AI 3D generation — 技能 — openclaw中文资讯站

技能详情（站内镜像，无评论）

Create, convert, and download AI-generated 3D models using Neural4D APIs. Optimized for commercial pipelines.

媒体与内容

许可证：MIT-0

MIT-0 ·免费使用、修改和重新分发。无需归因。

版本：v1.0.0

统计：⭐ 0 · 191 · 1 current installs · 1 all-time installs

⭐ 0

安装量（当前） 1

🛡 VirusTotal ：良性 · OpenClaw ：良性

Package：6e6e6e/ai-3d-generation

安全扫描（ClawHub）

VirusTotal ：良性
OpenClaw ：良性

OpenClaw 评估

The skill's requirements and runtime instructions are consistent with its stated purpose of driving Neural4D text/image-to-3D pipelines; nothing requested is disproportionate or unrelated.

目的

Name/description (AI 3D generation via Neural4D) align with the SKILL.md: endpoints, async polling, matting and conversion pipelines, and downloading model URLs. Required binaries (curl, jq) are reasonable for an instruction-only HTTP-based integration. The declared config path (~/neural4d-3d-generation/) is plausible for storing model artifacts. Minor note: the registry metadata lists no required env vars but the SKILL.md expects an optional …

说明范围

The instructions confine operations to calling Neural4D endpoints, polling job status, uploading images for matting, and downloading model files. They do not instruct the agent to read unrelated files, search system state, or send data to unexpected endpoints. All external network activity is targeted at the documented base URL.

安装机制

No install spec or code files — instruction-only — so nothing will be written or executed on disk by an installer. This is the lowest-risk install model.

证书

The only credential mentioned is NEURAL4D_API_TOKEN (documented in SKILL.md as required for API calls and marked optional in metadata). That single API token is proportional to making authenticated requests. The skill requests a configuration directory for storing artifacts; this is reasonable but means filesystem write/read permissions will be used in that path. There are no unrelated secrets or multiple credentials requested.

持久

The skill does not request always:true and is user-invocable. It does not claim to modify other skills or system-wide settings. No persistent installation steps are defined.

综合结论

This skill is instruction-only and appears to do what it says: call Neural4D endpoints to generate and convert 3D assets. Before installing, confirm the API host (https://alb.neural4d.com:3000) is the legitimate service you expect, and avoid putting a high-privilege/shared token in a global environment variable — prefer a dedicated API token with limited quota. Expect the skill to upload images and download model files to the configured ~/neur…

安装（复制给龙虾 AI）

将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。

请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「AI 3D generation」。简介：Create, convert, and download AI-generated 3D models using Neural4D APIs. Optim…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/6e6e6e/ai-3d-generation/SKILL.md
（来源：yingzhi8.cn 技能库）

SKILL.md

打开原始 SKILL.md（GitHub raw）

---
name: AI 3D Generation
slug: 3d-generation
version: 1.0.0
homepage: 
description: Create, convert, and download AI-generated 3D models using Neural4D APIs. Optimized for commercial pipelines.
changelog: Initial release with Text-to-3D, Image-to-3D matting pipelines, and physical format conversion (STL/FBX/USDZ).
metadata: {"clawdbot":{"requires":{"bins":["curl", "jq"],"env.optional":["NEURAL4D_API_TOKEN"],"config":["~/neural4d-3d-generation/"]},"os":["linux","darwin","win32"]}}
---

## Setup

On first use, ensure the `NEURAL4D_API_TOKEN` environment variable is set.
All API requests must include the header: `Authorization: Bearer <YOUR_TOKEN>`.

## When to Use

Use this skill when generating 3D models from text prompts or images using DreamTech's Neural4D engine. This is particularly suited for creating assets where precise format conversions (like `.stl`, `.obj`, `.fbx`) and physical dimensions are required for manufacturing workflows.

## Core Rules & Cost Guardrails

### 1. Point Consumption Awareness
Always track API point costs before executing bulk runs:
- **Text to 3D:** 20 points per operation.
- **Image to 3D:** 20 points per operation.
- **Chibi-style Generation:** 30 points per operation.
- **Format Conversion:** 10 points per operation.
- You can query the remaining balance at `/api/queryPointsInfo`.

### 2. Asynchronous Polling Contract
Model generation is asynchronous. You must poll for completion:
- Query `/api/retrieveModel` using the `uuid`.
- Check `codeStatus`:
  - `0`: Generation complete.
  - `1`: Generating (Wait and poll again).
  - `-3`: Generation failed.

## Workflow Pipelines

### Pipeline A: Text to 3D
1. **Request:** `POST https://alb.neural4d.com:3000/api/generateModelWithText`.
   - Payload: `{"prompt": "...", "modelCount": 4, "disablePbr": 0}`.
2. **Retrieve:** Extract `uuids` from the response.
3. **Poll:** Call `/api/retrieveModel` with the `uuid` until `codeStatus` is `0`.
4. **Download:** Extract `modelUrl` and download the `.glb` asset.

### Pipeline B: Image to 3D (Strict 3-Step Process)
1. **Matting:** Submit the image (JPG/PNG, <10MB, 256x256 to 6048x8064) via `multipart/form-data` to `/api/mattingImage`. Extract the `requestId`.
2. **Get Matting Result:** Send the `requestId` to `/api/getMattedResult`. Extract a preferred `fileKey` from the response.
3. **Generate:** Send the `fileKey` to `/api/generateModelWithImage` to start generation and receive `uuids`.
4. **Poll:** Use `/api/retrieveModel` to poll status and get the `modelUrl`.

### Pipeline C: Format Conversion for Manufacturing
For physical prototyping, default exports must be converted from `.glb`.
1. **Request:** `POST https://alb.neural4d.com:3000/api/convertToFormat`.
2. **Payload:** Provide the `uuid`, desired `modelType` (e.g., `stl`, `fbx`, `obj`), and `modelSize` in millimeters (must be > 1).
3. **Poll Status:** Check `statusType`:
   - `0`: Complete, use `modelUrl` to download.
   - `1`: Converting (Wait and retry).
   - `-1`: Failed or bad parameters.

## External Endpoints Reference

All requests route through the base URL: `https://alb.neural4d.com:3000/api`.

| Action | Endpoint | Auth | Purpose |
|--------|----------|------|---------|
| Text to 3D | `/generateModelWithText` | Bearer Token | Generate from text prompt |
| Retrieve | `/retrieveModel` | Bearer Token | Poll status and get model URL |
| Matting | `/mattingImage` | Bearer Token | Pre-process image |
| Matting Result | `/getMattedResult` | Bearer Token  | Retrieve file keys for image generation  |
| Image to 3D | `/generateModelWithImage` | Bearer Token | Generate from matted fileKey |
| Convert Format | `/convertToFormat` | Bearer Token | Convert to stl/fbx/obj with physical size |
| Job Progress | `/queryJobProgress` | Bearer Token | Check percentage progress |