Tailwind logo

Tailwind

Community
nahid-sparktales
tailwind

Work inside an existing Tailwind codebase without degrading it — use the project's theme tokens instead of arbitrary values, extend the theme when a token is genuinely missing, extract repetition into components rather than @apply, resolve class conflicts with the project's merge helper, and make dark mode a token decision. Fires when writing or editing Tailwind classes in a repo that already uses it. Not for deciding whether to adopt Tailwind, not for visual design direction, and not a rendered-output check.

Overview

Publishernahid-sparktales
Repositoryagent-dispatcher
Skill nametailwind
Stars
58
Forks
5
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by nahid-sparktales on GitHub. Read the source before you install it.

Installation

Install the Tailwind 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/nahid-sparktales/agent-dispatcher/tree/main/skills/frontend/tailwind
  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/nahid-sparktales/agent-dispatcher.git /tmp/agent-dispatcher
mkdir -p .claude/skills
cp -r /tmp/agent-dispatcher/skills/frontend/tailwind .claude/skills/tailwind
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tailwind 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 Tailwind 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 Tailwind 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.

Tailwind

A Tailwind codebase degrades one arbitrary value at a time. Every value you hardcode is a design decision the theme can no longer make.

When this fires

Writing or editing Tailwind utility classes in a project that already uses Tailwind. It does not fire for choosing a styling approach, for visual design direction, or for CSS in a project that does not use Tailwind.

Procedure

  1. Read the theme before writing a class. Tailwind's major versions place theme configuration differently — a JS/TS config file in some, a CSS-side theme block in others — so find where this project defines its tokens (and confirm the version from the lockfile; see stack-detection). Read the colors, spacing, radius, font and breakpoint tokens that exist.
  2. Read one or two existing components in the same area. The class vocabulary a team actually uses is a stronger constraint than what Tailwind permits.
  3. Reach for a token before a value. Semantic color tokens over raw palette steps, scale spacing over pixel values. If you are about to type a bracketed arbitrary value, first check whether a token covers it.
  4. When no token covers it, add the token — do not sprinkle the value. Ask whether this is a one-off (one arbitrary value, with a comment saying why) or a design decision (belongs in the theme). Adding a theme token changes the whole app's vocabulary, so say what you are adding and why in the report.
  5. Do not extract on the second repetition. Two similar class lists are cheaper than a wrong abstraction. At the third, extract a component — the props and boundaries question is component-architecture, not a CSS question. Reserve @apply for a genuinely global primitive in the stylesheet; an @apply block that reimplements a component is worse than the repetition.
  6. Merge conditional classes with the project's helper. Later position in the class string does not win a conflict — the generated stylesheet's order decides, so p-2 and p-4 in one string resolve unpredictably. Use the project's existing cn/merge utility for any conditional or overridable class, and pass overrides through it rather than concatenating.
  7. Never build a class name from a fragment. Tailwind finds classes by scanning source text, so bg-${color}-500 produces no CSS. Write full class strings in a lookup map, and confirm the file you are editing is inside the project's content/source scan paths — a class in an unscanned file silently produces nothing.
  8. Make dark mode a token decision, not a per-utility one. Check the project's dark-mode strategy first (media query vs a class/attribute toggle) and follow it. Prefer semantic tokens whose values differ per theme over stacking a dark: variant on every utility; add dark: where the token system genuinely cannot express the difference.
  9. Keep the class order the project keeps. If a class-sorting formatter is configured, run the project's format command rather than hand-sorting.
  10. Look at it in both themes and at the breakpoints you touched. Class lists are not evidence of rendering; hand that off to browser-verification.

Checklist

  • Theme tokens read before classes were written
  • No arbitrary value that an existing token covers
  • Any new token added to the theme, with the reason stated
  • Repetition extracted at the third occurrence, as a component
  • @apply used only for a global primitive, if at all
  • Conditional/override classes routed through the project's merge helper
  • No class name assembled from fragments
  • Dark mode expressed through tokens where the system allows it
  • Project formatter run; class order matches the codebase
  • Light and dark rendered and looked at, not inferred

Failure handling

  • A class is in the source but no style appears — check, in order: the file is inside the scan paths, the class name is a complete literal string, the utility actually exists in this major version, and the build was re-run.
  • A style applies but the wrong value wins — a conflict, not a specificity puzzle. Route both classes through the merge helper instead of adding !important.
  • Dark mode is right in one place and wrong in another — the two places are using different mechanisms (one token, one dark: variant). Unify on the project's strategy.
  • A design needs a value no token has and the theme owner is not you — use one arbitrary value with a comment and raise the missing token. Do not add tokens to a shared theme unasked; that is a change to every screen.
  • A theme token's value needs changing — that repaints the app. Stop and ask before editing an existing token's value, even when it looks obviously wrong.

Evidence to report

The tokens used; any token added, with its file and the reason; the count of arbitrary values left and why each survived; whether repetition was extracted or deliberately left; and confirmation that light and dark were both rendered, or a plain statement that they were not.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Tailwind AI skill do?

Work inside an existing Tailwind codebase without degrading it — use the project's theme tokens instead of arbitrary values, extend the theme when a token is genuinely missing, extract repetition into components rather than @apply, resolve class conflicts with the project's merge helper, and make dark mode a token decision. Fires when writing or editing Tailwind classes in a repo that already uses it. Not for deciding whether to adopt Tailwind, not for visual design direction, and not a rendered-output check.

Why use Tailwind on TypingMind?

Because you install it once and use it with any model. Tailwind 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 Tailwind in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/nahid-sparktales/agent-dispatcher/tree/main/skills/frontend/tailwind. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Tailwind?

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 Tailwind?

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

Is the Tailwind AI skill free?

Yes. It is published on GitHub by nahid-sparktales 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 👇