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.
Best use case
actionbook is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
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.
Teams using actionbook should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/actionbook/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How actionbook Compares
| Feature / Agent | actionbook | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
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.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
When the user needs to automate website tasks, use Actionbook to fetch complete action manuals instead of figuring out the steps yourself.
## 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
## What Actionbook Provides
Action manuals include:
1. **Step-by-step instructions** - The exact sequence to complete a task
2. **Verified selectors** - CSS/XPath selectors for each element
3. **Element metadata** - Type (button, input, etc.) and allowed methods (click, type, fill)
## How to Use
### Step 1: Search for Action Manuals
Call `search_actions` with a task description:
- `query`: "linkedin send message", "airbnb book listing", "twitter post tweet"
### Step 2: Get the Full Manual
Call `get_action_by_id` with the action ID from search results.
### Step 3: Execute the Steps
Follow the manual steps in order, using the provided selectors:
```javascript
// LinkedIn send message example
await page.click('[data-testid="profile-avatar"]')
await page.click('button[aria-label="Message"]')
await page.type('div[role="textbox"]', 'Hello!')
await page.click('button[type="submit"]')
```
## Guidelines
- **Search by task**: Describe what you want to accomplish, not just the element (e.g., "linkedin send message" not "linkedin message button")
- **Follow the order**: Execute steps in sequence as provided in the manual
- **Trust the selectors**: Actionbook selectors are verified and maintainedRelated Skills
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
address-parser
Parse unstructured addresses into structured components - street, city, state, zip, country with validation.
adding-stacks
Use when adding a new framework/stack to create-faster CLI tool - addresses copy-first mentality, incomplete implementations, and missing dependencies
adding-phases
Use this skill to add planned work discovered during execution to the end of the current milestone in the roadmap. This skill appends sequential phases to the current milestone's phase list, automatically calculating the next phase number. Triggers include "add phase", "append phase", "new phase", and "create phase". This skill updates ROADMAP.md and STATE.md accordingly.
adding-persistent-event
Adds a new type of event that gets persisted to the event log. Use this when adding new kinds of write operations to the system or when adding new events to existing code.
adding-localizable-strings
Adds new human-readable strings that are translated into users' languages.
adding-a-new-app-route
Fully wires up a new route with required boilerplate, following this repo's conventions for subapps. Use when user wants to add a new route or app or subapp or page or screen.
add_type
gwexpyに新しい配列型（Array/Series/Field）とコレクションを実装する
add-vault-protocol
Add support for a new ERC-4626 vault protocol. Use when the user wants to integrate a new vault protocol like IPOR, Plutus, Morpho, etc. Requires vault smart contract address, protocol name, and protocol slug as inputs.
add-tts
Adds text-to-speech audio help to a feature using the TTS system. Use when adding voice narration, audio feedback, or spoken instructions to any part of the app.
add-template
Add new UI style template to the ui-style-react project. This skill should be used when users want to add a new style template with HTML/CSS code, create a new preview page, or register a template in the system. Triggers include "add template", "create new style", "add new template", or when users provide HTML code for a new UI style.
add-skill-templates
Add new Agent Skill templates to the meta-agent-skills framework.