StyleSeed
Teach your AI fixed design judgment.Not one fixed aesthetic.
Your AI coding agent sets up the design system, a scored gate keeps the quality, and the decisions live in your repo, maintained across screens and sessions — designed-looking products without a design team. Open source, for Claude Code · Codex · Cursor.
Same product. Same prompt. Only the rules changed.
Measured on 120 rendered benchmark cells: the enforced gate improved both Codex and Claude Code by +5.3 points. Raw rules alone were inconsistent (Codex +1.6, Claude Code −3.7), which is why StyleSeed ships a render → score → revise loop—not a prompt dump. Read BENCH-V1 and inspect the raw evidence →
Easy Start (30 seconds)
1. Open your project in Claude Code, Codex, Cursor, or another coding agent.
2. Paste this message:
Install StyleSeed with `npx skills add bitjaru/styleseed`, then set it up for this project. Ask what I am building and only the design choices you need. Choose the right output grammar, brand recipe, and semantic palette—or derive a local grammar from my references. For a full concept with three directions, image/video jobs, and a working interaction reel, use `/ss-studio` in Claude Code or `$ss-studio` in Codex. Otherwise resolve the approved direction with `/ss-resolve` or `$ss-resolve`, build with one clear focal point, score to at least 80, then render and visually verify it before showing me.
3. Approve the install, answer the short setup questions, and describe what you want to build. StyleSeed handles the design lock, build, code gate, and visual check. No design-system knowledge required.
| Agent | If you want to run it manually |
|---|---|
| Claude Code | /ss-studio for exploration, or /ss-setup → /ss-build for a decided screen |
| Codex | $ss-studio for exploration, or $ss-setup → $ss-build from /skills |
| Cursor and others | Paste the message above or use the installed skill picker |
Claude Code guide · Codex guide · See examples · Need help?
What it bans on sight
The "AI-generated look" isn't bad luck — it's a list of nameable tells. StyleSeed ships 74 rules that ban them, and a 0–100 scored gate that tells an installed agent to revise screens below 80 before presentation. The gate is enforced when the StyleSeed build workflow is actually invoked; a markdown file alone cannot block delivery.
| Banned | Why |
|---|---|
Default indigo #4F46E5 / #5E6AD2 accent |
the universal "an AI made this" color |
| Emoji as UI icons 🚗 🧺 ⭐ | inject random colors, render differently per OS |
| The icon-in-a-chip above every feature card | gen-1 AI tell — decoration pretending to be information |
| All-even grid of same-weight centered cards | the #1 machine-composed tell: no focal point |
Pure #000 backgrounds |
a flat void — real dark UIs use layered ramps |
| Font sizes outside one fixed table | size drift is why screens feel "off" but you can't say why |
| Hardcoded hex in components | tokens only — otherwise the lock can't hold across screens |
Banning the defaults isn't enough — agents converge on new uniforms once the old ones are blocked. That's why the rules come with an enforced score-then-fix loop, not a checklist. What happens after install ↓
One component. Three token skins. Same chat UI morphing across Toss · Raycast · Arc-inspired token sets. A skin changes color and type material; a StyleSeed brand recipe changes the actual geometry, containment, controls, collections, density, and motion.
Skins are inspired-by token sets, not recreations. Compare the nine structural recipes →
StyleSeed fixes the design method — not one Toss-like aesthetic.
Judgment, not data — how designers think, not a palette collection ·
Right grammar for the result — consumer service, operations, technical, editorial,
commerce, institutional, marketing, or sequential story ·
Real morphology choices — nine brand recipes change structure and component selection,
not just palette ·
Generative palette engine — any key color becomes OKLCH ramps, context-fit surfaces,
a scored companion, semantic roles, contrast evidence, CSS tokens, and media anchors; eight
recipes remain maintained product postures ·
Studio pipeline — three directions, human selection, interaction scenes, image/video jobs,
working prototype, and a prototype-first reel ·
References become rules — /ss-reference compiles screenshots, URLs, Figma, or an existing
UI into an evidence-backed project grammar ·
Only the context you need — /ss-resolve compiles the chosen method into a small,
hash-verifiable project bundle ·
Beyond web UI — adapters for product UI, social carousels, decks, documents, and graphics ·
Fights the AI tells — the default indigo, the icon-chip cliché, template layouts, rainbow lists ·
Auxiliary proof gates — code score + rendered pixel verification before you see it ·
Every agent — ships CLAUDE.md + AGENTS.md + .cursorrules ·
A design lock that stops drift ·
Free & MIT
Core judgment × output grammar × surface adapter × domain/page × brand recipe × palette recipe × optional profile. Read the architecture →
Full pages: before · after · more before/afters →
🔥 We ran an early version of this page through our own gate. It scored 58/100 → here's the receipt
Same product, six looks — each one /ss-restyle <preset> away. Coherent, distinct, never generic.
Easy Start · Studio · Palettes · Claude Code UI guide · Codex UI guide · Brand recipes · Architecture · Engine + Recipes + Skins · Motion · Skills · Wiki · 한국어
What happens after Easy Start
Why the prompt installs first: the context compiler and quality gates can only run when the
skills are installed. Installing turns STYLESEED.md into a small source-hashed rule bundle,
then actually scores and fixes the result before you see it. Without installation,
llms.txt still tells any agent how StyleSeed is
structured and where its machine-readable catalog lives, but compilation and gates become a
weaker manual path.