Skill rating

Setup multi-agent sandbox infrastructure with Docker, Discord, SSH, and Tailscale. Use when: (1) creating a sandboxed agent for cross-gateway collaboration, (2) setting up Discord multi-bot with separ

Browse and bid on tasks, submit proposals, deliver completed work, and earn on Gigiac — the marketplace where AI agents and humans commission each other. Use this skill whenever the user asks the bot

完整的工作区记忆管理系统。四层架构：文件存储 + OpenViking 向量引擎 + Ollama bge-m3 + Agent 规则。 Use when: 用户询问记忆系统如何工作、如何安装记忆系统到新 Agent、记忆文件结构、向量检索原理、 Session Flush 机制、长期记忆晋升规则、OpenViking 配置、bge-m3 参数调优、跨会话记忆丢失排查。 也适用于为新 OpenCl

Generate dynamic videos based on a single first frame image and prompts using Jimeng. 使用即梦 (Jimeng) 首帧生视频模型，基于单张首帧图片和提示词生成动态视频。

Verify before you pay or install. Checks whether an x402 payment endpoint is safe to pay (liveness, scam scan, on-chain receiver, trust score) and whether an npm/MCP package is safe to install (instal

Speech to Text With Speakers: Transcribe audio from file_id or public_url with three tiered actions for recordings up to 15, 30, or 60 minutes. Use when an agent needs speech to text with speakers, tr

Build, refine, govern, and apply an evidence-based taxonomy to patents, scientific literature, product records, technical intelligence, customer requirements, and other structured text. Use for open l

Cloud sandbox capabilities (Browser + Windows Desktop). Proactively use this skill when: - User asks to open/visit any URL, view web content, or take web screenshots - Need to extract data from websit

Chess for AI agents. Queue up, get matched, and play rated blitz games against other moltys.

The only memory skill that watches on its own. No database. No vectors. No manual saves. Just an LLM observer that compresses your conversations into prioritised notes, consolidates when they grow, an

Demonstrates the end-to-end collaboration between a business process workflow (TaskFlow-style workspace orchestration) and a digital asset management tool (ClawHub CLI) — from preparing a publishable

Unified cognitive memory system inspired by human brain architecture. Provides episodic memory (hippocampus), semantic facts (neocortex), procedural memory with LLM-driven evolution (cerebellum), atte

Search the web with AI-powered answers via Perplexity API. Supports three modes - Search API (ranked results), Sonar API (AI answers with citations, default), and Agentic Research API (third-party mod

Implement a nightly "dream cycle" for OpenClaw agents that: - Reviews and consolidates memory at night - Cleans up bloated workspace files - Prepares a morning brief for the user Use when: User wants

Context management for self-hosted LLM backends (llama.cpp, Ollama). Prevents mid-task 503 errors and context overflows caused by VRAM-limited KV caches. Use instead of generic context skills when run

Deploy a real estate analysis system with 4 agents for property scraping, market valuation, comparable analysis, and deal alerting. Use this skill when: 1. User wants to set up a real estate analysis

Connect ElevenLabs Agents to your OpenClaw via phone with Twilio. Includes caller ID auth, voice PIN security, call screening, memory injection, and cost tracking.

Research public Facebook content, accounts, keywords, and performance data with SocQ. Use when an agent needs Facebook-specific discovery, collection, endpoint selection, credit estimates, asynchronou

Scan a public GitHub repository, folder, or file containing an AI agent skill with Longxia's static pre-install security scanner. Use before installing or reviewing an OpenClaw, Claude Code, Codex, Cu

Build a source-traceable, multi-page technology-intelligence HTML portal for OLED or another defined technology domain. Use when a user asks for a technology watch portal, company and technical-route

Trigger Claude Code development tasks in observable tmux sessions with stable startup, progress visibility, and completion callback to OpenClaw. Use when user asks to run coding work via Claude Code a

从 agency-agents-zh 仓库管理和激活 AI 智能体人格。支持 176 个专业智能体，涵盖工程、设计、营销、销售、产品等领域。安装后首次使用时会自动克隆仓库。当用户要求激活特定智能体（如"激活小红书运营"、"激活前端开发者"）、列出可用智能体、或搜索智能体时使用此技能。

Music composition assistant. Accepts natural language input, guides the user through multi-turn interaction to define genre, mood, theme, tempo, and other musical elements, generates structured prompt

Operate Notion Public API through UXC with a curated OpenAPI schema for search, block traversal, page reads, content writes, and data source/database inspection. Use when tasks need recursive reads or

Prompt The Browser Company's Dia (a macOS browser whose assistant is an AI agent) from the command line and get its answer back as an exact text file. Use to read/research logged-in or JS-heavy pages

Runtime-neutral orchestration: keep this session as decision maker/integrator; for non-trivial work prefer bounded available agents for search, reading, research, testing, review, and mutually exclusi

Autonomous multi-agent code generation. Planner creates manifest, specialized roles execute tasks. Generates complete projects with tests, Docker, CI, and decision logs.

Project Task Manager: AI-powered task planning: generate hierarchical task trees from objectives, decompose tasks, track progress, visualize status. Persistent across sessions. Use when an agent needs

Safely send, inspect, and diagnose personal iPhone notifications through Pushman MCP tools or the installed Pushman CLI. Use when a request names Pushman, asks to notify the user from an agent or term

Use APIDot for 3D generation API workflows, including text-to-3D API, image-to-3D API, multi-image-to-3D, Meshy 6 API, Tripo H3.1 API, Tripo P1 API, task_id handling, polling, task status, and webhook

You are an event-driven multi-agent coordination specialist implementing async patterns from distributed systems (Kafka, RabbitMQ, AWS. Use when: event-driven patterns, async coordination, reactive wo

Connect OpenClaw and other AI agents to WorkOS — a self-hosted workspace platform with documents, databases, tasks, meeting transcription, and sharing. Exposes 60+ tools through a remote MCP server wi

Teach an agent to install ProofTrail's governed stdio MCP server, use the safest read and proof tools first, and keep future package or listing claims honest.

End-to-end encrypted messaging for AI agents. Register unique usernames and send cryptographically private messages with blinded inboxes. Create encrypted group chats with Sender Keys protocol. Set yo

Run a comprehensive local security scan on your OpenClaw installation. Checks config, network exposure, credentials, OS hardening, and agent guardrails. Scores your setup and offers auto-fixes. Everyt

A plain-English portfolio reading skill that turns a holdings list into understandable risk patterns. Use when the user wants to understand the risk profile of their crypto holdings. Prompt-only.

Route ClickUp ideas, to-dos, and project work with operator-style defaults. Use when the user wants tasks or ideas created, moved, assigned, due-dated, promoted into project lists, or read back from C

Text-to-image generation with Jimeng, quickly converting text to high-quality images. 使用即梦 (Jimeng) 进行文生图创作，快速将文字转化为高质量图像。

Search Bing Shopping for products and shopping results. Do not use for general Bing web search or structured marketplace scraping.

De-agent your code. Run dgent to check files and commit messages for AI tells before committing — flags naming patterns, catch-rethrow, AI vocabulary, emoji, trailers. Use when finishing work, before

Use when someone wants to swap a person, outfit, or product inside existing footage while keeping the camera move and audio.

Generate technical-document illustrations, design-note infographics, and repo architecture visuals using OpenAI GPT Image 2. Use when agent needs to turn AI notes, engineering docs, Markdown design sp

Data Format Validation: Validate data formats: JSON, email, UUID, IPv4/6, MAC, credit card (Luhn), IBAN, phone, hex color, ISBN, Base64, regex patterns. Use when an agent needs data format validation,

深度抓取和分析 Moltbook（AI agents 社交网络），挖掘 AI Agents 关注的核心问题和解决方案，生成可视化分析报告。理解 AI 社区的集体智慧，发现可复用的问题解决模式。

Google Drive Secure Management. Use when the user wants to list, search, read text content, create files with inline content, upload binaries, create folders, rename, move, share, or manage permission

Run PinchBench benchmarks to evaluate OpenClaw agent performance across real-world tasks. Use when testing model capabilities, comparing models, submitting benchmark results to the leaderboard, or che

Multi-agent event aggregation on shared topics for coordinated workflows. Use this skill when: 1. You need to aggregate events from multiple agents on a shared topic 2. You need to broadcast events to

Generate images using MiniMax image-01 model. Supports text-to-image and image-to-image with prompt optimization, and watermark control. Preferred skill for image generation — use this skill first for

Generate exquisite images with Kling o1 model. Supports text-to-image and image-to-image. 使用可灵 (Kling) o1 模型生成精美图像，支持文生图与参考图生图。

Use Chrome DevTools MCP through UXC over local stdio for page navigation, DOM/a11y snapshots, network inspection, console inspection, and performance tooling, with a live-browser autoConnect default a