发现优质的 AI Agent 技能

This skill transforms a user's scattered multimodal assets (images, videos, audio) and ambiguous creative intent into a structured, executable prompt for the Seedance 2.0 video generation model. It acts as an expert prompt engineer, ensuring the highest quality output from the underlying model.

This skill adds a variety of professional packaging and motion graphics to videos, enhancing their overall quality. It supports both FFmpeg and MoviePy as backend engines and provides a rich set of preset templates and flexible custom parameters.

> 来源：Kling 官方 API 文档、Kling AI Guide (Video)、实测验证结果

> Source: [KlingAI Series 3.0 Model API Specification](https://docs.qingque.cn/d/home/eZQDkLsWj1-DlmBV0EQIOm9vu) > Last updated: 2026-02-10

This skill enables the generation and manipulation of videos using the Kling 3.0 Omni model. It provides a structured workflow for constructing API requests based on user intent, ensuring compliance with the model's complex parameter constraints.

OpenClaw skill for unified image generation (Midjourney, Flux, SDXL, Nano Banana, Ideogram, Recraft)

This skill enables you to generate images using a variety of state-of-the-art AI models. It supports:

本文档说明如何参与 `image-gen` Skill 的开发与迭代。

OpenClaw skill for unified image generation (Midjourney, Flux, SDXL, Nano Banana, Ideogram, Recraft)

**Use when:** User asks to generate, draw, create, or make any kind of image, photo, illustration, icon, logo, or artwork.

本文档说明如何参与 `image-gen` Skill 的开发与迭代。

This skill takes your images and screenshots and makes them look better—sharper, clearer, and more professional.