meshy-openclaw
Generate 3D models, textures, images, rig characters, animate them, and prepare for 3D printing using the Meshy AI API. Handles API key detection, task creation, polling, downloading, and full 3D print pipeline with slicer integration. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, 3D print a model, or interact with the Meshy API. For Claude Code or Cursor, use the meshy-3d-generation and meshy-3d-printing skills instead.
meshy-dev · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add meshy-dev/meshy-3d-agent --skill meshy-openclaw技能说明
name: meshy-openclaw description: Generate 3D models, textures, images, rig characters, animate them, and prepare for 3D printing using the Meshy AI API. Handles API key detection, task creation, polling, downloading, and full 3D print pipeline with slicer integration. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, 3D print a model, or interact with the Meshy API. For Claude Code or Cursor, use the meshy-3d-generation and meshy-3d-printing skills instead. license: MIT-0 compatibility: Requires Python 3 with requests package. Compatible with OpenClaw and all Agent Skills tools. metadata: author: meshy-dev version: "0.4.1" homepage: https://github.com/meshy-dev/meshy-3d-agent openclaw: primaryEnv: MESHY_API_KEY requires: env: - MESHY_API_KEY bins: - python3 - curl install: - kind: uv package: requests allowed-tools: Bash, Write
Meshy 3D — Generation + Printing
Directly communicate with the Meshy AI API to generate and print 3D assets. Covers the complete lifecycle: API key setup, task creation, exponential backoff polling, downloading, multi-step pipelines, and 3D print preparation with slicer integration.
SECURITY MANIFEST
Environment variables accessed:
MESHY_API_KEY— API authentication token sent in HTTPAuthorization: Bearerheader only. Never logged, never written to any file except.envin the current working directory when explicitly requested by the user.
External network endpoints:
https://api.meshy.ai— Meshy AI API (task creation, status polling, model/image downloads)
File system access:
- Read:
.env/.env.localin the current working directory only (API key lookup) - Write:
.envin the current working directory only (API key storage, only on user request) - Write:
./meshy_output/in the current working directory (downloaded model files, metadata) - Read: files explicitly provided by the user (e.g., local images passed for image-to-3D conversion), accessed only at the exact path the user specifies
- No access to home directories, shell profiles, or any path outside the above
Data leaving this machine:
- API requests to
api.meshy.aiinclude theMESHY_API_KEYin the Authorization header and user-provided text prompts or image URLs. No other local data is transmitted. Downloaded model files are saved locally only.
All paths below are relative to this skill's own directory (the directory containing this SKILL.md). Resolve them before running.
| Resource | When to use |
|---|---|
scripts/meshy_task.py | Bundled CLI for every Meshy API call (create / poll / download / record / …) |
scripts/slicers.py | Detect installed slicers; open a model file in a slicer |
scripts/fix_obj.py | Fix OBJ coordinate system, scale, and origin for slicers |
| reference.md | Full API reference: every parameter, response schema, error code |
| references/setup.md | API key setup — read when Step 0 finds no key |
| references/pipelines.md | Generation recipes: exact payloads + script calls per endpoint |
| references/printing.md | Print pipeline walkthroughs: slicer detection, analyze/repair, white model, multicolor, Creative Lab |
| references/troubleshooting.md | Error recovery trees and task failure messages |
IMPORTANT: First-Use Session Notice
When this skill is first activated in a session, inform the user:
All generated files will be saved to
meshy_output/in the current working directory. Each project gets its own folder ({YYYYMMDD_HHmmss}_{prompt}_{id}/) with model files, textures, thumbnails, and metadata. History is tracked inmeshy_output/history.json.
This only needs to be said once per session.
IMPORTANT: File Organization
All downloaded files MUST go into a structured meshy_output/ directory in the current working directory. Do NOT scatter files randomly.
- Each project:
meshy_output/{YYYYMMDD_HHmmss}_{prompt_slug}_{task_id_prefix}/ - Chained tasks (preview → refine → rig) reuse the same
project_dir - Track tasks in
metadata.jsonper project, and globalhistory.json - Auto-download thumbnails alongside models
The bundled CLI implements this: project-dir, record, and thumbnail subcommands.
IMPORTANT: Shell Command Rules
Use only standard POSIX tools. Do NOT use rg, fd, bat, exa/eza.
IMPORTANT: Run Long Tasks Properly
Meshy generation takes 1–5 minutes. Run each poll as a single Bash call and let it finish — the bundled CLI prints unbuffered progress in real time. Tasks sitting at 99% for 30–120s is normal finalization — do NOT interrupt. Pass a larger --timeout for heavy tasks instead of retrying.
IMPORTANT: Never Rebuild Bundled Scripts
scripts/meshy_task.py is the single source of truth for create_task / poll_task / download / get_project_dir / record_task / save_thumbnail. Never retype, paraphrase, or "reconstruct" these helpers from memory — not even partially. Compose CLI calls in bash, or write a small Python script that does sys.path.insert(0, "<this skill's scripts dir>") and from meshy_task import ....
Step 0: API Key Detection (ALWAYS RUN FIRST)
Only the current session environment and .env / .env.local in the current working directory are checked. Never scan home directories or shell profile files.
python3 scripts/meshy_task.py check-env
Decision After Detection
READY: key=...→ Proceed to Step 1.READY: NO_KEY_FOUND→ Go to Step 0a.PYTHON_REQUESTS: MISSING→ Runpip install requests.
Step 0a: API Key Setup (Only If No Key Found)
Follow references/setup.md: create a key at https://www.meshy.ai/settings/api (Pro plan requi
阅读完整来源 ↗