Skip to content
SkillModel-led2,578 tokens in use

procedural-gen

Builds dungeon, cave, terrain and loot generators in Python that reproduce from a seed, and proves them with a seed sweep for connectivity, determinism and variety.

9,682 stars on the repository Apache License 2.0gamedev-skills/awesome-gamedev-agent-skills · skills/disciplines/procedural-gen
npx skills add gamedev-skills/awesome-gamedev-agent-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing procedural-gen costs

92tokens idle
2,578tokens in use
6,191tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter8/15
  • Structure25/25
  • Examples12/15
  • Output15/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 129

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity92
  • Maintenance96
  • Community60
  • Maturity24
  • Momentum40

Procedural Generation is an engine-neutral skill for generating levels, terrain and drops from rules and a seed. It covers seeded RNG, dungeon layouts, caves, wave function collapse, noise terrain and weighted loot tables, with Godot and Unity mappings.

The central rule is determinism: one seed gives one world, so bugs replay and players can share seeds. The agent generates into simple data structures, validates every result and runs a seed sweep before asking you to play named seeds.

What You Get

  • A seeded RNG setup with child streams per system, so one new roll does not reshuffle a layout
  • A small PRNG whose sequence you own, with pinned test outputs, for seeds that must survive updates
  • A weighted drop table and notes on bags and pity timers
  • A seed sweep that reports failures, distinct maps and floor ratio over many seeds
  • Reference notes on rooms and corridors, BSP, drunkard’s walk, cellular caves and WFC
  • Reference notes on noise terrain, biomes, island shaping and scatter placement

Common Use Cases

  • A dungeon generator whose rooms must all be reachable from the spawn
  • Noise terrain and biomes that do not line up in bands
  • Daily challenges or shareable world seeds that must replay the same map
  • Loot tables with rarities and guaranteed drop rates

What Makes It Unique

It pairs each algorithm with a validation step, so generation code always comes with a check. The seed sweep tests determinism, reachability and distribution across hundreds of seeds, and a second process run catches hash-order drift. It also warns that Python, .NET and Godot do not promise stable sequences across versions, and shows how to ship your own PRNG.

Under The Hood

The skill is a SKILL.md with two reference files, one on dungeon generation and one on noise. The agent writes Python generator and test code in your project and runs it, including the seed sweep in two separate processes to compare digests. For engine-side generators it follows the headless test approach of the Godot testing skill. It does not fetch web pages or call outside services.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers