TypingMindTypingMindThe best frontend for AI
Bullframe Convert logo

Bullframe Convert

Community
marcop135
bullframe-convert

Convert existing HTML and CSS to Bullframe CSS. Use when migrating a page off Bootstrap, Tailwind, a hand-rolled stylesheet, or an older Bullframe version, and when asked to remove custom CSS in favour of the framework.

Overview

Publishermarcop135
Repositorybullframe.css
Skill namebullframe-convert
Stars
47
Forks
3
Bundled files
2
LicenseMIT
Links
Skill sourceRepositoryHomepage
  • 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.

  • 2 bundled files

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

  • Open source

    Published by marcop135 on GitHub. Read the source before you install it.

Installation

Install the Bullframe Convert 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-convert
  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-convert .claude/skills/bullframe-convert
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bullframe Convert 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 Convert 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 Convert 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.

Convert to Bullframe

This is advisory work, not a codemod. Read the source, rewrite the markup, and report what could not be mapped. Never run a blind find and replace: class names from other frameworks look similar to Bullframe's and are not the same.

When to use

Migrating a page or component onto Bullframe, stripping custom CSS that the framework already covers, or upgrading markup from Bullframe v5.

Inputs to gather

The HTML, the stylesheet that styles it, which framework it uses today, the target build, and how aggressive to be: replace the reset only, or convert the whole page.

Rules

  1. Work in four passes, in order: base styles, layout, utilities, leftovers.
  2. Pass 1, base. Delete the reset, normalize and base typography rules; link one Bullframe build instead. Most of the deleted CSS is now element styling.
  3. Pass 2, layout. Map the page's container and grid onto .bf-container (--fluid, --break-xs|md|lg), .bf-row and .bf-col-1 … .bf-col-12. Per-breakpoint column classes have no equivalent: collapse them to the desktop span and put the breakpoint on the container.
  4. Pass 3, utilities. Map declaration by declaration against api.json. Never guess a name from the source framework.
  5. Pass 4, leftovers. Anything with no equivalent stays as project CSS. List it. Do not silently drop a rule.
  6. Upgrade the markup while you are there: a <div class="header"> becomes <header>, <div class="card-title"> becomes a heading, a clickable <div> becomes a <button> or <a>.
  7. Preserve every accessibility attribute: alt, aria-*, for, id, lang, scope, tabindex. Add the skip link if the page lacks one.
  8. Output the converted file plus a mapping table and a residual list. The user needs to see what moved and what stayed.

Name mapping

Common false friends. The left column does not exist in Bullframe.

SourceBullframe
container, container-fluidbf-container, bf-container--fluid
row, col-md-6bf-row, bf-col-6 + bf-container--break-md
d-flex, justify-content-endbf-display-flex, bf-display-flex--justify-end
mt-3, mb-4bf-m-t-3, bf-m-b-4
p-3bf-p-3 (padding-bottom) or bf-p-t-3
text-center, text-startbf-t-center, bf-t-left
fw-bold, font-weight-boldbf-t-weight-700
text-truncatebf-t-truncate
btn btn-primarybf-btn bf-btn--primary
table table-stripedbf-table bf-table--zebra
visually-hidden, sr-onlybf-sr-only
card, card-bodyno equivalent: compose <article> with tokens
badge, alert, navbarno equivalent: semantic markup plus tokens

Spacing steps do not translate by number. Bullframe's 1 … 4 are 0.5rem, 1rem, 2rem, 3rem, and the unsuffixed .bf-m-N sets margin-bottom only.

Recipe

  1. Inventory: list every class in the source and every rule in its stylesheet.
  2. Decide the target build.
  3. Convert the markup pass by pass.
  4. Diff the result against the original visually, not just structurally.
  5. Emit: converted file, mapping table, residual CSS with a one-line reason for each rule that stayed, and a count of removed declarations.

Example

examples/before.html is a div-heavy page on a custom stylesheet. examples/after.html is the same page converted: two stylesheets replaced by one, div wrappers replaced by landmarks, card titles promoted to headings, inline footer styling replaced by .bf-t-center and <small>.

Expected output

The converted markup, plus the mapping table and the residual list. The converted page must validate and must reference only classes present in api.json.

Failure modes

  • Mechanical prefixing: mt-3 becoming bf-mt-3, d-flex becoming bf-d-flex, text-center becoming bf-text-center. All three are wrong.
  • Keeping per-breakpoint column classes with a bf- prefix.
  • Dropping rules that had no mapping instead of reporting them.
  • Losing aria-*, alt or for attributes during the rewrite.
  • Linking Bullframe while leaving the old framework's stylesheet in place.
  • Converting a page that only needed the utilities build, and rewriting its base styles for no reason.
  • Treating a .bf-m-N class as all-sides margin.

Do not

  • Do not run a regex replace over class attributes.
  • Do not rewrite the project's own component CSS that Bullframe does not cover.
  • Do not change copy, structure or behaviour while converting styles.
  • Do not delete a rule you cannot explain.

Canonical docs

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 Bullframe Convert AI skill do?

Convert existing HTML and CSS to Bullframe CSS. Use when migrating a page off Bootstrap, Tailwind, a hand-rolled stylesheet, or an older Bullframe version, and when asked to remove custom CSS in favour of the framework.

Why use Bullframe Convert on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/marcop135/bullframe.css/tree/main/src/skills/bullframe-convert. 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 Bullframe Convert?

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 Convert?

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

Is the Bullframe Convert 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.

Related AI Skills

View all
openclaw logo

Canvas

openclaw
OrganizationPopular

Present hosted widget documents on a connected macOS panel and control panel visibility or navigation.

82.2K
391K
Instructions
View
openclaw logo

Diagram Maker

openclaw
OrganizationPopular

Create SVG/HTML or Excalidraw diagrams for concepts, architecture, flows, and whiteboards.

82.2K
391K
2 files
View
mattpocock logo

Grill With Docs

mattpocock
CommunityPopular

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

23K
273.1K
1 files
View
mattpocock logo

Grill Me

mattpocock
CommunityPopular

A relentless interview to sharpen a plan or design.

23K
273.1K
1 files
View

Set up your own AI workspace now

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