agentleFS
TabooHarmonyTabooHarmony/roblox-brain/skills/gameplay/roblox-building/SKILL.md

roblox-building

Skill150 starsChanged 52 days agoMITView on GitHub

Use when building or editing geometry, maps, props, or generated assets with MCP or standalone Luau.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Search project assets and Toolbox first.

    line 34
  2. Distinctive:

    Check mesh bounds, collision, PBR, and quality levels.

    line 37
  3. Distinctive:

    Use permitted images; wait for jobs to finish.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Roblox Building

When to Load

Load for geometry, props, maps, and spatial onboarding via MCP or Luau.

Quick Reference

MCP Build Mode

1-2. Inspect Studio/Workspace/assets; name root, origin, dimensions, assets. 3-4. Build in phases with readback; verify tree, view, traversal.

Asset Choice

  • Search project assets and Toolbox first; check type, creator, price, scripts, fit.
  • Paid/cross-owner insertion: disclose creator, ID, price, rights first. Inspect scripts/dependencies; remove unneeded code. See roblox-security.
  • MCP: generate_procedural_model, generate_mesh, generate_material.
  • Check mesh bounds, collision, PBR, and quality levels.
  • Use permitted images; wait for jobs to finish.
  • EditableImage/EditableMesh: permission + memory limits.
  • Native Parts/CSG when reuse/generation is unsuitable.
  • Asset privacy: new accounts/groups create Images/Decals/Meshes Restricted — blank texture/invisible mesh usually means a missing grant, not corruption. Read the Output error; grant the experience in Creator Dashboard. See roblox-studio-mcp.

Player Scale

Player ~5 studs | Door 4w×7h | Ceiling 10-14 | Counter 3.5-4 | Seat 1.5 | Path 6+

Spatial Rules

  • Name dimensions; offset sub-parts from anchor CFrames, never guessed world coordinates.
  • Snap to 0.125/0.25/0.5 studs. Build complex CSG near origin, then PivotTo the destination.
  • Set anchoring, collision, shadows, color, material explicitly.

Acceptance

Prop: named model, pivot, scale, bounds, materials, collision, anchoring, no loose parts, provenance. Map: root/origin, zones, landmarks, spawns/return paths, traversal, bounds excluding Baseplate/Terrain/SpawnLocation. Evidence: readback, view when supported, playtest results.

Anti-Patterns

Guessing coordinates | unanchored/duplicate parts | hardcoded world positions | silent CSG failure | oversized batches | claims without readback

Details: references/full.md (maps, validation, assets).

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.