Agent Skills · Design & Media
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
Generates text-free cover backgrounds for book PDFs while preserving vector text, barcodes, and solid fills, then outputs a layered PDF and PNG.
Upload a design screenshot or brief, then get scores and actionable suggestions across visual hierarchy, information architecture, cognitive load, and emotional resonance.
Generates a 1080P virtual-singer MV from audio, lyrics, storyboard, and reference images via an AI production pipeline.
Drive GPT-Image-2 via Codex CLI with scene-specific templates to generate concise prompts for hero images, posters, models, and social assets.
A GraphicsMagick-based command-line image tool for format conversion, resizing, color adjustment, GIF animation, batch processing, and common presets.
A front-end video subtitle timing tool that uses F-key marking, frame stepping, and Markdown export to create subtitle templates.
Turn product stills into per-frame detail clips, referencing public Instagram Reels and generating short silent videos.
Locally converts humming or audio melodies into MIDI and optionally generates complete songs without uploading recordings.
An image generation capability for agents that supports text-to-image and reference-image workflows via async task polling, with per-call billing.
Generate and save images such as illustrations, posters, and social media graphics through the OpenAI-compatible Images API for Jiema GPT Image.
Upload a portrait to run Python retouching with style preview, smoothing, color grading, and upscaling, without Photoshop.
An engineering-driven solution that integrates design styles, UX workflows, design systems, and multi-platform implementation to solve cross-project design consistency.