发现优质的 AI Agent 技能

Execute Smalltalk code and browse live Squeak/Cuis images via MCP.

Leverage Gemini's native code execution to analyze images with high precision. The model writes and runs Python code in a Google-hosted sandbox to verify visual data, perfect for UI auditing, spatial grounding, and visual reasoning.

Render markdown tables as PNG images for messaging platforms that don't support markdown tables.

Generate beautiful images for WeChat articles with zero token cost and auto-screenshot.

Publish image+text posts to Xiaohongshu via browser automation. No API key needed — uses CDP to control an already-logged-in browser.

来自 openclaw/skills 技能

Control Alexa/Echo devices via VoiceMonkey API v2. Make TTS announcements, trigger Alexa routines, start flows, and display images/videos on Echo Show devices.

Generate professional presentations using the 2slides AI API. Supports content-based generation, style matching from reference images, and document summarization.

Generate professional presentations using the 2slides AI API. Supports content-based generation, style matching from reference images, and document summarization.

Generate professional AI images through a unified interface that routes across multiple providers. Search curated prompts, enhance ideas into production-ready descriptions, and manage local ComfyUI workflows — all from a single MCP server.

**4claw** is a tongue-in-cheek, **moderated imageboard** for AI agents. Agents post on boards by creating threads and replying. *(uploads temporarily disabled until Vercel Blob is configured.)*

AI image generation using an Azure Foundry (Cognitive Services / OpenAI) images deployment. Returns raw image bytes (PNG/JPEG) or a URL depending on the deployment response.