Bullframe Core logo

Bullframe Core

Community
marcop135
bullframe-core

Core conventions for writing HTML styled with Bullframe CSS. Use before any other Bullframe skill, and whenever choosing a build, scaffolding a page, theming with tokens, or deciding whether to write custom CSS.

Overview

Publishermarcop135
Repositorybullframe.css
Skill namebullframe-core
Stars
47
Forks
3
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 marcop135 on GitHub. Read the source before you install it.

Installation

Install the Bullframe Core 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/marcop135/bullframe.css/tree/main/src/skills/bullframe-core
  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/marcop135/bullframe.css.git /tmp/bullframe.css
mkdir -p .claude/skills
cp -r /tmp/bullframe.css/src/skills/bullframe-core .claude/skills/bullframe-core
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bullframe Core 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 Bullframe Core 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 Bullframe Core 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.

Bullframe core conventions

Bullframe is one stylesheet of plain CSS. No build step, no JavaScript, no components to import. It styles semantic HTML, then adds .bf-* utilities on the class-based builds.

Read _shared/conventions.md and _shared/builds.md alongside this file. They hold the rule list and the build table this skill applies.

When to use

Any task that writes or edits HTML in a project that links Bullframe. Every other Bullframe skill assumes these rules.

Rules

  1. Link exactly one base build. Two base builds cascade over each other and produce wrong colours in dark mode.
  2. Do not invent classes. Check api.json (shipped at node_modules/bullframe.css/dist/skills/api.json, published at https://bullframecss.marcopontili.com/api.json). 179 classes, 47 tokens, and nothing else exists.
  3. Prefer the element over the class. <button> is already styled; .bf-btn is for links that must look like buttons and for buttons that need the framework's chrome.
  4. Prefer a utility over a declaration. Before writing style="margin-bottom: 2rem", use .bf-m-b-3.
  5. Prefer a token over a literal. var(--bf-gray-light), not #ccc; the dark builds rebind those tokens, a literal does not follow.
  6. Keep custom CSS in one project stylesheet, loaded after Bullframe, and confine it to :root token overrides plus genuinely project-specific rules.
  7. The root font-size is 62.5%, so 1rem is about 10px. --bf-body-font-size-rem is 1.6rem, which renders as 16px.

Page scaffold

Class-based, light. Every generated page starts here.

html
<!doctype html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1" />
    <title>Page title</title>
    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bullframe.css" />
  </head>
  <body>
    <a class="bf-skip-link" href="#main-content">Skip to content</a>
    <main id="main-content" class="bf-container bf-container--break-md">
      <h1>Page title</h1>
      <p class="bf-lead">One sentence that says what this page is for.</p>
    </main>
  </body>
</html>

Classless, same page:

html
<!doctype html>
<html lang="en">
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=device-width, initial-scale=1" />
    <title>Page title</title>
    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bullframe.css/dist/css/bullframe-classless.min.css" />
  </head>
  <body>
    <main>
      <h1>Page title</h1>
      <p>One sentence that says what this page is for.</p>
    </main>
  </body>
</html>

There is no skip link on a classless build: .bf-skip-link is not in that stylesheet.

Layout

.bf-container caps width at 114rem and adds gutters. .bf-container--fluid is full width. .bf-row is a flex row with negative gutters, .bf-col-1 … .bf-col-12 are twelfths.

html
<main id="main-content" class="bf-container bf-container--break-md">
  <section class="bf-row">
    <div class="bf-col-8">Main column</div>
    <div class="bf-col-4">Sidebar</div>
  </section>
</main>

Columns in one row sum to 12 or less. Responsiveness is a container modifier: --break-xs stacks below 576px, --break-md below 768px, --break-lg below 992px. Use --break-md unless there is a reason not to.

Theming

html
<link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/bullframe.css" />
<style>
  :root {
    --bf-blue: rgb(84 47 194);
    --bf-blue-light: rgb(64 32 160);
    --bf-focus-ring-color: rgb(84 47 194);
  }
</style>

That restyles links, primary buttons and focus rings across the page. Check contrast: the shipped blues are WCAG AA (4.5:1) on white, and a replacement has to clear the same bar.

Do not

  • Do not link bullframe.css and bullframe-dark.css together, or any two base builds.
  • Do not write .bf-col-md-6, .bf-col-sm-12, .bf-d-flex, .bf-mt-3, .bf-text-center or .bf-card. None exist. The real names are .bf-col-6, .bf-display-flex, .bf-m-t-3, .bf-t-center, and a card is composed markup.
  • Do not add a theme-toggle script to get dark mode; pick a -system-default build.
  • Do not set outline: none anywhere.
  • Do not reimplement the grid, the spacing scale or the type scale in project CSS.
  • Do not add a CSS framework alongside Bullframe.

Canonical docs

Frequently asked questions

What does the Bullframe Core AI skill do?

Core conventions for writing HTML styled with Bullframe CSS. Use before any other Bullframe skill, and whenever choosing a build, scaffolding a page, theming with tokens, or deciding whether to write custom CSS.

Why use Bullframe Core on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/marcop135/bullframe.css/tree/main/src/skills/bullframe-core. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Bullframe Core?

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 Bullframe Core?

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

Is the Bullframe Core AI skill free?

Yes. It is published on GitHub by marcop135 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 👇