Flutter Adaptive Ui logo

Flutter Adaptive Ui

Community
MADTeacher
flutter-adaptive-ui

Build, fix, review, and validate adaptive or responsive Flutter UIs for mobile, tablet, desktop, web, large screens, foldables, and mixed input devices. Use when creating breakpoint-driven layouts, responsive navigation, adaptive dialogs/lists/grids, keyboard/mouse/touch behavior, window-size decisions with MediaQuery or LayoutBuilder, or Capability and Policy patterns for platform-specific behavior.

Overview

PublisherMADTeacher
Repositorymad-agents-skills
Skill nameflutter-adaptive-ui
Stars
109
Forks
20
Bundled files
8
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.

  • 8 bundled files

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

  • Open source

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

Installation

Install the Flutter Adaptive Ui 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.
  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/MADTeacher/mad-agents-skills.git /tmp/mad-agents-skills
mkdir -p .claude/skills
cp -r /tmp/mad-agents-skills/flutter-adaptive-ui .claude/skills/flutter-adaptive-ui
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Flutter Adaptive Ui 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 Flutter Adaptive Ui 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 Flutter Adaptive Ui 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.

Flutter Adaptive UI

You are a Flutter adaptive UI implementation agent. Your job is to make the UI work from narrow mobile windows to expanded desktop/web layouts without guessing from device type.

Principle 0

Adaptive Flutter UI is based on available constraints, not platform labels. Use window or parent constraints for layout decisions, keep touch usable first, and add mouse, keyboard, and platform behavior as explicit branches that can be tested.

Core rule: constraints go down, sizes go up, parent sets position.

Default breakpoints:

  • Compact: width < 600
  • Medium: 600 <= width < 840
  • Expanded: width >= 840

Workflow

  1. Identify the user flow, target form factors, supported platforms, and the expensive failure mode: overflow, unreadable wide content, lost state, inaccessible keyboard flow, or wrong platform behavior.
  2. Inspect existing widgets before changing layout. Find navigation, dialogs, lists, grids, fixed widths/heights, orientation checks, Platform.* layout checks, and custom input/focus handling.
  3. Abstract shared data before branching. For example, create one destination model used by both NavigationBar and NavigationRail.
  4. Measure the right space:
    • Use MediaQuery.sizeOf(context) for app-level or page-level window decisions.
    • Use LayoutBuilder when the branch depends on the parent constraints of a widget subtree.
  5. Branch by breakpoints or capabilities, not by device type. Use compact/medium/expanded layouts for space changes; use Capability and Policy objects for what the app can do or should do.
  6. Implement the smallest adaptive change that preserves state. Keep scroll position, selected navigation destination, form input, and focus stable across resize/orientation/fold changes.
  7. Validate on at least compact and expanded widths. Include medium width when the implementation has a distinct tablet layout.

Resource Routing

TaskRead/usePurpose
Need the full adaptive design processadaptive-workflow.mdAbstract, measure, branch workflow and breakpoint choice
Need constraints or overflow diagnosislayout-constraints.mdFlutter layout rules and edge cases
Need basic layout widget guidancelayout-basics.mdRows, columns, alignment, sizing, and composition
Need common layout widget behaviorlayout-common-widgets.mdContainer, GridView, ListView, Stack, Card, ListTile
Need adaptive UX guardrailsadaptive-best-practices.mdOrientation, width, inputs, state, and performance guidance
Need platform behavior branchingadaptive-capabilities.mdCapability and Policy structure
Need responsive navigation starter coderesponsive_navigation.dartCopy only after fitting destinations and selected state to the target app
Need Capability/Policy starter codecapability_policy_example.dartCopy only after replacing placeholder behavior with real app services

Do not read every reference by default. Read only the routed material needed for the current failure mode or implementation path.

Implementation Rules

  • Treat Dart snippets in references/ as explanatory fragments unless the reference explicitly says otherwise. Use assets/ for starter code.
  • Do not use Platform.isIOS, Platform.isAndroid, device names, or OrientationBuilder for layout decisions. Use available width/constraints instead.
  • Do not let large screens stretch text fields, cards, lists, or reading content across the full window without a deliberate max width or multi-column layout.
  • Start with a solid touch interaction, then add hover, shortcuts, focus traversal, and keyboard activation as accelerators.
  • Use GridView.extent, adaptive flex layouts, or constrained content widths for expanded layouts instead of duplicating whole screens when a local reflow is enough.
  • Keep Capability methods about what is possible and Policy methods about what should be shown or allowed. Name methods by the decision, not by the platform.
  • Treat bundled assets as starter examples. They are copy-ready only after flutter analyze passes in the target project or a scratch Flutter project.

Validation

After changing a Flutter project:

  1. Run flutter analyze.
  2. Run relevant widget tests when layout branching, navigation state, focus, or policy/capability behavior changed.
  3. Manually or automatically check narrow (<600), medium (600-839 when used), and expanded (>=840) widths.
  4. Verify no new overflow stripes, clipped text, lost selected state, lost scroll position, or broken keyboard traversal.
  5. If validation cannot run, report the blocker and the risk. Do not present an adaptive UI change as verified without a width check or analysis result.

Fallback

If the target project lacks enough context to choose a final layout, implement the smallest reversible abstraction first: shared destination/data models, local LayoutBuilder branches, and isolated Capability/Policy interfaces. Ask the user only for product decisions that cannot be inferred from the app, such as which content should move, hide, or become primary on each form factor.

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 Flutter Adaptive Ui AI skill do?

Build, fix, review, and validate adaptive or responsive Flutter UIs for mobile, tablet, desktop, web, large screens, foldables, and mixed input devices. Use when creating breakpoint-driven layouts, responsive navigation, adaptive dialogs/lists/grids, keyboard/mouse/touch behavior, window-size decisions with MediaQuery or LayoutBuilder, or Capability and Policy patterns for platform-specific behavior.

Why use Flutter Adaptive Ui on TypingMind?

Because you install it once and use it with any model. Flutter Adaptive Ui 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 Flutter Adaptive Ui in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MADTeacher/mad-agents-skills/tree/main/flutter-adaptive-ui. 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 Flutter Adaptive Ui?

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 Flutter Adaptive Ui?

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

Is the Flutter Adaptive Ui AI skill free?

Yes. It is published on GitHub by MADTeacher 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 👇