AI Agent Skills

Default downstream MiniMax H3 specialist for every image-based request unless the user explicitly declares boundary-only first/last frames with no reusable reference rol…

Downstream MiniMax H3 specialist for professional text-to-video (T2VA) prompts using the official three-field format. Use after minimax-h3-creative-director routes a req…

PyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)

Clawd 像素风动画生成器。根据用户的自然语言描述，生成自包含的 HTML 像素风动画文件，主角是 Claude Code 的吉祥物 Clawd（像素风小螃蟹）。当用户提到 clawd、clawd 动画、像素动画、pixel animation、给 clawd 做一个小动画、让小螃蟹做某事、或任何涉及为 Clawd 角色创建动画场景的…

Use when a narrated video's beats and draft narration need visual direction, scene concepts, metaphors, worlds, action, camera logic, or visual continuity before storybo…

Code for FreeTraj, a tuning-free method for trajectory-controllable video generation

Generates one expressive narration MP3 per scene for an English storybook, using the ElevenLabs MCP (text_to_speech). Reads {slug}_scenes.json (from scene-splitter), pro…

Open or rebuild the video-lens gallery index — your personal library of saved video summaries. Use this whenever the user wants to browse, open, or search saved video re…

Create videos programmatically with Claude Code and Remotion

OpenAi-Sora (SoraFlows) is an open-source, cross-platform web application for AI-powered video creation and editing using the latest OpenAI Sora model. Effortlessly gene…

Image Processing techniques using OpenCV and Python.

Orchestrator that runs the full AI Storybook pipeline end-to-end on one English story. Dispatches the 4 component skills in order — scene-splitter → story-illustrator →…

The master program for producing or editing a video end to end — read this at the START of any video task (after video-router), then follow the gates and the per-line st…

A library for real-time video stream decoding to CUDA memory

Official PyTorch Implementation of Unified Video Action Model (RSS 2025)

This is a library of FFmpeg for android... 📸 🎞 🚑