agentleFS
witnesstodarkwitnesstodark/mr-mak-workspace/.agents/skills/game-level-design/SKILL.md

game-level-design

Skill800 starsChanged 23 days agoMITView on GitHub

Turn a game-level brief or existing scene snapshot into a reviewable spatial plan, then apply approved changes with coordinate, navigation and scene checks. Use for layouts, encounter placement and terrain plans.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Check main/alternate routes, chokepoint width, clearances, encounter order and travel distances against actual character sizes and speeds.

    line 33
  2. Distinctive:

    Verify saved terrain dimensions, height/axis conversion, prefab references, colliders, navigable paths, spawn locations and camera bounds …

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Game level design

Establish the play goal, scale, camera, movement/navigation limits and existing visual setup. Inspect the scene and documented mechanics before proposing placements. Reuse approved lighting/material settings when making another level; a new layout does not imply permission to redesign the game's presentation.

Keep source and proposal separate

For an existing level, capture a read-only source snapshot with scene identity, units, origin, axis convention, terrain/navigation data and object IDs. Record source hashes or revisions. For a new level, label the baseline as a proposal; do not describe a generated map as an engine export.

Store edits separately: layer overrides, marker additions/moves/removals and design notes. Keep alternate layouts independent. Regeneration must not silently replace a user's edited draft. On a changed source, preserve a recovery copy and resolve conflicts rather than treating the draft as disposable.

Make the plan useful for decisions

Show terrain, passage, obstacles, cover and objectives as distinct layers. Define brush/cell sizes in world units. Visual ground colour is not necessarily a navigation blocker; tree cover, water and a road may have different rules. Preserve stable marker IDs and distinguish counts, capacity and starting occupants. Unchosen prefabs or mechanics remain explicit design intent.

Check main/alternate routes, chokepoint width, clearances, encounter order and travel distances against actual character sizes and speeds. A 2D simulation can compare strategies only within its documented assumptions. Its result does not prove native navigation, combat behaviour or final balance.

Apply only the approved plan

Export a manifest mapping coordinates, source revision and markers to engine assets. Reject stale/conflicting revisions before applying. Confirm the target scene and which objects are generated; do not overwrite an unrelated authored scene or manual edits as a side effect of a rebuild.

Verify saved terrain dimensions, height/axis conversion, prefab references, colliders, navigable paths, spawn locations and camera bounds in the engine. Traverse representative routes and test the changed encounter flow. Preserve unrelated gameplay values and assets. Deliver the editable plan, applied scene, export manifest, native captures and unresolved choices.

Example request: "Plan a small valley with two routes to the objective, then apply the chosen version." Success includes a reviewable layout, measured route clearance and a verified native path through the saved scene. Dependencies: project design rules; an editor bridge/CLI or engine access for scene work.

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.