- Capability
- Description
- Text to 3D
- Generate 3D models from text descriptions
- Image to 3D
- Convert single or multiple images to 3D
- Retexture
- Apply new textures to existing models
Specs
- CapabilityDescription
- Text to 3DGenerate 3D models from text descriptions
- Image to 3DConvert single or multiple images to 3D
- RetextureApply new textures to existing models
- RemeshChange topology, polycount, or export format
- Auto-RiggingAdd skeleton to humanoid characters (includes walking + running)
- AnimationApply custom animations to rigged characters
- Text to ImageGenerate 2D images from text
- Image to ImageTransform existing images
- CapabilityDescription
- Print PipelineText/Image to 3D → OBJ download → Slicer
- Printability CheckManual checklist review (automated API coming soon)
- Slicer IntegrationOpen in Bambu Studio via URL scheme
- Multi-Color GuidanceManual color workflow (automated API coming soon)
- CapabilityDescription
- All generationText/Image to 3D, Retexture, Remesh, Rig, Animate, Text/Image to Image
- 3D printingOBJ download + Bambu Studio integration
- FeatureAgent Skill (this repo)
- SetupCopy Markdown files
- DependenciesPython 3 + requests
- How it worksAI reads instructions, makes API calls directly
- IDE supportAmp, Cline, Codex, Cursor, Gemini CLI, Claude Code, OpenCode and 20+ more
- File managementVia skill instructions
README
Meshy 3D Agent
AI agent skills for the Meshy AI 3D generation platform. Enables AI coding assistants (Cursor, Claude Code, OpenClaw) to generate 3D models, textures, images, rig characters, animate them, and prepare models for 3D printing — no MCP server required.
How It Works
These are pure Markdown skills — no server, no dependencies, no build step. Your AI assistant reads the skill files and gains the ability to interact with the Meshy API directly using shell commands and Python scripts.
Skills
meshy-3d-generation (core)
Full 3D generation lifecycle: API key setup, task creation, polling, downloading, and multi-step pipelines.
| Capability | Description | Credits |
|---|---|---|
| Text to 3D | Generate 3D models from text descriptions | 20-30 |
| Image to 3D | Convert single or multiple images to 3D | 20-30 |
| Retexture | Apply new textures to existing models | 10 |
| Remesh | Change topology, polycount, or export format | 5 |
| Auto-Rigging | Add skeleton to humanoid characters (includes walking + running) | 5 |
| Animation | Apply custom animations to rigged characters | 3 |
| Text to Image | Generate 2D images from text | 3-9 |
| Image to Image | Transform existing images | 3-9 |
meshy-3d-printing (optional)
3D printing workflow: printability checks, slicer integration (Bambu Studio), multi-color guidance.
| Capability | Description | Credits |
|---|---|---|
| Print Pipeline | Text/Image to 3D → OBJ download → Slicer | 20 |
| Printability Check | Manual checklist review (automated API coming soon) | 0 |
| Slicer Integration | Open in Bambu Studio via URL scheme | 0 |
| Multi-Color Guidance | Manual color workflow (automated API coming soon) | 0-10 |
The printing skill depends on the generation skill's script template and environment setup.
meshy-openclaw (OpenClaw / ClawHub)
A single unified skill for the OpenClaw ecosystem. Combines generation + printing into one file, with OpenClaw-compatible metadata.clawdbot frontmatter and a full SECURITY MANIFEST.
| Capability | Description | Credits |
|---|---|---|
| All generation | Text/Image to 3D, Retexture, Remesh, Rig, Animate, Text/Image to Image | 3–30 |
| 3D printing | OBJ download + Bambu Studio integration | 0 |
Designed for ClawHub publishing. API key is stored only in
.envin the current working directory — no shell profile access.
Quick Install
One command to install all skills:
npx skills add meshy-dev/meshy-3d-agent
Then set your API key (pick any method below):
Or simply start using the skill — when the agent loads it, it will detect that no API key is configured, ask you for it, and set it up automatically.
<details>
<summary>macOS / Linux</summary>
Option A: Global (recommended) — add to your shell profile so it persists across sessions:
nano ~/.zshrc
Add this line at the end, save and exit (Ctrl+O, Enter, Ctrl+X):
export MESHY_API_KEY="msy_YOUR_API_KEY"
Then reload:
source ~/.zshrc
Option B: Project-local — create a .env file in your project root:
echo 'MESHY_API_KEY=msy_YOUR_API_KEY' > .env
Remember to add
.envto your.gitignoreto avoid committing your key.
</details>
<details>
<summary>Windows</summary>
Option A: Permanent (recommended) — set via System Environment Variables:
setx MESHY_API_KEY "msy_YOUR_API_KEY"
Restart your terminal after running this command.
Option B: Current session only:
$env:MESHY_API_KEY = "msy_YOUR_API_KEY"
Option C: Project-local — create a .env file in your project root:
MESHY_API_KEY=msy_YOUR_API_KEY
</details>
Prerequisites
- A Meshy API key (get one here — requires Pro plan or above)
- Python 3 with
requestspackage (pip install requests)
Manual Installation
<details>
<summary>OpenClaw</summary>
Option A: Via ClawHub
npx clawhub install meshy-dev/meshy-3d-agent
Option B: Manual — copy the skills/meshy-openclaw/ folder to your OpenClaw skills directory.
</details>
<details>
<summary>Cursor</summary>
# Core (required)
mkdir -p .cursor/skills
cp skills/meshy-3d-generation/SKILL.md .cursor/skills/meshy-3d-generation.md
cp skills/meshy-3d-generation/reference.md .cursor/skills/meshy-reference.md
# 3D Printing (optional)
cp skills/meshy-3d-printing/SKILL.md .cursor/skills/meshy-3d-printing.md
</details>
<details>
<summary>Claude Code</summary>
# Core (required)
mkdir -p .claude/skills
cp skills/meshy-3d-generation/SKILL.md .claude/skills/meshy-3d-generation.md
cp skills/meshy-3d-generation/reference.md .claude/skills/meshy-reference.md
# 3D Printing (optional)
cp skills/meshy-3d-printing/SKILL.md .claude/skills/meshy-3d-printing.md
</details>
Skill vs MCP Server
| Feature | Agent Skill (this repo) | MCP Server |
|---|---|---|
| Setup | Copy Markdown files | npx meshy-mcp-server |
| Dependencies | Python 3 + requests | Node.js >= 18 |
| How it works | AI reads instructions, makes API calls directly | Dedicated server process with structured tools |
| IDE support | Amp, Cline, Codex, Cursor, Gemini CLI, Claude Code, OpenCode and 20+ more | Any MCP-compatible client |
| File management | Via skill instructions | Built-in auto-save with project folders |
Both approaches provide the same Meshy API capabilities. Choose based on your preference and setup.