Godot Genre Tower Defense logo

Godot Genre Tower Defense

Community
thedivergentai
godot-genre-tower-defense

Expert blueprint for tower defense games (Bloons TD, Kingdom Rush, Fieldrunners) covering wave management, tower targeting logic, path algorithms, economy balance, and mazing mechanics. Use when building TD, lane defense, or tower placement strategy games. Keywords tower defense, wave spawner, pathfinding, targeting priority, mazing, NavigationServer baking.

Overview

Publisherthedivergentai
RepositoryGD-Agentic-Skills
Skill namegodot-genre-tower-defense
Stars
727
Forks
43
Bundled files
15
LicenseLGPL-3.0
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.

  • 15 bundled files

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

  • Open source

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

Installation

Install the Godot Genre Tower Defense 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/thedivergentai/GD-Agentic-Skills.git /tmp/GD-Agentic-Skills
mkdir -p .claude/skills
cp -r /tmp/GD-Agentic-Skills/skills/godot-genre-tower-defense .claude/skills/godot-genre-tower-defense
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Godot Genre Tower Defense 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 Godot Genre Tower Defense 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 Godot Genre Tower Defense 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.

Core Loop

  1. Prepare: Build/upgrade towers with available currency
  2. Wave: Enemies spawn and traverse path toward goal
  3. Defend: Towers auto-target and damage enemies
  4. Reward: Kills grant currency
  5. Escalate: Waves increase in difficulty/complexity

NEVER Do (Expert Anti-Patterns)

Design & Strategy

  • NEVER make all towers have the same niche; strictly ensure distinct specialties: Aura Slow, Armor Piercing, Anti-Air, Burst Sniper, and Splash Damage.
  • NEVER allow a "Death Spiral" with no exit; strictly provide small comeback bonuses or interest on saved gold to prevent early inevitable failure.
  • NEVER make early waves feel like busywork; strictly provide an "Early Call" bonus to skip wait times and accelerate engagement.
  • NEVER trust client-side economy updates; strictly require the authoritative server to validate currency addition and tower purchases in co-op.

Pathing & Placement

  • NEVER allow the player to "Seal" the exit in mazing games; strictly validate path existence with NavigationServer2D.map_get_path() before finalizing tower placement.
  • NEVER use synchronous bake_navigation_polygon() for mazing; strictly offload to a worker thread to prevent 100ms+ frame hitches during placement.
  • NEVER use global coordinates for grid logic; strictly convert to Vector2i/Vector3i to ensure pixel-perfect tower alignment.

Performance & Systems

  • NEVER call get_overlapping_bodies() every frame; strictly use signals (body_entered/body_exited) to maintain a local target cache.
  • NEVER use _process() for projectile movement if count > 500; strictly use the PhysicsServer2D/3D directly for high-performance bullet-hell tiers.
  • NEVER spawn hundreds of projectiles as full Nodes; strictly use Object Pooling to reuse resources and avoid garbage collection stutters.
  • NEVER use standard Strings for priorities; strictly use StringName (&"first", &"strongest") for O(1) hash comparisons in targeting loops.
  • NEVER ignore the progress property on PathFollow nodes; strictly use it as the O(1) way to identify the target closest to exit.
  • NEVER process tower search logic every frame; strictly throttle ACQUIRE searches (e.g., every 5-10 frames) to save significant CPU cycles.
  • NEVER scale Tower CollisionShape non-uniformly; strictly adjust the radius property of the Shape resource to preserve collision math.
  • NEVER delete enemies immediately on death; strictly use set_deferred("disabled", true) and wait one frame to prevent physics server crashes.
  • NEVER hardcode waves in huge switch statements; strictly use Custom Resources (.tres) for clean balancing and sequence editing.

🛠 Expert Components (scripts/)

Original Expert Patterns

  • wave_manager.gd - Professional wave orchestrator with Resource-based enemy composition and cleanup.
  • tower.gd - Base turret class with FSM state management and firing logic.
  • tower_targeting_system.gd - Autonomous priority logic (First/Last/Strongest/Weakest) for efficient targeting.

Modular Components

Decision Trees (MANDATORY script reads)

Path style

StyleApproachScripts / APIs
Fixed lanesPath2D / PathFollow2D progresswave_manager.gd, wave_resource_spawner.gd
MazingSeal-check before placeNavigationServer2D.map_get_path / AStarGrid2D (NEVER)
Organic curvesBezier PathFollow progressPrefer PathFollow over per-frame seek

Targeting priority

PrioritySort keyMANDATORY
FIRSTHighest progress (closest to exit)tower_targeting_system.gd
LASTLowest progresssame — LAST implemented
STRONGEST / WEAKESThealth desc / ascsame — WEAKEST implemented

Use signal-cached range Area enter/exit + frame-sliced acquire (acquire_interval_frames). Never get_overlapping_bodies() every frame.

Economy

ConcernRuleScript
Wave compositionResource .tres waveswave_manager.gd
Co-op purchasesServer validates goldtower_defense_patterns.gd
ComebackInterest / early-call bonusDesign-level — not tower FSM

PhysicsServer Projectile Golden Path

When count > ~500:

  1. MANDATORY tower_defense_patterns.gd spawn_fast_bullet (PhysicsServer3D kinematic RIDs).
  2. Pool RIDs; AoE via intersect_shape; defer collision disable on death.
  3. Modest counts: homing_projectile_3d.gd / pooled Nodes OK.

Tower FSM

MANDATORY: tower.gd for idle → acquire → windup → fire. Targeting stays in tower_targeting_system.gd.

Deep recipes (on demand)

TopicReference / script
Waves / towers / pathsarchitecture-overview.md
Projectile lead & targetingkey-mechanics.md
Maze validation & burst searchelite-technical-patterns.md + grid_path_validator.gd

Reference

Progressive disclosure: open Official Documentation links only when researching a specific API; load Related Skills when routing to a peer domain — do not preload the whole lattice.

Official Documentation

  • Navigation introduction (2D) — NavigationRegion2D baking and map queries for mazing TD path validity.
  • Using NavigationAgents — agent path following and avoidance when towers reshape walkable space.
  • NavigationServer2Dmap_get_path seal checks before committing tower placement.
  • AStarGrid2D — integer-grid path probes that simulate build cells without a full nav bake.
  • PathFollow2Dprogress / progress_ratio for fixed-lane enemies and First/Last targeting.
  • PathFollow3D — 3D track followers used by wave spawners and homing aim references.
  • Using Area2D — signal-driven range caches (body_entered / body_exited) instead of per-frame overlap polls.
  • Physics introduction — layers/masks so tower ranges hit enemies, not other towers or walls.
  • Using servers — PhysicsServer bodies for high-count projectiles without Node overhead.
  • Resources — WaveDefinition .tres data instead of hard-coded spawn switches.
  • Using multiple threads — WorkerThreadPool / Thread patterns for async navigation rebakes during placement.
  • Using TileMaps — TileMapLayer grids for build cells, paths, and placement snapping.

Related Skills

Prerequisites
Complements
Downstream / consumers
  • godot-genre-rts — base defense and unit-placement loops that reuse path validation and economy pressure.
  • godot-multiplayer-networking — authoritative purchase validation and unreliable minion sync for co-op TD.
Master
  • godot-master — library router and mirrored module entry for cross-skill discovery.

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 Godot Genre Tower Defense AI skill do?

Expert blueprint for tower defense games (Bloons TD, Kingdom Rush, Fieldrunners) covering wave management, tower targeting logic, path algorithms, economy balance, and mazing mechanics. Use when building TD, lane defense, or tower placement strategy games. Keywords tower defense, wave spawner, pathfinding, targeting priority, mazing, NavigationServer baking.

Why use Godot Genre Tower Defense on TypingMind?

Because you install it once and use it with any model. Godot Genre Tower Defense 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 Godot Genre Tower Defense in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/thedivergentai/GD-Agentic-Skills/tree/main/skills/godot-genre-tower-defense. 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 Godot Genre Tower Defense?

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 Godot Genre Tower Defense?

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

Is the Godot Genre Tower Defense AI skill free?

Yes. It is published on GitHub by thedivergentai under the LGPL-3.0 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 👇