Agent Skills · Design & Media
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
Automatically analyzes PPT, image, text, and video assets to generate a 1080p MP4 with AI voiceover and subtitles, plus an editable JianYing draft compatible with v5.9, v10.9, and v11.2.
Upload a reference portrait and choose red, white, or blue to generate a standard ID photo with a solid background and return an image URL.
Wraps Wasu's proxied Seedance video generation API with one-prompt or HTML config workflows, model selection, first/last frames, reference assets, credential caching, and video download.
Guides step-by-step parameter collection, drawing generation, and production status tracking.
Generate 8 to 20 tagged voice clips from a written credit-card benefits table.
Turn real stories and emotions into Suno-ready lyrics, Style prompts, metadata, and multilingual song or instrumental plans.
Recognize Chinese text fonts, OCR text, and candidate fonts from an image and render a local HTML result.
Batch image compression, watermarking, format conversion, resizing, stitching, EXIF editing, and renaming for e-commerce, creators, and photographers.
Generates practical color systems for UI, brand, posters, and data visualization with concrete values, roles, usage ratios, palette logic, light/dark variants, and accessibility notes.
Guides step-by-step configuration of Baiyin video generation, including model selection, media input, prompt polish, task submission, and status polling.
Generate videos via Thingo using Doubao Seedance, supporting text-to-video, image-to-video, and video extension/editing with local MP4 download.
An end-to-end workflow for brand IP character design, covering research, concepting, visual settings, creative brief, and demo video production, with data sourcing, multiple concepts, parameterized proportions, and character consistency.