Game Feel logo

Game Feel

Community
rshankras
game-feel

Game feel ("juice") for Apple apps — celebration choreography, haptic vocabulary design, sound-effect layers, and the event×channel feedback audit. Use when big moments fall flat, when designing haptics or SFX, or when auditing whether every meaningful event actually reaches the user.

Overview

Publisherrshankras
Repositoryclaude-code-apple-skills
Skill namegame-feel
Stars
744
Forks
70
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Game Feel 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/rshankras/claude-code-apple-skills.git /tmp/claude-code-apple-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-apple-skills/skills/design/game-feel .claude/skills/game-feel
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Game Feel 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 Game Feel 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 Game Feel 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.

Game Feel (Juice)

Makes an app's meaningful moments land — through coordinated motion, haptics, and sound. Animation technique lives in design/animation-patterns; confetti/badge generation lives in generators/milestone-celebration. This skill is the discipline layer: which events deserve feedback, on which channels, and how to verify nothing important is silent.

When This Skill Activates

Use this skill when the user:

  • Says the app feels flat, lifeless, or "lacks juice/polish/delight"
  • Wants celebrations designed (winners, streaks, reveals, score changes)
  • Asks to design or review haptics (vocabulary, Core Haptics, .sensoryFeedback)
  • Asks about sound effects, buzzers, countdown ticks, or fanfares
  • Wants a feedback audit — do the right events fire the right channels?
  • Is building a party/group game where the phone is shared, passed, or watched at a distance

Core Principles

1. Channels have different reach — match the channel to the audience

ChannelWho perceives it
HapticsOnly the person holding the device
Screen motionWhoever is looking at the screen
AudioThe whole room
Torch / flashThe whole room, even in noise

A single-user utility can lean on haptics. A shared-phone or room-facing app (party games, kitchen timers, presentations) must put its signature moments on a room-scale channel. The most common juice failure: all feedback is haptic, and the phone is lying on a table.

2. Feedback scales with rarity

Tick < action confirmed < success < round complete < winner. If the rarest event (winning) fires the same pattern as a routine one (round end), the app has no climax. Reserve the biggest pattern, the confetti burst, and the fanfare for the rarest event.

3. Escalation must agree across channels

If the timer's ring turns amber at 10s and red at 5s, the haptic tier and any audio tick must escalate at the same thresholds. Cross-channel disagreement reads as broken, not layered.

4. Single-owner rule

Exactly one code layer fires feedback for a given event. When an engine and a view-store both react to "music stopped", the user gets a double-buzz. Decide the owner (usually the layer closest to the state machine) and make the other layer silent.

5. Juice amplifies meaning — it never decorates

Every effect must be attached to an event the user cares about. Ambient/always-on effects (background particles, looping glows) are texture, not feedback — keep them static or slow, and never let them compete with event feedback.

6. Every channel needs an accessibility story

  • Motion → gate large-scale motion on Reduce Motion, with a static equivalent
  • Haptics → user-facing toggle (the system provides no global haptics setting for Core Haptics)
  • Sound → mute toggle independent of system volume; a deliberate, documented silent-switch policy

Decision Tree

What do you need?
├─ Which events should have feedback, and on which channels?
│  └─ → feedback-audit.md (event×channel matrix + three-lens audit)
├─ Design or review haptics (vocabulary, service architecture, APIs)
│  └─ → haptic-design.md
├─ Add a sound-effect layer (assets, latency, AVAudioSession coexistence)
│  └─ → sound-design.md
├─ HOW to animate a celebration/transition you've already decided on
│  └─ → design/animation-patterns (springs, transitions, symbol effects)
├─ Generate confetti / badge / milestone UI code
│  └─ → generators/milestone-celebration
└─ Animated SF Symbols for feedback moments
   └─ → design/sf-symbols (preset vocabulary)

Review Checklist

When reviewing an app's game feel, verify:

  • Signature moments hit ≥2 channels (e.g. winner = motion + haptic + sound)
  • Room-facing events use a room-scale channel (audio, display-size motion, torch)
  • Rarity gradient exists — the rarest event has visibly/audibly the biggest feedback
  • No channel disagreement — escalation thresholds match across visual/haptic/audio
  • Single owner per event — no double-fire from two layers
  • Score/number changes animate (.contentTransition(.numericText())) — values never teleport
  • State changes transition — no hard cuts between phases of a flow
  • Reduce Motion parity — every gated effect has a static equivalent conveying the same information
  • User controls exist — haptics toggle; mute toggle if there's an SFX layer
  • Loading/waiting states have anticipation — determinate progress or a live effect, not a bare spinner at a climactic moment

Reference Files

FileContent
feedback-audit.mdEvent×channel matrix method, three-lens audit (runnable subagent prompts), scoring rubric, output format
haptic-design.mdAPI decision table, semantic-vocabulary service architecture, pattern design rules, lifecycle, pitfalls
sound-design.mdMinimal SFX kit, asset formats and latency, AVAudioSession coexistence with music, silent-switch policy, pitfalls

Related Skills

  • design/animation-patterns — the how of every motion technique
  • design/sf-symbols — symbol effect vocabulary for feedback glyphs
  • generators/milestone-celebration — production confetti/badge/celebration code
  • ios/accessibility-audit — Reduce Motion and assistive-tech verification

References

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 Game Feel AI skill do?

Game feel ("juice") for Apple apps — celebration choreography, haptic vocabulary design, sound-effect layers, and the event×channel feedback audit. Use when big moments fall flat, when designing haptics or SFX, or when auditing whether every meaningful event actually reaches the user.

Why use Game Feel on TypingMind?

Because you install it once and use it with any model. Game Feel 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 Game Feel in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rshankras/claude-code-apple-skills/tree/main/skills/design/game-feel. 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 Game Feel?

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 Game Feel?

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

Is the Game Feel AI skill free?

Yes. It is published on GitHub by rshankras 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 👇