Agent Skills · Design & Media
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
Fast dLazy API image generation with text-to-image and image-to-image support.
Convert themes and dimensions into editable Canva posters, covers, or social media graphics via Canva Connect API/MCP and return an edit link.
Upload a palm photo to detect major palm lines, generate a traditional palmistry reading and a labeled illustration, for entertainment only.
Use Volcano Engine Ark's Doubao Seedream model for text-to-image, image-to-image, and multi-image fusion with customizable size and local saving.
An engineer-focused color toolkit for encoding conversion, contrast checks, accessibility guidance, palette generation, HTML previews, and smart color recommendations, using Python standard libraries.
Locally converts notes, articles, or text into Douyin-style 9:16 talking-head short videos with script, images, TTS, subtitles, and Remotion rendering.
Call Jimeng 4.6 via Volcengine Visual Intelligence for text-to-image, image-to-image, task lookup, and image download.
A five-stage confirmation workflow for interior renders using Jimeng, DeepSeek, SU/V-Ray, and ComfyUI/Flux for base maps, material balls, and six-face control.
Local CLI for Coze Coding that calls image, video, speech, search, LLM, and embedding integration APIs while handling PAT and project context.
Collects ratio, titles, scene, and core metaphor, then generates calm, geometric minimalist art posters.
Expands brief image requests into detailed English prompts and generates 1024×1024 images via the Pollinations Flux API.
A Remotion-based video animation workflow covering project setup, component animation, TTS audio integration, quality checks, and rendering.