Creative · Design

Agent-side workflows that turn novels into production-ready short-drama bibles—characters, outlines, and art guides—without leaving Claude Code or Codex.

A Claude Code skill that ships 39 film styles as prompts — and proves each one with a demo film its agent rendered, scored, and narrated entirely in code.

Those viral Claude Opus 5.5 animations are just code the model wrote — this list collects them with the prompts that produced them, so you can copy the technique instead of guessing.

This agent skill bundles 123 scraped Apple HIG pages so your coding agent critiques UI with citations instead of vibes.

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.

It exists because agents default to cliché unless you feed them the vocabulary of craft.

It wires an infinite whiteboard directly into an AI film pipeline so solo creators can script, storyboard, generate, and rough-cut without tab-hopping.

onetake is a Claude Agent Skill that makes product films in one unbroken take — and auto-rejects any video where one beat simply replaces the next.

Agents can draw SVGs all day; what they lack is the unglamorous craft of identity design — the brief, the optical corrections, the 16-pixel test, and knowing when to stop for approval.

A self-hostable infinite canvas that wires AI image generation, reference editing, and chat into one collaborative workspace.

A library of agent-native markdown playbooks that teach AI coding assistants to render, screenshot, and self-correct motion graphics instead of guessing at keyframes.

AutoShade turns a described look into an editable, Lightroom-compatible develop recipe instead of handing you a generated picture you can't use.

LocalMiniDrama wires your API keys into a Vue+Electron pipeline that turns story outlines into short-form AI video without shipping data to anyone else's cloud.

OmniChar Studio packages a character's face, body, and wardrobe into a portable `.char` file that stays consistent across models — and trains the LoRAs to back it up.

Over 3,600 community-curated prompts for ByteDance's Seedance 2.0, treating AI video generation less like prompting and more like micro-screenwriting.

explainroo hands Claude Code or Codex a local TTS, word-timing and canvas pipeline so it can turn a script into a finished MP4 — no API keys, no cloud rendering.

Motion-anything is a local-first engine that generates animated pages and launch videos from a single sentence, then edits motion component-by-component on the running page.

Oil UI makes coding agents produce several genuinely distinct UI directions, put them side by side, and refine against real screenshots.

It exists to stop AI-generated presentations from being final, adding a browser-based editing and tuning layer before exporting to real PPTX.

This unofficial rebuild of a Google Research project chains specialized agents to turn rough text and data into publication-ready academic figures.