Actionbook actionbook
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.
install
source · Clone the upstream repo
git clone https://github.com/actionbook/actionbook
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/actionbook/actionbook "$T" && mkdir -p ~/.claude/skills && cp -r "$T/playground/rust-learner/skills/actionbook" ~/.claude/skills/actionbook-actionbook-actionbook-3979a1 && rm -rf "$T"
manifest:
playground/rust-learner/skills/actionbook/SKILL.mdsource content
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 by keyword. Returns: URL-based action IDs, content previews, relevance scoressearch_actions
- Get full action details. Returns: action content, page element selectors (CSS/XPath), element types, allowed methods (click, type, extract), document metadataget_action_by_id
Parameters
search_actions:
(required): Search keyword (e.g., "airbnb search", "google login")query
:type
|vector
|fulltext
(default)hybrid
: Max results (default: 5)limit
: Filter by source IDs (comma-separated)sourceIds
: Minimum relevance score (0-1)minScore
get_action_by_id:
(required): URL-based action ID (e.g.,id
)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"] } ] }