An agent skill that turns Claude Code into a motion-design studio for voiceover explainer videos, complete with word-level audio sync and an anti-PPT camera system that refuses to let frames sit still.
Creative · Design
underdogs breaking outDoop is an open-source multiplayer canvas where humans and AI agents design live HTML together, replacing prompt-and-refresh workflows with real-time pair editing over MCP.
It exists because most AI-built pages are either forgettable or flashy broken messes, and this skill enforces both narrative scroll design and a hard craft floor.
A structured prompt system that forces image generators to obey graphic design rules like negative space ratios and ink limits.
It turns DeepSeek's chat interface into a studio for generating, refining, and exporting actual editable designs and slides.
It forces any compatible AI agent to generate IP mascot logos under strict design constraints instead of leaving the look to model hallucination.
A pair of agent skills that direct Claude, Cursor, and Codex to research top-grossing mobile apps before building Expo and React Native screens, then verify the output in a frame-by-frame simulator loop.
Agent-side workflows that turn novels into production-ready short-drama bibles—characters, outlines, and art guides—without leaving Claude Code or Codex.
An open-source answer to paywalled AI camera-angle tools, wrapping Qwen-Image-Edit-Plus in a Three.js control rig so anyone can generate multi-angle images without a subscription.
CozyClay puts previsualization in a single browser tab so you can stage scenes, pose characters, and hand the camera off to an AI model or an LLM agent.
A single CLI and credit balance for generating images, video, audio, and text when creator suites are too slow or expensive for automated pipelines.
OpenEdit hands your coding agent a video-editing pipeline that needs no GUI or timeline.
A structured knowledge kit that forces Claude to design like a senior architect instead of an enthusiastic intern.
Maestro is a local creative suite that uses a built-in LLM to plan, shoot, and edit multi-clip music videos and short films without sending anything to the cloud.
It provides the skill definitions and pipeline glue so coding agents can turn a text game brief into engine-ready assets and runtime code across UE5, Unity, Godot, and more.
A curated recipe library that turns 'draw a cat' into a validated, style-locked prompt for 19 hand-drawn aesthetics, from xkcd to Ghibli.
Because agents can't drag clips in Premiere Pro, this editor speaks JSON, JSX, and plain English instead.
This repository exists to track which companies have officially published DESIGN.md files so AI coding agents can generate consistent UI without extracting design tokens from Figma files or websites.
A browser-native slide editor that treats cloud sync as a liability and runs generative AI locally via Chrome APIs or WebGPU.
ClipForge generates shoppable short-form videos from a single product image while automatically enforcing platform compliance rules for Chinese social commerce.




