Core Actionbook
- 738 installs
- 1.4k repo stars
- Updated May 24, 2026
- actionbook/rust-skills
core-actionbook is an internal agent skill that exposes actionbook MCP selectors for developers whose rust-skills workflows need structured page manuals instead of parsing full HTML for docs.rs and crate research.
About
core-actionbook is an internal support skill in actionbook/rust-skills that connects agents to the actionbook MCP server for pre-computed browser action manuals. Instead of parsing entire HTML pages, agents call search_actions with a keyword and get_action_by_id to retrieve URL-based action IDs, content previews, CSS or XPath selectors, element types, and allowed methods such as click, type, and extract. The three-step workflow is search, fetch the manual, then execute selectors with a browser automation tool such as agent-browser. Parameters include hybrid vector or fulltext search, a default limit of five results, optional sourceIds filters, and minScore thresholds. The skill is user-invocable false and should load only when another rust-skills workflow explicitly requests actionbook-backed selectors. Developers reach for core-actionbook when rust-learner or related rust-skills agents need reliable docs.rs, crates.io, or release-page extraction during Rust research automation.
- Shared action trait contracts
- Composable handler modules
- CLI and agent entrypoints
- Error and telemetry hooks
- Actionbook crate conventions
Core Actionbook by the numbers
- 738 all-time installs (skills.sh)
- Ranked #27 of 121 Rust skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/actionbook/rust-skills --skill core-actionbookAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 738 |
|---|---|
| repo stars | ★ 1.4k |
| Last updated | May 24, 2026 |
| Repository | actionbook/rust-skills ↗ |
How do rust-skills agents fetch DOM selectors?
Implement reusable Rust action primitives and handlers that power agent workflows, terminal tools, and composable automation inside actionbook projects.
Who is it for?
Developers running actionbook/rust-skills agent workflows that need structured browser selectors for Rust documentation and crate research.
Skip if: Engineers building unrelated frontend features or invoking skills manually should skip core-actionbook because it is internal-only and disable-model-invocation.
When should I use this skill?
Another rust-skills workflow explicitly requests actionbook-backed selectors for Rust documentation or crate page automation.
What you get
Actionbook action IDs, element selector maps, and browser-ready extraction manuals for Rust documentation pages.
- Actionbook action ID matches
- DOM selector manuals
- Browser-ready extraction steps
By the numbers
- Documents 2 actionbook MCP tools: search_actions and get_action_by_id
- Default search_actions result limit is 5
Files
Actionbook
Pre-computed action manuals for browser automation. Agents receive structured page information instead of parsing entire HTML.
Workflow
1. search_actions - Search by keyword, returns URL-based action IDs with content previews 2. get_action_by_id - Get full action manual with page details, DOM structure, and element selectors 3. Execute - Use returned selectors with your browser automation tool
MCP Tools
search_actions- Search by keyword. Returns: URL-based action IDs, content previews, relevance scoresget_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"]
}
]
}policy:
allow_implicit_invocation: false
Related skills
Rust Async PatternsGenerate correct, production-grade async Rust code using Tokio, async-trait, channels, streams and proper error handling.16.6k38.5k
Rust Best PracticesGet concise, high-signal Rust style guidance that an agent can apply directly to code suggestions and reviews.15.1k101
Tauri V2Get expert guidance when creating cross-platform desktop and mobile apps using web technologies and Rust.6.7k14
Rust TestingGenerate comprehensive Rust tests following TDD with unit, integration, async, property-based, and mocked tests.6.1k238kRust PatternsGenerate and review idiomatic Rust code that follows ownership rules, error handling conventions, and concurrency best practices.5.7k238k
Rust SkillsEnsure every line of Rust they generate follows battle-tested idioms for ownership, error handling, performance and API design.4k380How it compares
Pick core-actionbook over generic browser skills when rust-skills workflows already depend on actionbook pre-computed page manuals.
FAQ
When should agents load core-actionbook?
Agents should load core-actionbook only when another actionbook/rust-skills workflow explicitly requests actionbook-backed selectors; the skill is internal, user-invocable false, and not meant for direct user invocation.
What do actionbook MCP tools return?
core-actionbook wraps actionbook MCP tools that return URL-based action IDs, content previews, DOM selectors as CSS or XPath, element types, allowed methods like click and extract, and document metadata for browser automation.
What is the core-actionbook workflow?
core-actionbook follows search_actions by keyword, get_action_by_id for the full manual, then execute returned selectors with a browser automation tool such as agent-browser inside rust-skills research flows.