Responsive Layout

Organization

KyaniteLabs

responsive-layout

Use when a page or component must survive narrow containers, long or translated content, zoom, reflow, or overflow without device-name breakpoints.

Overview

Publisher	KyaniteLabs
Repository	`tastecheck`
Skill name	`responsive-layout`
Stars	10
Forks	7
Bundled files	4
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.
4 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by KyaniteLabs on GitHub. Read the source before you install it.

Installation

Install the Responsive Layout 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/KyaniteLabs/tastecheck/tree/main/skills/responsive-layout
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/KyaniteLabs/tastecheck.git /tmp/tastecheck
mkdir -p .claude/skills
cp -r /tmp/tastecheck/skills/responsive-layout .claude/skills/responsive-layout

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

Use it in TypingMind

Enable Responsive Layout 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 Responsive Layout 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 Responsive Layout 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.

Responsive Layout

Responsive layout is intrinsic reflow plus content-led breakpoints/container queries, not named-device CSS.

The decision order

Start mobile-first with Grid/Flex intrinsic sizing (minmax, auto-fit, clamp, %/fr).
Add breakpoints only where content breaks; reusable components use container queries.
Verify minimum supported viewport, 200–400% zoom, long/translated content, narrow embeds, and wide views without overflow or collapse.

Preserve hierarchy under pressure

Start with non-disappearing content, reading order, and narrowest real container. Choose stack/reorder/progressive reveal/rail from observed pressure; test long content, locale, zoom, and embeds before calling it responsive.

Non-negotiables

Start from the narrowest supported content state; avoid device-name breakpoints.
Prevent overflow with min-width: 0, bounded media, and wrapping; reflow rather than shrink to unusable.
Prefer container queries for reusable components when their behavior depends on their container, not the viewport.
At narrow widths and zoom, reading/interaction should not require two-dimensional scrolling. Isolate essential exceptions (wide tables, maps, timelines, canvases) in a labelled, keyboard-operable scroll region.

Quick-start patterns

Use references/patterns.md for grid, sidebar, stack, cluster, and container-query patterns. Start with minmax(min(16rem, 100%), 1fr), min-width: 0, logical sizing, and content-led breakpoints.

Reference files

assets/layout-patterns.css — intrinsic examples after pressure evidence.
references/patterns.md — patterns, units, images, and overflow debugging.
references/decision-records.md — novel-case ADR rules.

Evidence

Use five-field ledger; start Reason with check ID.

Status	Reason	Remediation	Evidence	Provenance
	layout-strategy — content hierarchy and intrinsic composition
	containment — breakpoint and container-query rationale
	narrow-reflow — 320px, long-content, and overflow result
	zoom-interaction — zoom and keyboard-reachable interaction result
	handoff — component and accessibility boundary

Pressure test

Each row names longest-pressure fixture, width/zoom, expected and observed result (or fail-closed missing evidence). Test full shell, narrow, 400%, and narrow embed; record what stays first/stacks/folds and why. No rendered build means plan, not pass.

How to deliver

Deliver content-led layout/breakpoints and rerunnable narrow/long/container/zoom/keyboard evidence; hand type, rhythm, and state concerns onward.

Contract (generated)

Canonical detail: contract.json.

Route: A layout needs intrinsic reflow, responsive hierarchy, container behavior, or overflow repair (+1 in contract.json); avoid: The request is only to choose a spacing scale or type system (+1 in contract.json)
Exclude: Do not choose breakpoints from device names (+1 in contract.json)
Stop / handoff: Pause when content priority is unknown and reflow would silently hide required information (+1 in contract.json); receives [art-direction, design-system-interview, improve-existing-website, spacing-system, tasteroll, theming, web-typography] -> sends [component-states, form-ux, a11y-pass, deslop-ui, i18n-ready]
Output: An intrinsic layout strategy with justified breakpoints and responsive verification evidence
Evidence: table_with_evidence with status, reason, remediation, evidence, provenance.

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 Responsive Layout AI skill do?

Use when a page or component must survive narrow containers, long or translated content, zoom, reflow, or overflow without device-name breakpoints.

Why use Responsive Layout on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/KyaniteLabs/tastecheck/tree/main/skills/responsive-layout. 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 Responsive Layout?

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 Responsive Layout?

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

Is the Responsive Layout AI skill free?

Yes. It is published on GitHub by KyaniteLabs 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

Pretext

NousResearch

OrganizationPopular

Build creative browser demos with DOM-free text layout.

Sketch

Throwaway HTML mockups: 2-3 design variants to compare.

Tldraw Offline

Drive and script tldraw offline canvases with an agent.

Brand Guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Responsive Layout

The decision order

Preserve hierarchy under pressure

Non-negotiables

Quick-start patterns

Reference files

Evidence

Pressure test

How to deliver

Contract (generated)

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now