Agent skill

Procedural Generation

by jame581 in jame581/GodotPrompter

A skill your agent uses when implementing procedural generation — noise-based terrain, BSP dungeons, cellular automata caves, wave function collapse, and seeded randomness in Godot 4.3+

MITAuto-check passedGame Development

Install Procedural Generation

skills CLI
$ npx skills add jame581/GodotPrompter --skill procedural-generation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jame581/GodotPrompter procedural-generation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jame581/GodotPrompter.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/procedural-generation .claude/skills/procedural-generation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
procedural-generation
GitHub stars
799
Token cost
~1.2k tokens
SKILL.md length
483 words
Files
5 (incl. references)
Skills in repo
58
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when implementing procedural generation — noise-based terrain, BSP dungeons, cellular automata caves, wave function collapse, and seeded randomness in Godot 4.3+

  • Works in 7 steps: Seeded Randomness → Noise-Based Generation (FastNoiseLite) → BSP Dungeon Generation → …
  • Implementing procedural generation — noise-based terrain
  • SKILL.md covers 1. Seeded Randomness, 2. Noise-Based Generation…, 3. BSP Dungeon Generation and 4. Cellular Automata (Cave…, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Procedural Generation is an agent skill from jame581/GodotPrompter. Use when implementing procedural generation — noise-based terrain, BSP dungeons, cellular automata caves, wave function collapse, and seeded randomness in Godot 4.3+

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/bsp-dungeons.md`, `references/cellular-automata.md` and `references/noise-generation.md`).

It sits in Game Development, covering Game development. It works with Godot and C#. The repository describes itself as: Agentic skills framework for Godot 4.x. Domain-specific skills for AI coding agents (Claude Code, Copilot, Antigravity, Cursor). The licence is MIT.

When your agent uses it

  • Implementing procedural generation — noise-based terrain
  • Cellular automata caves
  • Wave function collapse
  • Seeded randomness in Godot 4.3+

Example prompts

  • “/procedural-generation”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Seeded Randomness
  2. Noise-Based Generation (FastNoiseLite)
  3. BSP Dungeon Generation
  4. Cellular Automata (Cave Generation)
  5. Wave Function Collapse (WFC)
  6. Common Pitfalls
  7. Implementation Checklist

What it can do on your machine

Read from SKILL.md and the folder at commit 1e7d79d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are gdscript and csharp).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Procedural Generation loads about 1.2k tokens when it runs, and up to ~6.9k if it reads all its reference files. Until then it costs about 47 tokens; SKILL.md has 483 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jame581/GodotPrompter at commit 1e7d79d, republished under its MIT licence (© jame581). 483 words, ~1,240 tokens.

Download SKILL.mdSave it as .claude/skills/procedural-generation/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
procedural-generation
description
Use when implementing procedural generation — noise-based terrain, BSP dungeons, cellular automata caves, wave function collapse, and seeded randomness in Godot 4.3+

Procedural Generation in Godot 4.3+

All examples target Godot 4.3+ with no deprecated APIs. GDScript is shown first, then C#.

Related skills: 2d-essentials for TileMapLayer usage, 3d-essentials for 3D terrain meshes, math-essentials for vectors and transforms, godot-optimization for chunk loading and performance.


1. Seeded Randomness

Always use seeds for reproducible generation. This enables shareable seeds, replay, and deterministic testing.

GDScript
gdscript
# RandomNumberGenerator — per-instance, seedable
var rng := RandomNumberGenerator.new()

func generate_level(level_seed: int) -> void:
    rng.seed = level_seed

    var width: int = rng.randi_range(20, 40)
    var height: int = rng.randi_range(15, 30)
    var enemy_count: int = rng.randi_range(3, 8)
    var treasure_chance: float = rng.randf_range(0.05, 0.15)

# AVOID: Global randf()/randi() — not reproducible across calls
# USE: rng.randf(), rng.randi(), rng.randf_range(), rng.randi_range()
C#
csharp
private RandomNumberGenerator _rng = new();

public void GenerateLevel(ulong levelSeed)
{
    _rng.Seed = levelSeed;

    int width = _rng.RandiRange(20, 40);
    int height = _rng.RandiRange(15, 30);
    int enemyCount = _rng.RandiRange(3, 8);
    float treasureChance = _rng.RandfRange(0.05f, 0.15f);
}

Tip: Generate a seed from a string for shareable level codes: var seed: int = "MyLevel".hash()


2. Noise-Based Generation (FastNoiseLite)

FastNoiseLite for height maps, biome distribution, 2D terrain. Key params: noise_type (Perlin / Simplex / Cellular / Value), frequency (lower = larger features), seed. For terrain, sample noise at each tile coord, threshold the value to pick a tile.

See references/noise-generation.md for the basic noise-map recipe, noise-type reference table, and 2D terrain + TileMapLayer walkthrough.


3. BSP Dungeon Generation

Binary Space Partitioning recursively splits a rectangle into smaller rectangles, carves a room inside each leaf, connects siblings with corridors. Produces grid-aligned room-based dungeons (think roguelike).

See references/bsp-dungeons.md for the full recursive partition + room placement + corridor connection algorithm in GDScript + C#.


4. Cellular Automata (Cave Generation)

Fill a grid with random walls/floors at ~45% density, then iterate "a cell becomes a wall if ≥ 5 of 8 neighbors are walls" 4-5 times. The result is organic cave shapes — no straight corridors.

See references/cellular-automata.md for the full GDScript + C# implementation with TileMapLayer integration.


5. Wave Function Collapse (WFC)

WFC is a constraint solver: given a tile set with adjacency rules, pick the lowest-entropy cell, collapse it to a valid tile, propagate constraints, repeat. Produces tile-rule-respecting output but is non-trivial to implement.

See references/wave-function-collapse.md for concept overview and a simplified GDScript + C# implementation.


Show full SKILL.md (209 more words)Show less

6. Common Pitfalls

SymptomCauseFix
Same level every timeNot seeding the RNGSet rng.seed before generation
Different results on different platformsUsing global randf() / randi()Use a dedicated RandomNumberGenerator instance
Noise looks blockyFrequency too highLower frequency (try 0.01–0.05)
Caves are all wall or all floorfill_chance too extreme or too few iterationsUse fill_chance 0.40–0.50 and 4–6 iterations
BSP rooms overlapSplit position too close to edgeEnsure min_room_size buffer in split calculation
WFC contradiction (no valid tile)Adjacency rules too restrictiveAdd more allowed neighbors or implement backtracking
Generation takes too longProcessing entire map in one frameUse await get_tree().process_frame to spread across frames, or use a thread

7. Implementation Checklist

  • All generation uses a seedable RandomNumberGenerator, never global randf()/randi()
  • Seeds are stored with save data so levels can be reproduced
  • FastNoiseLite frequency and octaves are tuned for the game's tile/world scale
  • Large generation is spread across frames or run on a thread to avoid freezing
  • Generated TileMapLayer content uses terrain autotiling when possible (not hardcoded tile coords)
  • BSP dungeons verify all rooms are connected before finalizing
  • Cave generation runs a flood-fill to ensure reachability between key points
  • Player spawn point is validated to be on a floor tile, not inside a wall

© jame581, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/procedural-generation of jame581/GodotPrompter.

  • SKILL.md
  • references/bsp-dungeons.md
  • references/cellular-automata.md
  • references/noise-generation.md
  • references/wave-function-collapse.md

Open the folder on GitHubat commit 1e7d79d

Compare with similar skills

Procedural Generation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Procedural Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Procedural Generation this skilljame581/GodotPrompter799—~1.2kAutomated safety check: PassMIT
Godot Admob App Openpoingstudios/godot-admob-plugin632—~1kAutomated safety check: PassMIT
Godot Admob Bannerpoingstudios/godot-admob-plugin632—~718Automated safety check: PassMIT
Godot Admob Get Startedpoingstudios/godot-admob-plugin632—~1kAutomated safety check: PassMIT
Godot Admob Interstitialpoingstudios/godot-admob-plugin632—~1.1kAutomated safety check: PassMIT
Godot Admob Native Overlaypoingstudios/godot-admob-plugin632—~1kAutomated safety check: PassMIT

Similar skills

  • Godot Admob App Open

    poingstudios/godot-admob-plugin

    Provides instructions to implement, load, show, and destroy App Open ads (shown on application startup or app resume) in GDScript and C.

    632 GitHub stars~1k tokensUpdated 8 days ago
    Game DevelopmentAuto-check passed
  • Godot Admob Banner

    poingstudios/godot-admob-plugin

    Provides instructions to implement, load, and destroy banner ads (AdView) using custom or adaptive sizes in GDScript and C.

    632 GitHub stars~718 tokensUpdated 8 days ago
    Game DevelopmentAuto-check passed
  • Godot Admob Get Started

    poingstudios/godot-admob-plugin

    Provides instructions to initialize the Godot AdMob SDK and configure user consent (UMP Flow) in GDScript and C.

    632 GitHub stars~1k tokensUpdated 8 days ago
    Game DevelopmentAuto-check passed
  • Godot Admob Interstitial

    poingstudios/godot-admob-plugin

    Provides instructions to implement, load, show, and destroy interstitial ads (full-screen image/text ads) in GDScript and C.

    632 GitHub stars~1.1k tokensUpdated 8 days ago
    Game DevelopmentAuto-check passed
  • Godot Admob Native Overlay

    poingstudios/godot-admob-plugin

    Provides instructions to implement, load, show, and destroy Native Overlay ads (customized/native-looking Control node template overlays) in GDScript and C.

    632 GitHub stars~1k tokensUpdated 8 days ago
    Game DevelopmentAuto-check passed
  • Apply the Stage Tamagotchi Godot C development method and code style when working in apps/stage-tamagotchi-kirie or its migration predecessor, engines/stage-tamagotchi-godot.

    50k GitHub stars~677 tokensUpdated today
    Game DevelopmentAuto-check passed

More from jame581/GodotPrompter

All 58 skills in this repo
  • Godot 2D Essentials

    jame581/GodotPrompter

    Covers Godot 4.3+ 2D systems with GDScript and C# examples: canvas layers, draw order, TileMaps, parallax, lights and shadows, particles and custom drawing.

    799 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Godot 3D Essentials

    jame581/GodotPrompter

    Covers Godot 4.3+ 3D systems such as materials, lighting, shadows, environment, global illumination, fog, LOD, occlusion culling and decals, with GDScript first and C# second.

    799 GitHub stars~3.7k tokensUpdated today
    Auto-check passed
  • Godot Ability System

    jame581/GodotPrompter

    Builds a data-driven ability system in Godot 4 from Resources and a component node, with cooldowns, buffs, stat modifiers, gameplay tags and HUD binding.

    799 GitHub stars~3k tokensUpdated today
    Auto-check passed
  • Godot Addon Development

    jame581/GodotPrompter

    Covers Godot 4.3+ editor plugins: plugin folders, @tool scripts, the EditorPlugin lifecycle, custom inspectors, dock panels and gizmos, in GDScript and C#.

    799 GitHub stars~3.3k tokensUpdated today
    Auto-check passed
  • Godot AI Navigation

    jame581/GodotPrompter

    Covers pathfinding and enemy movement in Godot 4.3 and later: navigation regions, NavigationAgent nodes, steering, behavior trees and patrol routes.

    799 GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • Godot Animation System

    jame581/GodotPrompter

    Covers animation in Godot 4.3 and later: AnimationPlayer basics, AnimationTree blend trees and state machines, sprite animation, skeleton IK and code-driven motion.

    799 GitHub stars~3.8k tokensUpdated today
    Auto-check passed

Works with

Questions about Procedural Generation

What does Procedural Generation do?

A skill your agent uses when implementing procedural generation — noise-based terrain, BSP dungeons, cellular automata caves, wave function collapse, and seeded randomness in Godot 4.3+. Procedural Generation is an agent skill from jame581/GodotPrompter.

When should I use Procedural Generation?

Procedural Generation fits situations like: implementing procedural generation — noise-based terrain; cellular automata caves; wave function collapse; seeded randomness in Godot 4.3+.

How do I install Procedural Generation in Claude Code?

Run `npx skills add jame581/GodotPrompter --skill procedural-generation -a claude-code`. Or copy the skill folder (skills/procedural-generation in jame581/GodotPrompter) into .claude/skills/procedural-generation in your project. Claude Code loads it when a task matches its description.

How do I install Procedural Generation in Codex?

Run `npx skills add jame581/GodotPrompter --skill procedural-generation -a codex`. Or copy the skill folder (skills/procedural-generation in jame581/GodotPrompter) into .agents/skills/procedural-generation in your project. Codex loads it when a task matches its description.

Can I use Procedural Generation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jame581/GodotPrompter --skill procedural-generation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/procedural-generation, .gemini/skills/procedural-generation, .github/skills/procedural-generation and .opencode/skills/procedural-generation in your project.

What does Procedural Generation need to run?

SKILL.md names no scripts, command-line tools or credentials: Procedural Generation is instructions for the agent only.

Does Procedural Generation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Procedural Generation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Procedural Generation use?

Procedural Generation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Procedural Generation use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 5.6k tokens, read only when the agent opens those files.

What are the alternatives to Procedural Generation?

Skills that share tags, products or a category with Procedural Generation: Godot Admob App Open (poingstudios/godot-admob-plugin, 632 stars), Godot Admob Banner (poingstudios/godot-admob-plugin, 632 stars), Godot Admob Get Started (poingstudios/godot-admob-plugin, 632 stars) and Godot Admob Interstitial (poingstudios/godot-admob-plugin, 632 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Procedural Generation?

jame581 (a GitHub user) maintains it in jame581/GodotPrompter, which has 799 GitHub stars. The repository holds 58 skills in this directory. The repository was last updated on October 8, 2026.

Source: jame581/GodotPrompter on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.