Fluid Design

Community

kemiljk

fluid-design

Design or refine springs, gestures, and interruptible motion when physical continuity or direct manipulation matters.

Overview

Publisher	kemiljk
Repository	`skills`
Skill name	`fluid-design`
Stars	64
Forks	3
Bundled files	2
License	MIT
Links	Skill source Repository

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

Installation

Install the Fluid Design 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/kemiljk/skills/tree/main/skills/fluid-design
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/kemiljk/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/fluid-design .claude/skills/fluid-design

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

Use it in TypingMind

Enable Fluid Design 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 Fluid Design 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 Fluid Design 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.

Fluid Design

Make interfaces feel like continuous physical systems, not discontinuous state flips.

Composition with other skills

This skill owns how interaction should feel.
modern-css-html owns the most native implementation that can still deliver that feel.
Prefer CSS/HTML when they can express the behaviour.
Use JavaScript/Motion/SwiftUI when you need interruption, velocity inheritance, gesture continuity, or spring physics CSS cannot express cleanly.

Defaults

Prefer springs over fixed-duration easings for interactive translation and scale.
Every user-triggerable animation must be interruptible.
Prefer direct manipulation over button-only indirection when the object can be grabbed.
Preserve velocity across gesture boundaries (release → settle/dismiss).
Keep shared identity across state/route changes when the same object survives.
Adapt interaction models to input method (mouse, trackpad, touch, keyboard).
Prefer FLIP, layout animation, or View Transitions for spatial continuity. Use direct layout-property animation only when appropriate to the component and its measured rendering cost.
Add progressive resistance at edges and rubber-banding at boundaries.
Sequence choreography: acted object leads, surroundings yield, then settle.
Provide a reduced-motion path that preserves affordances with safer alternatives.

Prefer / Reject

Prefer	Reject
`type: "spring"` for interactive motion	`transition: all`
CSS `transition` for colour/opacity	Expensive layout animation without a reason or performance check
Alternate reduced-motion layouts	`animation: none !important` as the only a11y plan
Velocity-aware hover gating on dense surfaces	Debounced hover that feels dead, or ungated strobing
Transform + opacity	Long locked keyframe sequences users must wait out

Tuning starting points

UI springs: stiffness 200–400, damping 20–30, mass 0.8–1.2
Layout reflow: ~200–350ms or a well-damped spring
Gesture dismiss: combine offset threshold + velocity threshold
Dense hover surfaces: EMA-smoothed velocity with separate engage/disengage thresholds

Input and accessibility

Desktop + motion: springs, deflection, velocity gating as designed.
Desktop + reduced motion: keep hierarchy and controls; swap spatial physics for quieter opacity/colour/snap models.
Touch: prefer drag/scroll metaphors over hover-dependent discovery.
Keyboard: every interactive surface remains operable without pointer precision.

Review checklist

Can the user reverse or redirect mid-motion?
Does travel distance/velocity change the motion response?
Are only compositor-friendly properties animating for interaction?
Does reduced motion keep the same tasks possible?
Do list/grid reflows preserve spatial memory?
Are hover-dense regions gated against fast pointer sweeps?
Is JS justified because CSS cannot express the behaviour?

References

Read Motion recipes for a matching gesture or transition implementation.
Read Principle notes when deciding how continuity should behave. Load only the reference needed for the task.

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 Fluid Design AI skill do?

Design or refine springs, gestures, and interruptible motion when physical continuity or direct manipulation matters.

Why use Fluid Design on TypingMind?

Because you install it once and use it with any model. Fluid Design 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 Fluid Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kemiljk/skills/tree/main/skills/fluid-design. 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 Fluid Design?

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 Fluid Design?

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

Is the Fluid Design AI skill free?

Yes. It is published on GitHub by kemiljk 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

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Frontend Slides

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a…

Plan Canvas

Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or…

Improve Codebase Architecture

mattpocock

CommunityPopular

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Fluid Design

Composition with other skills

Defaults

Prefer / Reject

Tuning starting points

Input and accessibility

Review checklist

References

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now