Every section earns its tokens by focusing on Knowledge Delta — the gap between what Claude already knows and what a senior Godot engineer knows from shipping real products.
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versiongodot-masterExecute the skills CLI command in your project's root directory to begin installation:
Fetches godot-master from thedivergentai/gd-agentic-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate godot-master. Access via /godot-master in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
70
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
70
stars
Every section earns its tokens by focusing on Knowledge Delta — the gap between what Claude already knows and what a senior Godot engineer knows from shipping real products.
Before writing any system, answer these three questions for EVERY piece of state:
StatsComponent owns health, NOT the CombatSystem)apply_damage())health_changed signal)If you can't answer all three for every state variable, your architecture has a coupling problem. This is not OOP encapsulation — this is Godot-specific because the signal system IS the enforcement mechanism, not access modifiers.
Organize every feature into four layers. Signals travel UP, never down:
┌──────────────────────────────┐
│ PRESENTATION (UI / VFX) │ ← Listens to signals, never owns data
├──────────────────────────────┤
│ LOGIC (State Machines) │ ← Orchestrates transitions, queries data
├──────────────────────────────┤
│ DATA (Resources / .tres) │ ← Single source of truth, serializable
├──────────────────────────────┤
│ INFRASTRUCTURE (Autoloads) │ ← Signal Bus, SaveManager, AudioBus
└──────────────────────────────┘
Critical rule: Presentation MUST NOT modify Data directly. Infrastructure speaks exclusively through signals. If a Label node is calling player.health -= 1, the architecture is broken.
match_started, player_died, settings_changed). Debugging sprawl is the cost — limit events to < 15.CombatBus only for combat nodes). This is the compromise that scales.| Scenario | Strategy | MANDATORY Skill Chain | Trade-off |
|---|---|---|---|
| Rapid Prototype | Event-Driven Mono | READ: Foundations → Autoloads. Do NOT load genre or platform refs. | Fast start, spaghetti risk |
| Complex RPG | Component-Driven | READ: Composition → States → RPG Stats. Do NOT load multiplayer or platform refs. | Heavy setup, infinite scaling |
| Massive Open World | Resource-Streaming | READ: Open World → Save/Load. Also load Performance. | Complex I/O, float precision jitter past 10K units |
| Server-Auth Multi | Deterministic | READ: Server Arch → Multiplayer. Do NOT load single-player genre refs. | High latency, anti-cheat secure |
| Mobile/Web Port | Adaptive-Responsive | READ: UI Containers → Adapt Desk→Mobile → Platform Mobile. | UI complexity, broad reach |
| Application / Tool | App-Composition | READ: App Composition → Theming. Do NOT load game-specific refs. | Different paradigm than games |
| Romance / Dating Sim | Affection Economy | READ: Romance → Dialogue → UI Rich Text. | High UI/Narrative density |
| Secrets / Easter Eggs | Intentional Obfuscation | READ: Secrets → Persistence. | Community engagement, debug risk |
| Collection Quest | Scavenger Logic | READ: Collections → Marker3D Placement. | Player retention, exploration drive |
| Seasonal Event | Runtime Injection | READ: Easter Theming → Material Swapping. | Fast branding, no asset pollution |
| Souls-like Mortality | Risk-Reward Revival | READ: Revival/Corpse Run → Physics 3D. | High tension, player frustration risk |
| Wave-based Action | Combat Pacing Loop | READ: Waves → Combat. | Escalating tension, encounter design |
| Survival Economy | Harvesting Loop | READ: Harvesting → Inventory. | Resource scarcity, loop persistence |
| Racing / Speedrun | Validation Loop | READ: Time Trials → Input Buffer. | High precision, ghost record drive |
One of the most impactful expert-only decisions. The Godot docs explicitly say "avoid using nodes for everything":
| Type | When to Use | Cost | Expert Use Case |
|---|---|---|---|
Object |
Custom data structures, manual memory management | Lightest. Must call .free() manually. |
Custom spatial hash maps, ECS-like data stores |
RefCounted |
Transient data packets, logic objects that auto-delete | Auto-deleted when no refs remain. | DamageRequest, PathQuery, AbilityEffect — logic packets that don't need the scene tree |
Resource |
Serializable data with Inspector support | Slightly heavier than RefCounted. Handles .tres I/O. |
ItemData, EnemyStats, DialogueLine — any data a designer should edit in Inspector |
Node |
Needs _process/_physics_process, needs to live in the scene tree |
Heaviest — SceneTree overhead per node. | Only for entities that need per-frame updates or spatial transforms |
The expert pattern: Use RefCounted subclasses for all logic packets and data containers. Reserve Node for things that must exist in the spatial tree. This halves scene tree overhead for complex systems.
From empty project to production-ready container.
MANDATORY — READ ENTIRE FILE: Foundations
/features/player/, /features/combat/), not by class type. A player/ folder contains the scene, script, resources, and tests for the player.GlobalSignalBus autoload with < 15 events.untyped_declaration warning in Project Settings → GDScript → Debugging..gitignore, export presets, and input map.Building modular, testable characters.
MANDATORY Chain — READ ALL: Composition → State Machine → CharacterBody2D or Physics 3D → Animation Tree Do NOT load UI, Audio, or Save/Load references for entity work.
InputComponent, never handles input directly. This allows AI/Player swap with zero refactoring.MoveState tells MoveComponent to act, not the other way around.Connecting Combat, Inventory, Stats through Resources.
MANDATORY Chain — READ ALL: Resource Patterns → RPG Stats → Combat → Inventory
ItemData.gd extending Resource. Instantiate it as 100 .tres files instead of 100 scripts.player_health_changed on the Signal Bus.@export Resource variables, or call resource.duplicate() in _ready(). Failure to do this is Bug #1 in Part 8.MANDATORY: Autoload Architecture → Save/Load → Scene Management
.get("key", default_value).MANDATORY: Debugging/Profiling → Performance Optimization
Diagnosis-first approach (NEVER optimize blindly):
_process is being called on hundreds of nodes. Move to single-manager pattern or Server APIs (see Part 6).MultiMeshInstance for repetitive geometry. Batch materials with ORM textures._process is used instead of _physics_process for movement.load(), or NavigationServer recalculation. Use ResourceLoader.load_threaded_request().MANDATORY: Input Handling → Adapt Desktop→Mobile → Platform Mobile Also read: Platform Desktop, Platform Web, Platform Console, Platform VR as needed.
InputManager autoload that translates all input types into normalized actions. NEVER read Input.is_key_pressed() directly — it blocks controller and touch support.MarginContainer with Safe Area logic for notch/cutout devices.AudioServer requires user interaction before first play (browser policy). Handle this with a "Click to Start" screen.MANDATORY: Prerequisites Time Estimate 15-45 minutes depending on use case complexity Steps Common Pitfalls ✓ Do ✗ Don't 💡 Pro Tips ✓ Use when Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement. ✗ Avoid when Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion. jwynia/agent-skills mindrally/skills kostja94/marketing-skills github/awesome-copilot wispbit-ai/skills mrgoonie/claudekit-skills Useful defaults in godot-master — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows. godot-master is among the better-maintained entries we tried; worth keeping pinned for repeat workflows. Useful defaults in godot-master — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows. Registry listing for godot-master matched our evaluation — installs cleanly and behaves as described in the markdown. godot-master has been reliable in day-to-day use. Documentation quality is above average for community skills. godot-master reduced setup friction for our internal harness; good balance of opinion and flexibility. godot-master fits our agent workflows well — practical, well scoped, and easy to wire into existing repos. godot-master has been reliable in day-to-day use. Documentation quality is above average for community skills. Registry listing for godot-master matched our evaluation — installs cleanly and behaves as described in the markdown. godot-master reduced setup friction for our internal harness; good balance of opinion and flexibility. showing 1-10 of 59Implementation Guide
Best Practices
When to Use This
Learning Path
Related Skills
typescript-best-practices
127Backendsame categoryfastapi-python
55Backendsame categorygoogle-search-console
47Backendsame categoryjava-springboot
46Backendsame categorypython-expert-best-practices-code-review
41Backendsame categorybackend-development
20Backendsame categoryReviews
4.7★★★★★59 reviewsPPratham Ware★★★★★Dec 28, 2024SSakura Taylor★★★★★Dec 24, 2024SSofia Kim★★★★★Dec 20, 2024KKaira Khanna★★★★★Dec 12, 2024SSakshi Patil★★★★★Nov 19, 2024LLi Thomas★★★★★Nov 19, 2024NNoah Sanchez★★★★★Nov 15, 2024SSakura Abebe★★★★★Nov 11, 2024RRen Zhang★★★★★Nov 7, 2024SSakura Diallo★★★★★Oct 26, 20241 / 6Discussion
Comments — not star reviews