Tinte logo

Tinte

Community
Railly
tinte

Agent-native design system infrastructure. Browse, install, and preview design systems from tinte.dev. Use when user asks about themes, design systems, presets, color palettes, or says "tinte". Works with shadcn/cli v4 presets and registries.

Overview

PublisherRailly
Repositorytinte
Skill nametinte
Stars
624
Forks
38
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Railly on GitHub. Read the source before you install it.

Installation

Install the Tinte AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Railly/tinte/tree/main/skills/tinte
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Railly/tinte.git /tmp/tinte
mkdir -p .claude/skills
cp -r /tmp/tinte/skills/tinte .claude/skills/tinte
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tinte in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Tinte on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Tinte is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Tinte - Design System Infrastructure

Generate, compile, install, and preview design systems from one source of truth.

Tinte maintains a theme graph of 13 semantic OKLCH color tokens that compiles to shadcn/ui presets, VS Code themes, terminal configs, and 19+ other formats.

Preset API (shadcn v4 compatible)

Every public Tinte theme is installable as a shadcn registry:base item.

Install a theme

bash
npx shadcn@latest add https://tinte.dev/api/preset/{slug}

Install theme fonts

bash
npx shadcn@latest add https://tinte.dev/api/preset/{slug}/font?variable=sans
npx shadcn@latest add https://tinte.dev/api/preset/{slug}/font?variable=mono

Get full preset pack (base + fonts + install commands)

GET https://tinte.dev/api/preset/{slug}?type=pack

Response:

json
{
  "base": { "$schema": "...", "name": "...", "type": "registry:base", "cssVars": { "light": {...}, "dark": {...} } },
  "fonts": [{ "$schema": "...", "name": "font-inter", "type": "registry:font", "font": {...} }],
  "slug": "theme-slug",
  "install": {
    "base": "npx shadcn@latest add https://tinte.dev/api/preset/{slug}",
    "fonts": ["npx shadcn@latest add https://tinte.dev/r/font/inter?variable=sans"]
  }
}

Browse Themes

GET https://tinte.dev/api/themes/public?search={query}&limit=20&page=1

Optional filters: ?vendor=tinte|tweakcn|rayso

Response includes themes[] with slug, name, concept, and color tokens.

Get Theme Details

GET https://tinte.dev/api/themes/slug/{slug}

Returns full theme data including light/dark color blocks and overrides.

Registry Routes (shadcn compatible)

These routes serve raw registry:base and registry:font items:

GET https://tinte.dev/r/{slug}                    # registry:base or registry:theme
GET https://tinte.dev/r/{slug}?type=registry:base  # explicit base type
GET https://tinte.dev/r/font/{family}?variable=sans # registry:font

Extract Theme from Image

Upload a screenshot or design image to extract a color theme:

bash
curl -s -X POST https://ray.tinte.dev/api/v1/extract-theme \
  -F "image=@design.png" | jq

AI mode for higher fidelity:

bash
curl -s -X POST "https://ray.tinte.dev/api/v1/extract-theme?mode=ai&model=anthropic/claude-haiku-4.5" \
  -F "image=@design.png" | jq

Response:

json
{
  "dark": { "bg": "#0a0a12", "bg_2": "#0f0f18", "ui": "...", "tx": "...", "pr": "...", "sc": "...", "ac_1": "...", "ac_2": "...", "ac_3": "..." },
  "light": { "bg": "#fafafa", "bg_2": "#f0f0f0", ... },
  "name": "Extracted Theme Name",
  "gradient": "linear-gradient(...)",
  "swatches": { "vibrant": { "hex": "#e84393" }, ... }
}

Screenshot Preview

Generate a code screenshot with any Tinte theme applied:

bash
curl -s -X POST https://ray.tinte.dev/api/v1/screenshot \
  -H 'Content-Type: application/json' \
  -d '{
    "code": "const x = 42;",
    "language": "typescript",
    "theme": "{slug}",
    "title": "preview.ts"
  }' -o preview.png

Agent Workflows

1. Browse and install a design system

1. GET https://tinte.dev/api/themes/public?search=minimal → pick theme
2. GET https://tinte.dev/api/preset/{slug}?type=pack → get install commands
3. npx shadcn@latest add https://tinte.dev/api/preset/{slug} → install base
4. npx shadcn@latest add https://tinte.dev/api/preset/{slug}/font?variable=sans → install fonts
5. npx shadcn info --json → verify

2. Extract design system from screenshot

1. POST ray.tinte.dev/api/v1/extract-theme -F image=@screenshot.png → get TinteBlock
2. Use extracted colors to search for matching themes or create new one
3. Install via preset API

3. Switch design system

1. npx shadcn info --json → read current project config
2. GET https://tinte.dev/api/themes/public?search=dark+minimal → browse alternatives
3. npx shadcn@latest add https://tinte.dev/api/preset/{new-slug} → overwrite with new theme

4. Preview result

1. POST ray.tinte.dev/api/v1/screenshot with theme slug → get PNG
2. Open screenshot to verify visual result

Color Model

Tinte uses 13 semantic OKLCH tokens per mode (light/dark):

TokenRole
bgBackground
bg_2Elevated surface
uiBorder, separator
ui_2Subtle border
ui_3Hover state
txPrimary text
tx_2Secondary text
tx_3Muted text
prPrimary accent
scSecondary accent
ac_1Accent 1
ac_2Accent 2
ac_3Accent 3

These compile to 30+ shadcn CSS variables (background, foreground, card, primary, secondary, muted, accent, destructive, chart-1..5, sidebar-*, etc.) with OKLCH color space formatting.

Design system compiler (Agent Plugins)

tinte compiles a project identity into an installable Agent Plugin (agent-plugins.org 1.0.0) so coding agents generate on-brand UI instead of default slop.

bash
tinte build --plugin --config tinte.config.json --out ./acme-plugin
# emits: plugin.json + skills/<name>-design/SKILL.md (composition law + identity)
#        + references/tokens.css (OKLCH token API from the theme graph)

tinte lint src/            # scan for hex/rgb/hsl literals and Tailwind palette classes
tinte lint --json          # machine-readable; exit 1 on violations (CI gate)

Extracting an identity from a reference site

The CLI never guesses colors. The agent looks, the CLI does the math:

bash
tinte from --emit-script > extract.js
agent-browser open https://example.com && agent-browser wait --load networkidle
agent-browser eval "$(cat extract.js)" > candidates.json
# The agent (vision) reviews a screenshot to assign semantic roles if needed.
tinte from --normalize candidates.json --name example --out draft-identity.json
# Draft only: fill voiceWords/dosDonts by hand, then validate strictly via tinte build.

--normalize detects primaryStyle: "inverted" (sites whose CTA is a foreground/background pair, not a hue) and normalizes pill radii. Tokens that need app states (destructive, ring, input) are reported as warnings, never invented.

Frequently asked questions

What does the Tinte AI skill do?

Agent-native design system infrastructure. Browse, install, and preview design systems from tinte.dev. Use when user asks about themes, design systems, presets, color palettes, or says "tinte". Works with shadcn/cli v4 presets and registries.

Why use Tinte on TypingMind?

Because you install it once and use it with any model. Tinte is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Tinte in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Railly/tinte/tree/main/skills/tinte. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Tinte?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Tinte?

As many as you like. As long as a model supports skills, you can use Tinte with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Tinte AI skill free?

Yes. It is published on GitHub by Railly under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇