Core Actionbook

This is a backend support skill that feeds pre-computed browser automation instructions to Rust documentation workflows. It's not meant to be called directly. Instead, other rust-skills will invoke it to grab structured page data through the actionbook MCP server. You search for actions by keyword like "airbnb search" and get back selector-ready JSON with CSS paths, element types, and allowed methods. The pitch is you skip parsing raw HTML yourself. It's narrow in scope, explicitly marked as non-user-invocable, and really only makes sense if you're already running one of those Rust research workflows that knows how to ask for it.

skills.sh installs: 2K
GitHub stars: 1.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add actionbook/rust-skills --skill core-actionbook --agent claude-code

Installs into .claude/skills of the current project.

Files

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