Turns the coding agents already on your laptop into a design studio that ships real artifacts.
Creative · Design
heavyweights · velocity + momentumA curated rulebook that tells LLMs how to pick colors, fonts, and layouts for 161 different product types.
huashu-design turns a one-sentence prompt into shipped HTML prototypes, MP4 animations, and editable PowerPoint decks — with enough guardrails to keep AI output out of the "purple gradient" slop zone.
A local-first editor that turns your existing coding-agent CLI into a designer that outputs single-file HTML, decks, posters, and social cards.
A local meta-layer that turns HTML, CSS, and a prompt into rendered video — no cloud fees, no new DSL to learn.
An open-source skill that lets coding agents edit raw footage into finished videos by reading transcripts instead of watching frames.
A Claude Code skill that generates zero-dependency HTML presentations by showing you visual previews instead of asking for design opinions you don't have.
A Python workflow that turns documents into natively editable .pptx files with animations, speaker notes, and optional audio narration.
A TypeScript skillset that turns a single photo into meshes, gaussian splats, and sound effects by orchestrating multiple generative models through Claude.
Pixelle-Video wires LLMs, image/video generators, TTS engines, and ffmpeg into a single Streamlit app that spits out short-form videos from a topic string.
Outpainting is the appetizer; the main course is automated 2D game asset generation with seam-aware tooling that exports engine-ready packs.
A Python pipeline that turns a keyword into a complete short-form video—script, stock footage, voiceover, subtitles, and all.
InkOS automates the full novel pipeline—draft, audit, revise—with human approval gates so you don't publish AI slop by accident.
Banana Slides turns natural language into editable PowerPoint decks using an image model that can render readable text.
Toonflow turns novels and scripts into animated shorts by wiring together LLMs, image generators, and video models behind a single desktop UI.
This project turns a handful of style keywords into full photography-director prompts for female portrait generation, with guardrails baked in.
A self-hostable infinite canvas that wires AI image generation, reference editing, and chat into one collaborative workspace.
OpenMontage turns Claude, Cursor, or Copilot into a full video production studio that researches, scripts, generates assets, and renders finished pieces.
A Codex skill pipeline that turns text prompts into sprite sheets, layered maps, and playable Godot or Unity prototypes.
A Vercel skill that scaffolds a full Next.js canvas editor so you can drag, crop, and export store-ready PNGs instead of wrestling with Figma templates.