Godot Game Loop Harvest logo

Godot Game Loop Harvest

Community
thedivergentai
godot-game-loop-harvest

Data-driven resource harvesting (mining, logging, foraging) for Godot 4: apply_hit tool/tier validation via HarvestToolData enums, HarvestResourceData yields, harvestable_node shake/deplete, respawn_manager world persistence, UNIX offline progress, autosave, and noise vein proc-gen. Trigger keywords: apply_hit, HarvestResourceData, HarvestToolData, offline UNIX, respawn_manager, tool tier, harvestable_node, FastNoiseLite veins.

Overview

Publisherthedivergentai
RepositoryGD-Agentic-Skills
Skill namegodot-game-loop-harvest
Stars
727
Forks
43
Bundled files
9
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.

  • 9 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 Game Loop Harvest 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-game-loop-harvest .claude/skills/godot-game-loop-harvest
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Godot Game Loop Harvest 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 Game Loop Harvest 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 Game Loop Harvest 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.

Script Catalog (MANDATORY by path)

PathMANDATORY reads
Hit / gatherharvestable_node.gd, resource_data.gd, harvest_tool_data.gd
Offline / autosaveharvest_loop_patterns.gd, harvest_autosave_manager.gd, harvest_inventory_manager.gd
Vein / respawn / worldharvest_respawn_manager.gd + FastNoiseLite vein notes below

Setup (short)

  1. Author HarvestResourceData / HarvestToolData .tres (tool enum + tier, yield range, optional drop scene).
  2. Attach harvestable_node.gd to StaticBody3D; assign data + mesh_to_shake; keep interaction on Layer 1.
  3. Autoload harvest_respawn_manager.gd as HarvestRespawnManager when world persistence is required.

Hit path

Raycast/interact → apply_hit(tool_data: HarvestToolData):

gdscript
if collider is HarvestableNode:
    collider.apply_hit(player_tool)
SignalPayloadWire to
harvested(data, amount)Inventory / harvest_inventory_manager
took_damage(curr, max)HUD bar / popup pool
interaction_failed(reason: StringName)"wrong_tool" / "low_tier" feedback

NEVER Do

  • NEVER use float for accumulated harvest counts — use int.
  • NEVER gather rates in _process without delta — framerate-scales economy.
  • NEVER trust OS.get_ticks_msec() for offline progress — use Time.get_unix_time_from_system().
  • NEVER check tool type via free-form strings — use HarvestToolData.ToolType / StringName enums (see scripts).
  • NEVER mutate shared Resource templatesduplicate(true) before runtime durability/health mutation.
  • NEVER queue_free() before VFX/SFX finish — hide mesh, swap collision layer, free after juice.
  • NEVER skip saving UNIX timestamp on exit — offline gains depend on it.
  • NEVER couple harvest logic to UI counters — signals only.
  • NEVER scale collision shapes non-uniformly — edit shape resource sizes.

Vein proc-gen (noise)

Use FastNoiseLite thresholds for organic clusters; spawn HarvestableNode instances where noise.get_noise_2dv(pos) > threshold. Persist depleted IDs via respawn manager — do not re-roll veins every load without a seed.

Tool durability

Keep durability on HarvestToolData (Resource), not the player node. Emit durability/break signals from the tool Resource after successful hits.

MANDATORY for offline UNIX math, worker-thread batching, popup pools, and vein proc-gen depth: harvest-elite-patterns.md. Do NOT Load when hit path + respawn manager suffice.

Reference

Progressive disclosure: Skim Official Documentation only for the APIs you are implementing (Resources, StaticBody3D hits, signals, timers, save/offline time). Open Related Skills when wiring inventory, autoloads, raycasts, or economy balance—do not preload the whole lattice.

Official Documentation

  • Resources — Author HarvestResourceData / HarvestToolData as shareable .tres assets so designers tune health, yield ranges, and tool gates without editing harvest scripts.
  • Resource — Call duplicate(true) before mutating runtime harvest/tool state so one node’s depletion or durability cannot rewrite the shared template Resource.
  • GDScript exports@export / @export_group power Inspector-authored tool tiers, yield ranges, respawn times, and drop scenes on harvest data Resources.
  • Using signals — Emit harvested, took_damage, and interaction_failed so inventory, HUD bars, and feedback UI subscribe without coupling to HarvestableNode internals.
  • StaticBody3D — World harvestables are static colliders players query/hit; keep them on an interaction layer and move to an inactive layer while depleted.
  • Collision shapes (3D) — Size shape resources directly; non-uniform scale on collision shapes breaks hit tests for pickaxes/axes against trees and ore nodes.
  • Idle and Physics Processing — Multiply continuous gather rates by delta (prefer _physics_process for fixed-step economy ticks) so harvest speed is not framerate-dependent.
  • Time — Persist Time.get_unix_time_from_system() for offline gains; do not use OS.get_ticks_msec() / uptime for real-world absence math.
  • Saving games — Persist inventory counts, depleted-node IDs, and absolute respawn/offline timestamps with the rest of progression data.
  • FileAccess — Interval autosave writes JSON (or binary) under user:// via FileAccess.open so harvest progress survives crashes between manual saves.
  • Tween — Hit “juice” shakes use short property tweens on the mesh child without allocating disposable animation players per strike.
  • Singletons (Autoload) — Register HarvestRespawnManager as an Autoload so scattered harvestables resolve /root/HarvestRespawnManager for world-scale depletion persistence.

Related Skills

Prerequisites
  • godot-resource-data-patterns — Harvest yields, tool stats, and drop scenes are Resource-first; establish composition/duplicate rules before baking economy numbers into nodes.
  • godot-signal-architectureharvested / inventory_updated ownership and safe connects keep gather nodes decoupled from HUD and inventory hubs.
  • godot-physics-3dStaticBody3D layers/masks and shape setup for interactable world props are prerequisites to reliable hit validation.
  • godot-gdscript-mastery — Typed Resources, await on create_timer, and Mutex/WorkerThreadPool patterns assume solid GDScript fundamentals.
Complements
  • godot-inventory-system — Connect harvested into a real inventory/stacking pipeline instead of leaving counts in a harvest-only dictionary.
  • godot-save-load-systems — Round-trip warehouse totals, tool durability, and depleted-node timers through the project save schema beyond interval JSON dumps.
  • godot-autoload-architecture — Respawn and inventory managers belong in a disciplined Autoload graph with clear init order and signal-bus boundaries.
  • godot-raycasting-queries — Player gather input typically raycasts or shapecasts to the harvestable collider before calling apply_hit(tool_data).
  • godot-tweening — Expand hit shakes into polish tweens (squash, flash, camera punch) without cutting VFX short via early queue_free().
  • godot-economy-system — Wire harvest yields into sinks, crafting costs, and vendor loops so gathering feeds a coherent economy.
Downstream / consumers
  • godot-monte-carlo-balancer — After yields, respawn times, and tool tiers are tunable Resources, Monte Carlo sims validate gather pacing and sink pressure before shipping curves.
  • godot-genre-survival — Survival loops compose harvesting with hunger, crafting, and world threat systems on top of this gather core.
  • godot-game-loop-collection — Collection/scavenger objectives often consume the same harvest/inventory signals for “gather N of X” quests.
  • godot-procedural-generation — Noise-driven resource veins and world placement build on harvest node data once the interaction loop is solid.
Master
  • godot-master — Library router and mirrored module entry; use when discovering peer skills or syncing shared script mirrors after Domain Skill edits.

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 Game Loop Harvest AI skill do?

Data-driven resource harvesting (mining, logging, foraging) for Godot 4: apply_hit tool/tier validation via HarvestToolData enums, HarvestResourceData yields, harvestable_node shake/deplete, respawn_manager world persistence, UNIX offline progress, autosave, and noise vein proc-gen. Trigger keywords: apply_hit, HarvestResourceData, HarvestToolData, offline UNIX, respawn_manager, tool tier, harvestable_node, FastNoiseLite veins.

Why use Godot Game Loop Harvest on TypingMind?

Because you install it once and use it with any model. Godot Game Loop Harvest 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 Game Loop Harvest in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/thedivergentai/GD-Agentic-Skills/tree/main/skills/godot-game-loop-harvest. 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 Game Loop Harvest?

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 Game Loop Harvest?

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

Is the Godot Game Loop Harvest 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 👇