agentleFS
Sign inStart free
jammyfujammyfu/open-game-skills/skills/disciplines/level-design/SKILL.md

level-design

Skill12 starsChanged 23 days agoMITView on GitHub

Use when rooms, hubs, overworld pockets, dungeons, or set pieces lack readable spatial choices, pacing, gating, landmarks, or measurable traversal structure before art polish.

9 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use game-ai, unreal-enhanced-input and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ukanwatSkill

    game-ai

    Design NPC and enemy decision-making with finite state machines, behavior trees, steering behaviors, and A* pathfinding — engine-neutral algorithms that pair with the detected engine's navigation API. Use when building enemy AI, an FSM or behavior tree, steering/flocking, or pathfinding, or when the user mentions state machine, behavior tree, blackboard, A*, navmesh, seek, or patrol/chase.

    Also in 5 projects that use this

  • MRCalderon3DSkill

    unreal-enhanced-input

    Implement Unreal input with Enhanced Input — Input Actions, Mapping Contexts, triggers/modifiers, and runtime remapping.

    Also in 5 projects that use this

  • ukanwatSkill

    camera-systems

    Build game cameras that feel good — 2D follow with a deadzone, look-ahead, smoothing, and level-bounds clamping; 3D third-person orbit with collision and first-person look; plus multi-target framing and a shake hook. Engine-neutral techniques that pair with the engine's camera node and rigs like Unity Cinemachine or Godot Camera2D/PhantomCamera. Use when the user mentions camera follow, follow camera, deadzone, look-ahead, camera smoothing, camera bounds/ limits, third-person camera, orbit camera, first-person look, Cinemachine, or camera jitter.

    Also in 4 projects that use this

  • +8 more from ukanwat

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Write project metrics before decoration: traversal speeds, jump/climb reach, corridor/door widths, encounter footprint, camera clearance, …

    line 21
  2. Very specific:

    Run representative routes without final art.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Level Design

This skill owns spatial structure, pacing, gating, and navigation intent. level-blockout owns greybox implementation; level-teach owns spatial teaching beats; world-map owns map UI.

Modes

ModeSpatial emphasis
open-airmultiple routes, long sightlines, landmark navigation
room-gateroom sequence and authored gates
hub-spokesafe hub with selectable spokes and returns
linear-setpiececontrolled pacing along a constrained route

Spatial contract

Write project metrics before decoration: traversal speeds, jump/climb reach, corridor/door widths, encounter footprint, camera clearance, sightline targets, checkpoint spacing, and any accessibility constraints that materially shape space.

Gates are explicit data: soft/resource, hard/key-or-ability, optional challenge, narrative/state, or project-specific variants. A gate should communicate why traversal is blocked through space, feedback, UI, or narrative according to the chosen presentation; invisible blockers are allowed only when the project deliberately uses them and validation supports the choice.

Decision density, rest spacing and landmark frequency are measured from the intended experience. Do not turn a heuristic such as “one decision every N seconds” into a universal law.

Acceptance

Run representative routes without final art. Record path choice points, traversal time, gate reasons, dead ends, sightlines and recovery routes. Verify metrics against locomotion/platform-jump and observe players through gameplay-validation. A pretty screenshot or map overlay alone is not level-design evidence.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free