game-studio
Skill2 starsChanged 28 days agoApache-2.0View on GitHub
Orchestrates a complete virtual game development studio pipeline using Gemini 4 Argon and Antigravity. Guides GDD (Game Design Document) drafting, core loop mechanics, sprint planning, procedural world building, audio synthesis, and multi-department review. Use when designing, architecting, building, or playtesting 2D/3D games from scratch.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- DECRUX9812/hermes-plugin-gameforgetheir own version, first seen Oct 25, 2026
- jonmumm/skillstheir own version, first seen Oct 21, 2026
- AVANT-ICONIC/skillstheir own version, first seen Oct 13, 2026
- openai/pluginstheir own version, first seen Oct 13, 2026
- caucy2026/skillstheir own version, first seen Oct 13, 2026
- fea-lib/skillstheir own version, first seen Aug 10, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- openai/plugins★ 7.8ksame name
- DECRUX9812/hermes-plugin-gameforge★ 44same name
- jonmumm/skills★ 2same name
- caucy2026/skills★ 1same name
- fea-lib/skills★ 1same name
- AVANT-ICONIC/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository108 other files it gives its agents.
- AGENTS.mdAGENTS.md
- everything-gemini-maintainerSkill
- adversarial-fuzz-generatorSkill
- agent-evalsSkill
- ai-first-engineeringSkill
- alloydb-omni-vectorSkill
- apache-kafka-streamsSkill
- api-craftsmanSkill
- architecture-designerSkill
- argon-3d-game-engineSkill
- argon-3d-scene-architectSkill
- argon-procedural-asset-generatorSkill
- argon-visual-critique-loopSkill
- argo-workflowsSkill
- autonomous-incident-healerSkill
- axum-web-serviceSkill
- bigquery-vector-searchSkill
- browser-qa-testerSkill
- chromadb-vector-storeSkill
- cilium-ebpf-networkingSkill
- clickhouse-analyticsSkill
- cloud-deploy-canarySkill
- cloudflare-r2-object-storageSkill
- cloudflare-workersSkill
- cloud-run-agentsSkill
- context-cachingSkill
- context-distillation-compressorSkill
- context-warmerSkill
- continuous-learningSkill
- cost-oracle-finopsSkill
- cross-repo-swarm-syncSkill
- cve-remediation-orchestratorSkill
- database-architectSkill
- dataproc-spark-analyticsSkill
- dbt-transformationSkill
- debezium-cdcSkill
- devops-pipelineSkill
- distributed-rate-limitingSkill
- docker-compose-orchestratorSkill
- duckdb-local-olapSkill
- dynamic-thinking-allocationSkill
- ebpf-microvm-sandboxSkill
- ebpf-sandbox-enforcerSkill
- elephant-goldfish-modelSkill
- envoy-ai-gatewaySkill
- ephemeral-swarm-orchestratorSkill
- fastapi-productionSkill
- fullstack-nextjsSkill
- game-audio-synthesizerSkill
- gemini-function-callingSkill
- gemini-groundingSkill
- gemini-live-audio-transcriberSkill
- gemini-live-multimodalSkill
- gemini-live-screen-visionSkill
- gemini-multimodalSkill
- genetic-prompt-cross-pollinatorSkill
- git-craftsmanSkill
- github-opsSkill
- google-axSkill
- google-flow-orchestratorSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 45
Before writing code, the studio establishes the game's foundation:
- Very specific: line 51
Every project begins with a structured GDD stored in docs/gdd/<title>.md:
- Distinctive: line 76
Before certifying release, the studio conducts a multi-lens review:
- Distinctive: line 105
When building games in Antigravity, delegate according to department expertise:
“Common” is measured: kept by at least 6 in 10 of the 6 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.
Files
Game Studio Orchestrator (game-studio)
The Game Studio Orchestrator transforms Google Antigravity and Gemini into an autonomous multi-role game development studio (inspired by studio hierarchies like Claude-Code-Game-Studios and elevated with Gemini 4 Argon's spatial reasoning). It coordinates creative vision, engine programming, procedural world generation, audio synthesis, and quality assurance into a disciplined production pipeline.
🏛️ Virtual Game Studio Organizational Hierarchy
flowchart TD
Director["👑 Game Director / Producer\n(Guards Vision, GDD, Milestones & Greenlights)"]
subgraph CreativeDept["Creative & Design Track"]
Director --> Designer["📐 Lead Game Designer\n(Core Loops, Economy, Mechanics, Pacing)"]
Director --> Narrative["📜 Narrative Designer\n(Lore, Dialogue, Environmental Storytelling)"]
end
subgraph EngineeringDept["Engineering & Physics Track"]
Director --> TechLead["💻 Spatial Game Architect\n(Three.js, WebGPU, Rapier/Cannon, 60 FPS Engine)"]
TechLead --> Physics["⚙️ Physics & Gameplay Programmer\n(Controllers, Decoupled Loops, Collisions)"]
end
subgraph ArtAudioDept["Art, World & Sensory Track"]
Director --> TechArtist["🎨 Procedural World Builder\n(Algorithmic Meshes, Vertex Colors, Instanced Shaders)"]
Director --> SoundLead["🎵 Audio Synthesizer\n(Web Audio API SFX, Dynamic Ambient Music)"]
end
subgraph QADept["QA & Polish Track"]
Director --> QALead["🧪 QA & Balance Playtester\n(Playability, Difficulty Curve, Frame Profiling)"]
QALead --> VisualCritic["👁️ Visual Critique Loop\n(Multimodal Frame Auditing & Refinement)"]
end📋 The 5-Phase Studio Production Lifecycle
Phase 0: High Concept & Pitch Matrix
Before writing code, the studio establishes the game's foundation:
- One-Sentence Hook: What makes this game immediately compelling?
- The 3 Core Pillars: Non-negotiable design principles that every feature must support.
- Target Emotion: What should the player feel? (e.g., Kinetic momentum, claustrophobic dread, puzzle mastery).
Phase 1: Game Design Document (GDD) Standardization
Every project begins with a structured GDD stored in docs/gdd/<title>.md:
- High Concept & Core Hook
- Core Gameplay Loop:
Action -> Feedback -> Reward -> Progression - Mechanics & Controls Specification: Primary inputs (WASD, Mouse, Touch), velocities, jump curves, acceleration.
- World & Level Architecture: Spatial scale, boundaries, obstacles, collectible placement.
- Aesthetic Direction: Color palette, lighting atmosphere, shader effects, camera perspective.
- Audio Landscape: Ambient soundscapes, interactive SFX cues, dynamic musical cues.
- Technical Specifications: Frame rate target (60 FPS), draw call ceiling ($< 100$), memory disposal rules.
Phase 2: Technical Sandbox & Physics Greybox
The spatial-game-architect constructs a playable greybox:
- Decoupled fixed-timestep loop (60Hz physics accumulator).
- Player controller with responsive input handling.
- Placeholder bounding boxes and collision volumes.
Phase 3: Procedural Assets & World Synthesis
The studio avoids multi-megabyte 3D downloads by leveraging procedural synthesis:
argon-procedural-asset-generator: Algorithmic terrain heightmaps, vertex-colored meshes, andInstancedMeshscattering.- Procedural canvas textures and custom GLSL/TSL shaders.
Phase 4: Procedural Audio & Sensory Feedback
The studio equips the game with rich sensory feedback:
game-audio-synthesizer: Pure Web Audio API procedural synthesis for lasers, jumps, explosions, coin chimes, and ambient music without external audio files.
Phase 5: Studio Critique & Gold Master Gate
Before certifying release, the studio conducts a multi-lens review:
- Design Review: Is the core loop intuitive within the first 5 seconds?
- Visual Critique:
argon-visual-critique-loopaudits camera framing, lighting contrast, and shadow acne. - Performance Audit: Does the game maintain $\ge 60\text{ FPS}$ with zero WebGL memory leaks?
🛠️ CLI Studio Workflow
Everything Gemini provides native CLI commands to orchestrate your studio:
# 1. Draft a complete Game Design Document (GDD)
everything-gemini game-studio gdd "neon-drifter"
# 2. Generate a phased milestone sprint plan
everything-gemini game-studio plan "neon-drifter"
# 3. Audit game codebase against 60 FPS budgets and memory disposal
everything-gemini game-studio audit
# 4. Initialize a complete playable 3D game template
everything-gemini game-studio init desk-racer🎮 Subagent Delegation Cheat-Sheet
When building games in Antigravity, delegate according to department expertise:
| Department Task | Assigned Subagent / Skill | Key Deliverables |
| Vision & Production | game-director | Comprehensive GDD, Milestone tracking, Release sign-off. |
| Engine & Scene Graph | spatial-game-architect | Three.js / WebGPU renderer, camera rigs, post-processing. |
| Physics & Controller | argon-3d-game-engine | Fixed 60Hz physics loop, arcade controller, collision matrix. |
| Procedural Assets | argon-procedural-asset-generator | Terrain meshes, low-poly vehicles, procedural textures. |
| Audio & SFX | game-audio-synthesizer | Web Audio API procedural sound effects & background music. |
| Visual QA | argon-visual-critique-loop | Canvas snapshot critique, shadow bias, PBR material tuning. |
| Automated Playtesting | browser-qa | Automated browser navigation, keypress simulation, WebP capture. |
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
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.

