skills/actionbook -g -y

Use without installing

npx skills use actionbook/actionbook@actionbook

指定 Agent (Claude Code)

npx skills add actionbook/actionbook --skill actionbook -a claude-code -g -y

安装 repo 全部 skill

npx skills add actionbook/actionbook --all -g -y

预览 repo 内 skill

npx skills add actionbook/actionbook --list

SKILL.md

Frontmatter

{
    "name": "actionbook",
    "description": "Access pre-computed website action manuals containing page descriptions, functionality, DOM structure, and element selectors for browser automation. Use when you need CSS\/XPath selectors for UI elements, building browser-based AI agents, or looking up how to interact with a website's UI."
}

Actionbook

Pre-computed action manuals for browser automation. Agents receive structured page information instead of parsing entire HTML.

Workflow

search_actions - Search by keyword, returns URL-based action IDs with content previews
get_action_by_id - Get full action manual with page details, DOM structure, and element selectors
Execute - Use returned selectors with your browser automation tool

MCP Tools

search_actions - Search by keyword. Returns: URL-based action IDs, content previews, relevance scores
get_action_by_id - Get full action details. Returns: action content, page element selectors (CSS/XPath), element types, allowed methods (click, type, extract), document metadata

Parameters

search_actions:

query (required): Search keyword (e.g., "airbnb search", "google login")
type: vector | fulltext | hybrid (default)
limit: Max results (default: 5)
sourceIds: Filter by source IDs (comma-separated)
minScore: Minimum relevance score (0-1)

get_action_by_id:

id (required): URL-based action ID (e.g., example.com/page)

Example Response

{
  "title": "Airbnb Search",
  "url": "www.airbnb.com/search",
  "elements": [
    {
      "name": "location_input",
      "selector": "input[data-testid='structured-search-input-field-query']",
      "type": "textbox",
      "methods": ["type", "fill"]
    }
  ]
}