agentleFS
SyphoDev-ytSyphoDev-yt/roblox-ai-skills/skills/roblox-3d-model/SKILL.md

roblox-3d-model

Skill128 starsChanged 26 days agoLicence not identifiedView on GitHub

Generate game-ready 3D models for Roblox from text prompts, headlessly and end to end, one asset or a whole batch - text to a VERIFIED 2D concept image, image to a high-poly mesh with Hi3DGen (a HuggingFace Space, one at a time; Kaggle is OFF, see the notice at the top), then headless Blender weld + decimate + UV + normal bake to a Roblox-legal MeshPart. GEOMETRY AND COLOUR BOTH WORK as of 2026-08-26 - colour is PAINTED procedurally into the UV atlas from a small JSON spec of stamps (paint_texture.py), which is exact and has no camera to align; the older concept-projection route still exists but smears and is only for assets that need the concept's actual markings. Assets go into Studio either with NO UPLOAD via AssetService EditableMesh/EditableImage (session-local, no credentials) or PERMANENTLY via a free Open Cloud upload as Model + Image (never Decal). batch.py chains the whole set: concepts, sheet, meshes, orient, paint, publish, studio - proven end to end. Use this whenever the user wants a Roblox mesh, prop, weapon, animal, crate, vehicle or any MeshPart generated rather than modelled by hand, wants a set of models made, wants an image turned into a Roblox model, asks about mesh triangle budgets, decimation, UV unwrapping or normal baking, or hits an asset upload that fails looking like a permissions error. Also trigger when a generated mesh is too heavy for Roblox, has no UVs, looks smooth and detail-less after being reduced, or when GPU quota is the thing blocking a batch of 3D generations.

  • Reads credentials
  • Installs packages

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “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.

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.