agentleFS
notquenotque/vexjoy-agent/skills/game/game-dev/SKILL.md

game-dev

Skill448 starsChanged 4 days agoMITView on GitHub

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

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the request spans modes, load both primary references.

    line 80
  2. Distinctive:

    Intake: Read target repository's governing files.

    line 93
  3. Distinctive:

    Completion gate: Every finding has evidence or is marked as inference.

    line 113
  4. Very specific:

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

    line 117
  5. Very specific:

    When asked to improve a game's retention, churn, or engagement: load references/autonomous-improvement.md.

    line 121
  6. Very specific:

    Add game feel: screen shake, particles, hit-stop, juice.

    line 160
  7. Distinctive:

    Generate: Follow the pipeline for the detected format.

    line 190
  8. Distinctive:

    Validate: Check dimensions, frame counts, transparency, color consistency.

    line 192
  9. Very specific:

    Probe: Run unity --version, unity editors -i --json, and unity license status --json.

    line 231
  10. Very specific:

    On a license error,: follow references/unity-licensing.md before you retry.

    line 236
  11. Distinctive:

    If the gate fails, route to quick, workflow, or the target project's skill.

    line 250

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Game Development

Six modes: Design (diagnosis, auditing, improvement), Pipeline (full lifecycle orchestration), Sprite (AI sprite generation), Phaser (2D engine builds), Unity (unity CLI, batch builds, tests, licensing), 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
UnityUnity project, unity CLI, Unity.exe -batchmode, -executeMethod, Unity build or tests, Unity license error, exit code 198
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. A folder with ProjectSettings/ProjectVersion.txt is a Unity project: switch to Unity mode.

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

Unity Mode

Build, test, and inspect Unity projects from a terminal, with the unity CLI or classic Unity.exe -batchmode. Load the reference that matches the task:

SignalReference
unity CLI install, version drift, JSON output, exit codes, editors, projects, Editor control, Hub CLI migrationreferences/unity-cli.md
Player build, compile check, tests, -executeMethod, CLI-to-Editor flags, project lock, parallel buildsreferences/unity-batchmode-builds.md
License errors, exit code 198, No valid Unity Editor license found, Personal entitlement, activation, CI seatsreferences/unity-licensing.md

Workflow

  1. Locate. Find the folder that holds ProjectSettings/ProjectVersion.txt; it can sit below the repository root. Read m_EditorVersion.
  2. Probe. Run unity --version, unity editors -i --json, and unity license status --json. Without the CLI, use classic Unity.exe; installing or upgrading software needs the user's OK.
  3. Pick the tool from the table in references/unity-batchmode-builds.md.
  4. Warn before launching. Batch runs can still bring Unity windows to the front, so tell the user before Unity starts on a desktop they are using, and group the runs.
  5. Run headless with --timeout and a log file: --log-file for unity build, -- -logFile <path> for unity run; unity test logs to <project>/Logs/Editor.log. Check unity editors running --json first: one Editor per project folder.
  6. Read the result. Branch on the exit code, then on errors[0].code, then on the log (error CS, Build Finished, Result:).
  7. On a license error, follow references/unity-licensing.md before you retry. Signals: Unity.exe exit 198, or CLI exit 6 with 198 in errors[0].message.

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.