Agent Skills · Design & Media
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
Generate 720p WorkRally videos from text or one reference image after paid WeChat Pay authorization.
Asynchronously generates 9-grid or 16-grid emoji sheets from a reference image and prompt, then splits them into individual sticker assets.
Generate WeChat sticker packs with Gemini or Qwen: collect character and style inputs, draw grid images, slice and remove backgrounds, then export album assets.
Generate video effects from person-outlined images using Tencent Cloud's TemplateToVideo API, with options for resolution, background music, and polling.
Use the dLazy CLI to generate short videos with Google Veo 3.1 Fast from text or image prompts, with async task status polling.
Automatically generates original instrumental background music that matches the emotional tone of a scene based on user-provided descriptions for short videos and other media.
Use Tencent Cloud's SegmentPortraitPic API to detect human outlines and generate portrait cutouts from images.
A Claude Code tool for generating Draw.io charts such as flowcharts, swimlanes, ER diagrams, and architecture diagrams with Chinese fonts, themes, sizes, and export formats.
Invoke the Kling O1 model via the dLazy API for text-to-image and image-to-image workflows.
Run Nano Banana Pro via the dLazy CLI for text-to-image and image-to-image generation, with API key auth, async tasks, and error handling.
Generate multilingual, natural audio with Gemini 2.5 TTS through the dLazy API, including async task handling and error messages.
Generate high-fidelity multi-screen mini program UI group images on one canvas with structure planning, prompt construction, polling, and consistency scoring.