Agent Skills · Design & Media
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
A Python 2/3-related skill tagged for GitHub and automation.
Use vidu-cli to call Vidu for text-to-image, text-to-video, image-to-video, start-end frames, reference generation, and async task queries.
Compiles visual ideas into copy-ready, model-native image prompts across major domestic and overseas image models, with reference classification, compliance checks, anti-AI-flavor rewriting, and iteration guidance.
Assigns fixed voices to named characters in a vertical short drama episode and delivers labeled dialogue clips in script order.
Generates images from prompts and aspect ratios with controlled call counts, size mapping, key reuse, and structured results.
Design Eye is a visual design reasoning engine that converts a theme into style decisions, master references, and bilingual image-generation prompts.
An async Agnes Video v2.0 API skill supporting text-to-video, image-to-video, multi-image, and keyframe workflows with task polling for the video URL.
Creates and polls Image2 text-to-image or image-to-image tasks with key handling, validation, and final result retrieval.
Generates heartfelt greeting-card messages for occasions and recipient relationships, with bilingual, multi-style, and length-adjusted options; visual design excluded.
Search Yiqixiu long-page H5 templates for landing pages by keyword and return titles, preview links, descriptions, and view counts.
Generate action videos from static character images with Jimeng Dream Actor via the dLazy CLI, including auth, uploads, and async task handling.
Create Future Vision image generation tasks with prompts, model types, sizes, and reference images, then poll task status.