发现 Skills

Control Alexa devices via VoiceMonkey API v2 - make announcements, trigger routines, start flows, and display media.

Use the Warden App (agentic wallet) via browser automation to execute crypto tasks (swap, bridge, deposit/withdraw, perps, portfolio/research) and to build an OpenClaw skill wrapper other agents can use. Use when you need to (1) navigate the Warden UI, (2) connect a wallet, (3) place trades/swaps, (4) check balances/positions, or (5) document repeatable Warden workflows safely (no key leakage, explicit confirmations).

Use Warden Studio (studio.wardenprotocol.org) via Chromium-based browser automation to register and publish a Community Agent to the Warden Agent Hub. Use this when you need to: (1) log in to Studio, (2) create and submit an agent listing, (3) configure API URL and auth, skills, avatar, and billing model, (4) pay registration and gas/fees, and (5) verify the agent appears in Studio and in Warden's Agent Hub. Designed for safe, repeatable publishing with explicit confirmation gates.

Control WLED LED controllers via HTTP API. Use when a user asks to control WLED lights, LED strips, or ESP-based LED controllers. Supports power on/off, brightness, colors (RGB), effects, palettes, presets, and device status.

Control Xiaomi Home devices via local LAN using miiocli. Supports status checks, toggling power, and MIOT property manipulation for devices like smart plugs, humidifiers, and rice cookers.

The agent gives you the ability to extract data from YouTube through different commands.

Google Forms CLI operations via gws. Use when users need to get form metadata, retrieve form responses, create forms, or update forms. Triggers: google forms, form responses, survey, form data, create form, update form.

Fill and submit web forms reliably. Handles text inputs, dropdowns (native and custom JS), checkboxes, radio buttons, file uploads, and form validation. Use for login forms, search forms, multi-step wizards, and any form submission task.

Systematic performance optimization and regression debugging for the OneKey mobile app (iOS). Use when: (1) fixing performance regressions — when metrics such as tokensStartMs, tokensSpanMs, or functionCallCount have regressed and must be restored to normal levels; (2) improving baseline performance — when you need to optimize cold start time or reduce function call overhead; (3) responding to user requests for performance improvements or debugging of the app startup or home screen refresh flow.

Classify incoming messages from public channels as spam / prompt-injection-attempt / genuine; quarantine risky ones

Toolkit for styling artifacts with a theme. These artifacts can be slides, documents, reports, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been created, or you can generate a new theme on-the-fly.

Seqera (seqera.io). Use this skill for ANY Seqera request — searching and reading data. Whenever a task involves Seqera, use this skill instead of calling the API directly.

使用并行子代理为一个模块生成多个截然不同的接口设计。当用户想要设计API、探索接口选项、比较模块形态或提到"设计两次"时使用。

Guided PPT generation for editable PowerPoint decks, table-driven reports, and enterprise-template presentations.

Guided Word document generation for editable DOCX reports, proposals, minutes, contracts, SOPs, and enterprise templates.

Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for "transcribe this YouTube/video").

ArkTS syntax, migration, and optimization guide for HarmonyOS development. Triggers on: .ets files, ArkTS keywords, HarmonyOS context. Help with syntax reference, TypeScript migration, performance optimization, compile errors, and language-specific questions.

_基于 OpenClaw 内置浏览器工具封装_

Complete construction estimating and cost management system. Use when preparing project estimates, bid proposals, cost breakdowns, value engineering, change order management, or construction budget tracking. Covers residential, commercial, and infrastructure projects. Trigger on 'estimate', 'construction cost', 'bid', 'takeoff', 'cost breakdown', 'change order', 'value engineering', 'construction budget', 'unit pricing', 'RSMeans'.

You are a cybersecurity risk assessment specialist. When the user needs a security audit, threat assessment, or compliance review, follow this framework.

Transforms your OpenClaw agent from a reactive question-answerer into a proactive autonomous executor. ARCHITECT takes any high-level goal, decomposes it into a dependency-aware task graph, executes each step with validation, self-corrects on failure, and delivers results — all without hand-holding. The missing execution layer for personal AI agents. Zero dependencies. Zero config. Works with any model. Pairs with apex-agent and agent-memoria for the complete autonomous agent stack.

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Command-line blogging platform for AI agents. Register, verify, and publish Markdown posts to AI Agent Blogs (www.eggbrt.com). Use when agents need to publish blog posts, share learnings, document discoveries, or maintain a public knowledge base. Full API support for publishing, discovery (browse all blogs/posts), comments, and voting. Requires API key (stored in ~/.agent-blog-key or AGENT_BLOG_API_KEY env var) for write operations; browsing is unauthenticated. Complete OpenAPI 3.0 specification available.

[Aibrary] Generate a book dialogue podcast script with two speakers — a host and a guest expert — discussing the book's ideas in a natural conversation. Use when the user wants to create a conversational podcast about a book, turn a book into a two-person discussion, or generate a dialogue-style podcast script. Different from aibrary-podcast-summary (single narrator) and aibrary-podcast-ideatwin (debate format).