generate-asset
Skill9 starsChanged 7 months agoMITView on GitHub
Generate a 3D asset for Roblox using Blender MCP. Creates models from text descriptions via AI (Hyper3D/Hunyuan3D) or downloads from PolyHaven/Sketchfab, optimizes for Roblox constraints, and exports FBX.
In this repository51 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- asset-auditSkill
- asset-from-imageSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- changelogSkill
- code-reviewSkill
- datastore-reviewSkill
- design-reviewSkill
- design-systemSkill
- doctorSkill
- economy-auditSkill
- estimateSkill
- exploit-checkSkill
- gate-checkSkill
- gddSkill
- hotfixSkill
- launch-checklistSkill
- luau-lintSkill
- map-systemsSkill
- milestone-reviewSkill
- monetization-modelSkill
- onboardSkill
- patch-notesSkill
- perf-profileSkill
- project-stage-detectSkill
- prototypeSkill
- publish-reviewSkill
- release-checklistSkill
- remotes-auditSkill
- retention-analysisSkill
- retrospectiveSkill
- reverse-documentSkill
- scope-checkSkill
- sprint-planSkill
- startSkill
- studio-inspectSkill
- studio-screenshotSkill
- studio-testSkill
- team-combatSkill
- team-economySkill
- team-polishSkill
- team-releaseSkill
- team-uiSkill
- tech-debtSkill
- wiki-ingestSkill
- wiki-lintSkill
- wiki-querySkill
- wiki-seedSkill
- wiki-updateSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
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
- Very specific: line 21
From reference image: use /asset-from-image instead
- Distinctive: line 47
Wait for approval before finalizing
≈ “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.
Files
/generate-asset — 3D Asset Generation
Delegate to: blender-mcp-operator
Steps
1. Gather Requirements
Ask:
- "What asset do you need?" (weapon, prop, character, environment piece, vehicle)
- "What style?" (low-poly, stylized, realistic, cartoon, sci-fi, fantasy)
- "Triangle budget?" (default: <5000 for props, <10000 for hero assets)
- "Any reference?" (image, description, similar game)
2. Choose Source
- AI generation (no reference exists):
mcp__blender-mcp__generate_hyper3d_model_via_text - From reference image: use
/asset-from-imageinstead - From library (generic asset):
mcp__blender-mcp__search_polyhaven_assetsorsearch_sketchfab_models
3. Generate / Download
- For AI: submit prompt, poll
get_hyper3d_statusuntil complete,import_generated_asset - For library: download and import into Blender scene
4. Inspect
mcp__blender-mcp__get_viewport_screenshot— visual reviewmcp__blender-mcp__get_object_info— check triangle count, dimensions, materials
5. Optimize for Roblox
Via mcp__blender-mcp__execute_blender_code:
- Decimate to target triangle budget
- Scale to Roblox units
- Set origin to base center
- UV unwrap if needed
- Apply clean topology (remove doubles, fix normals)
6. Export
- Export as FBX to
assets/models/<asset-name>.fbx - Verify file size
7. Preview and Approve
mcp__blender-mcp__get_viewport_screenshot— final screenshot- Present to user with: poly count, texture resolution, dimensions, screenshot
- Wait for approval before finalizing
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
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.

