Bullframe Media

Community

marcop135

bullframe-media

Build galleries, responsive embeds and media grids with Bullframe CSS. Use when creating an album, photo grid, video or map embed, figure with caption, or mixed media cards.

Overview

Publisher	marcop135
Repository	`bullframe.css`
Skill name	`bullframe-media`
Stars	47
Forks	3
Bundled files	1
License	MIT
Links	Skill source Repository Homepage

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

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/marcop135/bullframe.css/tree/main/src/skills/bullframe-media
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.

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-media .claude/skills/bullframe-media

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bullframe Media 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 Media 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 Media 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.

Media

Media layouts in Bullframe are grid columns plus embed utilities. Cards and galleries are composed markup; there is no gallery or card class.

When to use

An album, portfolio grid, video or map embed, captioned figure, filter chip bar over a media set, or any page whose main content is images or embeds.

Inputs to gather

Item list (image or embed URL, title, caption, meaningful vs decorative), grid density (two or three columns), whether a filter bar is needed, and light / dark / system theme.

Rules

Wrap iframes, video and map-like boxes in .bf-embed-responsive (16:9). Add .bf-embed-responsive--4-3 for a taller ratio. Non-replaced content inside the box needs .bf-embed-responsive--item.
There is no .bf-card or .bf-gallery. A media card is an <article> with a border, radius and padding written as var(--bf-*) declarations, or an image plus a body block.
Lay out cards with .bf-row and .bf-col-* that sum to 12 or less. Use .bf-container.bf-container--break-md so columns stack below 768px.
Meaningful images take real alt text. Decorative images take alt="".
Prefer <figure> with <figcaption> for a single captioned image.
A filter bar is a <nav aria-label="…"> of .bf-btn links; mark the active filter with aria-current="page".
Optional image treatments use .bf-filter-grayscale, .bf-filter-blur, .bf-filter-invert, .bf-filter-dim-images or .bf-filter-none. Do not invent filter classes.
Keep custom CSS out of the page unless the task asks for crop or object-fit rules that tokens cannot cover.

Recipe

Pick a class-based build (bullframe-core has the table).
Emit the scaffold with skip link and container.
Optional hero row, then optional filter <nav>.
Emit the grid: one .bf-row, equal .bf-col-4 or .bf-col-6 children.
Each cell is an <article> or <figure> with image or embed, then title and caption.
Re-read and delete any class that is not in api.json.

Example

examples/album.html is a six-tile album with a filter bar, captioned articles and a 16:9 embed section. Placeholders stand in for real assets.

Expected output

One HTML file with responsive embeds and a grid whose column classes sum to at most 12 per row. No gallery library and no invented media classes.

Failure modes

Inventing .bf-gallery, .bf-media, .bf-card or .bf-aspect-ratio.
A bare <iframe> or <video> without .bf-embed-responsive.
Missing or placeholder alt on meaningful photos.
Per-breakpoint column classes such as .bf-col-md-4 (they do not exist).
Filter chips built from unlabelled <div>s instead of a <nav> and buttons or links.

Do not

Do not add a lightbox or carousel library unless the task explicitly asks for one.
Do not put decorative images in the accessibility tree with non-empty alt text.
Do not use the classless build for a multi-column media grid; it has no grid utilities.

Canonical docs

Embeds: https://bullframecss.marcopontili.com/utilities/embeds.md
Filters: https://bullframecss.marcopontili.com/utilities/filters.md
Grid: https://bullframecss.marcopontili.com/utilities/grid.md
Cards: https://bullframecss.marcopontili.com/components/cards.md
Live album and media examples: https://bullframecss.marcopontili.com/examples

Bundled files

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

examples/album.html7 KB

Frequently asked questions

What does the Bullframe Media AI skill do?

Build galleries, responsive embeds and media grids with Bullframe CSS. Use when creating an album, photo grid, video or map embed, figure with caption, or mixed media cards.

Why use Bullframe Media on TypingMind?

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

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

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 Media?

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

Is the Bullframe Media 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

Camsnap

openclaw

OrganizationPopular

Capture frames or clips from RTSP/ONVIF cameras and local webcams, including USB pan/tilt/zoom control.

Content Engine

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content…

Fal Ai Media

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio…

Video Editing

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Media

When to use

Inputs to gather

Rules

Recipe

Example

Expected output

Failure modes

Do not

Canonical docs

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now