
3D High-Poly Models
Guides an agent to build detailed 3D models and prepare efficient runtime versions for web or real-time use.
- Repository
- MengTo/Skills
- Stars
- 7,187
- Licence
- MIT
- Files
- 3 files
What it does
When installed, the agent follows a set of guidelines for making close-up 3D geometry look realistic: it checks the camera's viewpoints, adds detail where it is visible (silhouettes, bevels, surface forms), and keeps a detailed master model. It then produces lighter runtime versions with LODs (lower-detail copies for distant objects), instancing, sensible shadow and loading strategies, and measured performance checks. The skill is guidance text; it does not itself ship modelling software.
Great for
- Developers building 3D web scenes or real-time viewers who need detailed assets without slow load times
- Artists or technical designers preparing architectural or scanned-stone assets for interactive use
Skip it if
- Simple low-poly or stylised projects, where the extra process adds overhead without benefit
- Anyone expecting the skill to run modelling tools automatically; it gives instructions and does not include scripts or tool integrations
Try asking
- “Create a detailed stone archway model with believable bevels and prepare LODs for a three.js scene”
- “Our rooftop tiles look faceted up close; help me remove the visible faceting and check the triangle count”
- “Set up glTF export and LOD thresholds for this high-detail building asset”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 3 original files, the MIT licence and an attribution note.
3d-high-poly-models.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip 3d-high-poly-models.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip 3d-high-poly-models.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Give the agent the current triangle count, target hardware and camera distances so it can make realistic decisions
- Ask for profiling on both desktop and mobile rather than relying on visual judgement alone
What's inside
- agents/openai.yaml
- REFERENCES.md
- SKILL.md
Redistributed unmodified from MengTo/Skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.