actionbook
Activate when the user needs to interact with any website — browser automation, web scraping, screenshots, form filling, UI testing, monitoring, or building AI agents. Provides pre-verified page actions with step-by-step instructions and tested selectors.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- actionbook
- description
- Activate when the user needs to interact with any website — browser automation, web scraping, screenshots, form filling, UI testing, monitoring, or building AI agents. Provides pre-verified page actions with step-by-step instructions and tested selectors.
03 SKILL.md 正文
When to Use This Skill
Activate when the user's request involves interacting with a website:
Activate when the user:
- Needs to do anything on a website ("Send a LinkedIn message", "Book an Airbnb", "Search Google for...")
- Asks how to interact with a site ("How do I post a tweet?", "How to apply on LinkedIn?")
- Wants to fill out forms, click buttons, navigate, search, filter, or browse on a specific site
- Wants to take a screenshot of a web page or monitor changes
- Builds browser-based AI agents, web scrapers, or E2E tests for external websites
- Automates repetitive web tasks (data entry, form submission, content posting)
- Wants to control their existing Chrome browser (Extension mode)
What Actionbook Provides
Actionbook is a library of pre-verified page interaction data. actionbook search finds actions matching a task description; actionbook get "<ID>" returns a structured document describing a page's purpose, functional capabilities, and DOM structure with inline CSS selectors — eliminating the need for runtime page structure discovery.
search and get
search — Find actions by task description
actionbook search "<query>" # Search by task intent
actionbook search "<query>" --domain site.com # Filter by domain
actionbook search "<query>" --url <url> # Filter by URL
actionbook search "<query>" -p 2 -s 20 # Pagination
Returns for each result:
ID— use withactionbook get "<ID>"to retrieve full detailsType—page(full page) orarea(page section)Description— page overview and function summaryURL— page where this action appliesHealth Score— selector reliability percentage (0–100%)Updated— last verified date
Constructing an effective search query
The query string is the primary signal for finding the right action. Pack it with the user's full intent — not just a site name or a vague keyword.
Include in the query:
- Target site — the website name or domain
- Task verb — what the user wants to do (search, book, post, filter, login, compose, etc.)
- Object / context — what they're acting on (listings, messages, flights, repositories, etc.)
- Specific details — any constraints, filters, or parameters the user mentioned (dates, location, category, language, etc.)
Rule of thumb: Rewrite the user's request as a single descriptive sentence and use that as the query.
| User says | Bad query | Good query |
|---|---|---|
| "Book an Airbnb in Tokyo for next week" | "airbnb" |
"airbnb search listings Tokyo dates check-in check-out guests" |
| "Search arXiv for recent NLP papers" | "arxiv search" |
"arxiv advanced search papers NLP natural language processing recent" |
| "Send a LinkedIn connection request" | "linkedin" |
"linkedin send connection request invite someone" |
| "Post a tweet with an image" | "twitter post" |
"twitter compose new tweet post with image media attachment" |
| "Filter GitHub issues by label" | "github issues" |
"github repository issues filter by label search issues" |
When the user provides extra context (e.g., specific dates, a city name, a topic), fold it into the query even if it won't match a stored action literally — it helps the search engine rank relevant pages higher.
# User: "Help me apply for a software engineer job on LinkedIn"
actionbook search "linkedin job search apply software engineer application form"
# User: "I need to search for machine learning papers on arXiv"
actionbook search "arxiv advanced search papers machine learning subject category"
If --domain or --url is known, always add them — they narrow results and improve precision.
get — Retrieve full action details by ID
# Use the ID from search results directly
actionbook get "arxiv.org:/search/advanced:default"
Returns a structured document with:
- Page URL — exact URL and query/path parameters
- Page Overview — what the page does
- Page Function Summary — interactive capabilities (e.g., "Search Term Input", "Subject Classification Filtering")
- Page Structure Summary — DOM hierarchy with CSS selectors inline
Selectors appear embedded in the structure description, e.g.:
Search Term Form Section: Contains search term input field (input[type="text"]),
field selector dropdown (select[name="searchtype"]), and submit button (button.Search)
Extract CSS selectors from the structure summary for use with browser commands.
Browser Commands
Quick reference. Full details with all flags and options: command-reference.md.
Navigation
actionbook browser open <url> # Open URL in new tab
actionbook browser goto <url> # Navigate current page
actionbook browser back / forward # History navigation
actionbook browser reload # Reload page
actionbook browser pages # List open tabs
actionbook browser switch <page_id> # Switch tab
actionbook browser close # Close browser
Interactions
actionbook browser click "<selector>" # Click element
actionbook browser fill "<selector>" "text" # Clear and type
actionbook browser type "<selector>" "text" # Append text
actionbook browser select "<selector>" "value" # Select dropdown option
actionbook browser hover "<selector>" # Hover
actionbook browser press Enter # Press key
Observation
actionbook browser text # Full page text
actionbook browser text "<selector>" # Element text
actionbook browser snapshot # Accessibility tree (live page structure)
actionbook browser screenshot # Save screenshot
actionbook browser screenshot --full-page # Full page screenshot
actionbook browser wait "<selector>" # Wait for element
actionbook browser wait-nav # Wait for navigation
actionbook browser close cleans up the browser session. Skip if the user requests the browser remain open.
Examples
User request: "Search arXiv for papers about Neural Networks, search in titles only"
# 1. Search — include the full intent: site + task + subject + filter preference
actionbook search "arxiv advanced search papers neural network title field" --domain arxiv.org
# 2. Get details — read Page Structure Summary for selectors
actionbook get "arxiv.org:/search/advanced:default"
# Response includes: input[type="text"], select[name="searchtype"], button.Search, etc.
# 3. Automate using selectors from the response
actionbook browser open "https://arxiv.org/search/advanced"
actionbook browser fill "input[type='text']" "Neural Network"
actionbook browser select "select[name='searchtype']" "title"
actionbook browser click "button.Search"
actionbook browser wait-nav
actionbook browser text
actionbook browser close
Fallback
Actionbook stores page data captured at indexing time. Websites evolve, so selectors may become outdated.
When a selector from actionbook get fails at runtime, actionbook browser snapshot provides the live accessibility tree with current selectors. Use selectors from the snapshot output to retry the interaction.
Selectors used in browser commands should come from actionbook get or actionbook browser snapshot output in the current session — not from prior knowledge or memory.
If actionbook search returns no results for a page, use snapshot as the primary source, or fall back to other available tools.
References
| Reference | Description |
|---|---|
| command-reference.md | Complete command reference with all flags and options |
| authentication.md | Login flows, OAuth, 2FA handling, session persistence |
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.