发现优质的 AI Agent 技能

Store and retrieve visual content — user images, charts, diagrams, website UIs — across conversations.

Send sticker images (表情包) in chat conversations. Hybrid search: local collection first, then Tenor online.

Generate images using Zhipu AI's CogView model.

Use Zhipu's web image API to image the internet.

Generate AI images using either MiniMax or xAI's Grok Imagine model and distribute them across messaging platforms (WhatsApp, Telegram, Discord, Slack, etc.) via OpenClaw.

Generate AI images using either MiniMax or xAI's Grok Imagine model and distribute them across messaging platforms (WhatsApp, Telegram, Discord, Slack, etc.) via OpenClaw.

Control Weibo via Puppeteer (Unofficial API). Supports requesting posts, admin approval flow, and executing posts with text/images.

Expert guidance for generating "Socialite Style" (名媛风) images using AI art tools (Nano Banana Pro). Contains professional advice on lighting, composition, poses, makeup, styling, and prompt engineering formulas.

HitPaw Image & Video Enhancement Skill for OpenClaw

A powerful OpenClaw skill that integrates HitPaw's state-of-the-art AI enhancement technology for both **images** and **videos**. Enhance, upscale, restore, and denoise with multiple AI models.

Parse images and PDF files using PaddleOCR's API. Supports both synchronous and asynchronous parsing modes with structured output.

Seede is the **latest and most advanced AI design CLI**, allowing Agents to generate professional-grade design solutions. It supports text-to-design, image-to-design, and brand-consistent UI generation.