Game Dev logo

Game Dev

Community
notque
game-dev

Game development: design, asset pipelines, Phaser, vanilla JS frontend, GM mode, match booking.

Overview

Publishernotque
Repositoryvexjoy-agent
Skill namegame-dev
Stars
443
Forks
50
Bundled files
164
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.

  • 164 bundled files

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

  • Open source

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

Installation

Install the Game Dev 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.
    https://github.com/notque/vexjoy-agent/tree/main/skills/game/game-dev
  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/notque/vexjoy-agent.git /tmp/vexjoy-agent
mkdir -p .claude/skills
cp -r /tmp/vexjoy-agent/skills/game/game-dev .claude/skills/game-dev
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Game Dev 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 Dev 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 Dev 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 Development

Five modes: Design (diagnosis, auditing, improvement), Pipeline (full lifecycle orchestration), Sprite (AI sprite generation), Phaser (2D engine builds), GM (large multi-system implementations). Cross-cutting concerns (audio, QA, deploy) load as needed. Classify the request and follow the matching section.

Mode Selection

ModeSignals
Designgame design, improve game, retention, churn, core loop, audit, game feel, balance, economy
Pipelinemake game, scaffold, game lifecycle, game audio, deploy game, game QA
SpriteAI sprite, generate character, portrait, spritesheet, animated sheet, pixel art
PhaserPhaser, 2D game, platformer, arcade physics, tilemap, side scroller
GMlarge GM implementation, multi-system GM, CPU systems, multi-wave overhaul

If the request spans modes, load both primary references. Design + Pipeline is common (design an improvement then implement it). Sprite + Phaser is common (generate assets then wire into a Phaser game).


Design Mode

Evidence-led game design diagnosis with 61 runnable capabilities. Start from repository evidence; never guess when the repo can answer.

Workflow

  1. Intake. Read target repository's governing files. Search for game, product, UI, analytics, and research guidance. Use file search to find design docs, player copy, rules, UI, config, tests, analytics, issues. Separate facts into: observed, documented, measured, inferred.
  2. Ask only what the repo cannot answer. Which player moment matters? What external evidence exists (playtests, telemetry, reviews)? Which constraints bind (platform, phase, team, time)?
  3. Load references. Route greedily -- load every module that could change the recommendation:
SignalLoad
Promise, fantasy, loops, goalsreferences/core-loop-and-pillars.md
Ideation, novelty, removal, reusereferences/creative-and-options.md
Player motives, personas, valuesreferences/player-and-social.md
Information, bias, randomnessreferences/cognition-and-choice.md
Failure, difficulty, fairnessreferences/fairness-and-failure.md
FTUE, flow, friction, sessionreferences/pacing-and-return.md
Co-op, competition, socialreferences/social-and-competitive.md
Rewards, currencies, passesreferences/progression-and-economy.md
Pitch, mood, prototypereferences/emotion-and-presentation.md
Scope, sequence, estimatesreferences/planning-and-production.md
Full health reportAll modules + references/full-diagnostic.md
  1. Diagnose. Trace the player path: cue -> interpretation -> choice -> response -> cost/reward -> feedback -> next intention. State player consequence, evidence, competing explanations, confidence, severity.
  2. Decide. Offer 2-5 distinct options. For each: player-visible change, pillar fit, scope, dependencies, effort, reversibility, success metric, stop rule. Prefer reversible experiments. Reject dark patterns.
  3. Completion gate. Every finding has evidence or is marked as inference. Every recommendation has a validation plan.

Discovery Mode

When request is bare "game design" or "what reviews are available": load references/capability-catalog.md and present the full domain-organized catalog of 61 capabilities.

Autonomous Improvement

When asked to improve a game's retention, churn, or engagement: load references/autonomous-improvement.md. Inspect the real game, run relevant capabilities, make the smallest safe reversible improvement, verify, leave a measurement plan.


Pipeline Mode

Full lifecycle orchestration: SCAFFOLD -> ASSETS -> DESIGN -> AUDIO -> QA -> DEPLOY. Each phase can be entered independently.

Entry Detection

RequestEntry Phase
make a game, new gameSCAFFOLD
generate assets, add spritesASSETS
add juice, particles, screen shakeDESIGN
add audio, background musicAUDIO
test game, visual regressionQA
deploy, ship, publish, iOSDEPLOY

Phase 1: SCAFFOLD

Detect engine (Three.js, Phaser, or vanilla canvas). Delegate to the appropriate engine skill or scaffold from template.

Phase 2: ASSETS

Route by asset type:

AssetReference
3D model, GLB, meshreferences/game-asset-generator.md + references/meshyai.md
Sprite, pixel art, tileLoad Sprite mode below
Image, texture, concept artreferences/fal-ai-image.md
Environment, gaussian splatreferences/worldlabs.md
Free assets, Sketchfabreferences/asset-sources.md
Motion data, BVH, mocapreferences/motion-pipeline.md

Phase 3: DESIGN

Add game feel: screen shake, particles, hit-stop, juice. Load references/game-feel-patterns.md.

Phase 4: AUDIO

Web Audio API patterns, AudioManager, AudioBridge. Load references/game-audio.md.

Phase 5: QA

Automated testing, visual regression, Playwright, canvas seams. Load references/game-qa.md.

Phase 6: DEPLOY

TargetReference
GitHub Pages, Vercel, generalreferences/deploy.md
iOS via Capacitorreferences/capacitor-ios.md
Promo videoreferences/promo-video.md

Sprite Mode

AI sprite generation: portrait, portrait-loop, spritesheet, per-row animated sheets. Load references/game-sprite-pipeline.md for the full pipeline.

Quick Steps

  1. Detect format. Portrait (single image), portrait-loop (idle animation), spritesheet (action set), per-row (multiple animations in rows).
  2. Select backend. Load references/backend-chain.md for dispatch: Codex CLI primary, Gemini fallback.
  3. Select style. Load references/style-presets.md for 9 era/hardware presets.
  4. Generate. Follow the pipeline for the detected format.
  5. Post-process. Background removal, palette quantization, sheet assembly.
  6. Validate. Check dimensions, frame counts, transparency, color consistency.

Phaser Mode

Phaser 3 2D game engine builds. Load references/phaser-gamedev.md for the full methodology.

Core Patterns

Load references/core-patterns.md for scene lifecycle, transitions, and input handling.

TaskReference
Scene lifecycle, transitionsreferences/core-patterns.md
TypeScript entry, Boot/Game skeletonsreferences/build-scaffolds.md
Arcade physics, collisionreferences/arcade-physics.md
Tilemaps, tile layersreferences/tilemaps.md, references/tilemaps-and-physics.md
Screen shake, particles, hit-stopreferences/game-feel-patterns.md
Polish scaffoldsreferences/polish-scaffolds.md
Animate scaffoldsreferences/animate-scaffolds.md

GM Mode

Evidence-to-live implementation for large GM programs (multi-system, multi-wave, CPU-intensive). Load references/gm-brilliant-implementation.md for the full methodology.

Applicability Gate

GM mode applies only when: multiple interconnected game systems change, CPU performance is a concern, or the implementation spans multiple deployment waves. If the gate fails, route to quick, workflow, or the target project's skill.

Key References

SignalReference
Stage contracts, checkpointsreferences/stage-contracts.md
CPU systems harmonyreferences/cpu-systems-harmony.md
Quality gatesreferences/quality-gates.md
Workflow DAG (34 stages)references/workflow-dag.md

Deep References

Load when the task needs detailed patterns, catalogs, or specifications.

Design

SignalReference
61 runnable capabilitiesreferences/capability-catalog.md
Capability coverage matrixreferences/capability-matrix.md
Full diagnostic report formatreferences/full-diagnostic.md
Individual capability specsreferences/capabilities/*.md (61 files)
VFX containment rulesreferences/vfx-containment.md
Menus, HUD, shop, settings, or other screen UI (load first)skills/shared-patterns/ui-design-judgment.md (game genre conventions win over web defaults), then skills/frontend/frontend/references/distinctive-frontend-design-refs/game-ui-polish.md

Pipeline

SignalReference
Game asset generatorreferences/game-asset-generator.md
Meshy AI 3D modelsreferences/meshyai.md
Fal.ai image generationreferences/fal-ai-image.md
WorldLabs environmentsreferences/worldlabs.md
Asset sources catalogreferences/asset-sources.md
Motion pipelinereferences/motion-pipeline.md
Game audioreferences/game-audio.md
Game QAreferences/game-qa.md
Deploy targetsreferences/deploy.md
Capacitor iOSreferences/capacitor-ios.md

Sprite

SignalReference
Full sprite pipelinereferences/game-sprite-pipeline.md
Backend dispatchreferences/backend-chain.md
Style presetsreferences/style-presets.md
Pixel art patternsreferences/pixel-art-sprites.md
Output formatsreferences/output-formats.md
Prompt rulesreferences/prompt-rules.md
Background removalreferences/bg-removal-local.md
Frame detectionreferences/frame-detection.md
Error catalogreferences/error-catalog.md

Phaser

SignalReference
Full Phaser methodologyreferences/phaser-gamedev.md
Core patterns, scene lifecyclereferences/core-patterns.md
Arcade physicsreferences/arcade-physics.md
Tilemaps and physicsreferences/tilemaps-and-physics.md
Game feel patternsreferences/game-feel-patterns.md
Performance patternsreferences/performance.md

GM

SignalReference
Full GM methodologyreferences/gm-brilliant-implementation.md
Stage contractsreferences/stage-contracts.md
CPU systems harmonyreferences/cpu-systems-harmony.md
Quality gatesreferences/quality-gates.md
Workflow DAGreferences/workflow-dag.md
Anchor alignmentreferences/anchor-alignment.md

Bundled files

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

and 104 more files.

Frequently asked questions

What does the Game Dev AI skill do?

Game development: design, asset pipelines, Phaser, vanilla JS frontend, GM mode, match booking.

Why use Game Dev on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/notque/vexjoy-agent/tree/main/skills/game/game-dev. 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 Dev?

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 Dev?

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

Is the Game Dev AI skill free?

Yes. It is published on GitHub by notque 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 👇