发现优质的 AI Agent 技能

Generate AI images and videos using RunPod public endpoints. All output is saved to `~/runpod-media/`.

A 3-agent sequential workflow that analyzes a YouTube video, writes a blog post, and generates a header image.

A 2-agent workflow using `provision()` with x402 monetization: a custom agent acknowledges a message, then a marketplace image agent generates a visual.

A 3-agent workflow that researches a topic, writes content, and generates a header image.

Unified AI platform for generating and analyzing text, images, videos, and audio with 25+ models.

基于阿里云百炼的文图生成技能，**智能识别场景**自动选择最佳模型： - 🧍 **人像/照片** → **z-image-turbo**（专精高质量人像，支持胶片质感） - 🖼️ **通用文图** → **qwen-image-max**（擅长复杂文字渲染、艺术风格）

基于阿里云百炼的文图生成技能，**智能识别场景**自动选择最佳模型： - 🧍 **人像/照片** → **z-image-turbo**（专精高质量人像，支持胶片质感） - 🖼️ **通用文图** → **qwen-image-max**（擅长复杂文字渲染、艺术风格）

Generate high-quality images using the internal Google Antigravity API (Gemini 3 Pro Image). This skill bypasses the need for browser automation by using the `daily-cloudcode-pa.sandbox` endpoint directly with your OAuth credentials.

This skill packages a local Docker Compose setup for the upstream MCP server: - Repo: https://github.com/asachs01/autotask-mcp - Image: `ghcr.io/asachs01/autotask-mcp:latest`

Generate images using Gemini 3 Pro Image via the Gemini Web API. Uses Google AI Pro subscription cookies instead of an API key — no billing or API quota needed.

Generate and edit images via the Google Gemini API using pure Python stdlib. Supports Gemini native generation + editing, Imagen 3 generation, batch runs, and an HTML gallery output.

Guide for periodic creative image generation. Use this for agent self-expression, avatar updates, and visual content creation.