Agent Skills · Design & Media
Curated skills for Claude, Cursor and other AI agents. Copy one prompt to install.
Turn prompts, images, video, or audio into deliverable videos with generation, editing, and extension, plus automatic task tracking and download.
Asynchronously generates face analysis, up to nine makeup steps, a nine-panel guide image, and a consistent effect image from a bare-face photo and theme.
Generates Jimeng AI image and video prompts for cinematic scenes with negative prompts, camera moves, lighting, composition, and parameter weights.
A tool-oriented wrap for SD WebUI, focused on tooling, GitHub, and automation use cases.
A TypeScript helper for Toonflow wrapping and automation.
A dLazy CLI client that converts text into emotional Kling TTS speech with async task and status polling support.
Generate a runnable single-file HTML product prototype with a split layout, SVG connectors, hover highlighting, and mobile view switching.
A closed-loop video production workflow for short videos, ads, and animation, covering storyboarding, asset generation, image-to-video, editing, and iterative delivery.
Use a local Ollama-deployed Moondream model to understand images and return descriptions to OpenClaw.
Vidu TTS and voice cloning skill with voice presets, pauses, emotions, and audio URLs.
Extract expressive features from an uploaded image and asynchronously generate a highly constrained black-and-white sketch-style image for avatars, memes, and creative visuals.
A film-critic guided exploration of lens grammar, narrative structure, and staging, using case studies and interactive questions to explain editing rhythm.