What makes Blender 资产生成 notable?

990 downloads. Trust evidence available

How should Blender 资产生成 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Blender 资产生成

Generates ecommerce/game/teaching 3D assets via Blender scripts (Blender 4.2+ including 5.x). Supports cloud Windows and local machines; reference-image guid... Skill: Blender 资产生成 Owner: yamasite Summary: Generates ecommerce/game/teaching 3D assets via Blender scripts (Blender 4.2+ including 5.x). Supports cloud Windows and local machines; reference-image guid... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-23T06:39:54.722Z | user Initial release of blender-asset-generator. - Generates structured, reproducible 3D asset projects for ecommerce, game, or teaching use c

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

990

Updated

Oct 11, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 990 downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 990 downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.0release · observed Apr 23, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.0.0release
Initial release of blender-asset-generator. - Generates structured, reproducible 3D asset projects for ecommerce, game, or teaching use cases via Blender scripts (supports Blender 4.2+ and 5.x). - Supports cloud Windows PC as primary runtime, with local execution on Windows or macOS as alternatives. - Offers text-only and vision-assisted workflows; gracefully degrades if reference images or vision are unavailable. - Produces clear project structure: spec.json, Blender Python scripts, run scripts, and required export formats (GLB mandatory, FBX/USDC optional), plus preview renders and QA evaluation. - Includes input templates and references to guide usage and ensure consistent quality.
Observed Apr 23, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s173svzz2y3tqm5hzwzbk529h185a2nq:blender-asset-generator

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-yamasite-blender-asset-generator/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

23,092 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: blender-asset-generator
description: Generates ecommerce/game/teaching 3D assets via Blender scripts (Blender 4.2+ including 5.x). Supports cloud Windows and local machines; reference-image guided workflow with graceful degradation when vision is unavailable.
---

# Blender Asset Generator (Blender 4.2+ / 5.x)

This Skill generates a reproducible asset project that can be executed in:
- Cloud PC (Windows) as the primary runtime
- Local computer (Windows or macOS) as an alternative runtime

The Skill outputs:
- A structured spec (`spec.json`) describing the asset
- Executable Blender Python scripts (`scripts/*.py`) using `bpy`
- Run scripts for Windows/macOS
- Export artifacts: `GLB` (required), `FBX` (optional), `USDC` (optional), plus preview renders

## Quick Start

1. Choose a mode:
   - `Text-only Mode` (no image or no vision): fast and deterministic
   - `Vision-assisted Mode` (reference images + multimodal model): extract structure/dimensions from images, then confirm with user

2. Provide input:
   - Required: object name + use case (`ecommerce` / `game` / `teaching`) + desired output formats (`GLB` required, `FBX` optional)
   - Optional: target size (at least one anchor dimension), poly budget, material style, reference images

3. The Skill will:
   - Normalize input into `spec.json`
   - Generate `scripts/build.py`, `scripts/render.py`, `scripts/export.py` (or update them)
   - Provide `Cloud (Windows)` and `Local (Windows/macOS)` run commands
   - Generate a QA checklist and a final evaluation

## Input Template

```text
Blender Version: 4.2+ (supports 4.2 and 5.x)
Primary Runtime: Cloud PC (Windows)
Output Priority: GLB required; FBX optional
USD: USDC optional (via file extension)

Use Case: ecommerce | game | teaching
Asset Name:
Asset Category: (e.g., bottle / lunch box / hanger / simple prop / teaching diagram)

Text Description (required):
- What it is:
- Key parts/components:
- Material style (optional): plastic/metal/glass/wood/fabric
- Target realism: low/medium/high

Dimensions (recommended):
- Provide at least ONE anchor dimension, e.g. height=240mm
- If unknown: provide category-typical size OR accept default size

Constraints (optional):
- Poly budget (triangles):
- UV: required | optional | no
- Texture placeholders: yes | no
- Naming convention: (optional)

Reference Images (optional):
- Attach images (front/side/top) if available
- If images are provided, say whether there is a scale reference in the image:
  - e.g. A4 paper / coin / ruler / hand / known product standard size
```

## References

Read these as needed:
- Workflow: `references/workflow.md`
- Ecommerce reference-image template: `references/ecommerce-reference-guided-template.md`
- Degradation strategy (no vision available): `references/degradation-strategy.md`
- QA checklist: `references/qa-checklist.md`
- Presets (common defaults): `references/presets.md`

## Output Contract

Always output in this structure:
1. `Project Package`
   - File tree (w

assets/project-skeleton/README.md

## Project Skeleton (Runnable)

This folder is a template for a runnable Blender 4.2+ project (including 5.x).

### What you do

1. Copy the entire folder as your working project.
2. Edit `spec.json` (or generate it via the Skill).
3. Run the appropriate script:
   - Cloud Windows: `run_cloud_windows.ps1`
   - Local Windows: `run_local_windows.ps1`
   - Local macOS: `run_local_macos.sh`

### Donut Demo

Use the included donut demo scripts to verify your Blender setup quickly:
- macOS: `run_donut_macos.sh`
- Windows: `run_donut_windows.ps1`

### What you get

- `scene.blend`
- `exports/<asset>.glb` (required)
- `exports/<asset>.fbx` (optional)
- `renders/front.png`, `renders/three_quarter.png`
- `run-log.txt`

_meta.json

{
  "ownerId": "kn7bhk6zsrsx57t0ny1db6b8y5834ykt",
  "slug": "blender-asset-generator",
  "version": "1.0.0",
  "publishedAt": 1776926394722
}

references/degradation-strategy.md

## Degradation Strategy (When Vision Is Not Available)

Problem: user provides reference images, but the local agent/runtime cannot do multimodal vision.

Design goal: never block the pipeline. Always continue with a deterministic text-driven build, while collecting the minimum extra info needed to make the asset usable.

### Rule 1: Acknowledge image, do not interpret it

If vision is unavailable:
- Do not guess shapes, colors, or dimensions from the image.
- Use the image only as a file attachment to be carried into the project package for later reference.

### Rule 2: Ask a "Minimal Clarification Form"

Ask the user to answer 6 items max (prefer 3):

```text
Minimal Clarification Form (No-Vision Mode)

1) What is it? (one sentence)
2) Choose the closest base shape:
   - A) box-ish (rounded rectangle)
   - B) cylinder-ish
   - C) bottle-ish (cylinder + neck)
   - D) flat plate/sheet
3) Provide ONE anchor dimension in mm:
   - height OR width OR diameter = ?
4) Do you need a lid/cap/handle/button? (yes/no; if yes, which)
5) Target style: matte plastic / metal / glass / other
6) Output: GLB (required); FBX (optional yes/no)
```

If the user refuses dimensions:
- Use a category default size from presets, and mark `open_questions` prominently.

### Rule 3: Continue with "Text-only Mode"

Proceed to generate:
- `spec.json` using defaults and user answers
- scripts + run commands
- preview renders

Mark all unconfirmed dimensions as:
- `confidence: low`
- or put into `open_questions`

### Rule 4: Provide a "Upgrade Path"

Offer two ways to improve accuracy later:
- User supplies one more anchor dimension or a simple dimension table
- User runs the same project in a vision-capable agent (cloud) to refine the spec

references/ecommerce-reference-guided-template.md

## Ecommerce "Reference-Image Guided" Template

Goal: given one or more reference images, produce a *confirmable* structure + dimensions spec for ecommerce assets, with low user effort.

### Inputs

- Images: ideally `front`, `side`, `top/back` (any subset works)
- Optional: scale reference in image (ruler, A4 paper, coin, hand, known standard)
- Text: product name + category + short description

### Output: "Structure Card" (agent-generated)

Always output this card before generating the final `spec.json`:

```text
Structure Card (Draft)

1) View & assumptions
- Views available: front/side/top/other
- Symmetry: none | left-right | radial
- Hidden parts: unknown | inferred (must be marked as inferred)
- Scale: known anchor | unknown (needs 1 anchor)

2) Components (decomposed)
- Component A: (e.g., main body) -> primitive: box/cylinder/profile
- Component B: (e.g., lid/cap) -> primitive: cylinder
- Component C: (e.g., handle/spout/button) -> primitive: box/cylinder/curve-extrude

3) Key dimensions (best-effort, mark confidence)
- Overall: height H=?, width W=?, depth D=? (confidence: high/med/low)
- Diameters: D1=?, D2=? (confidence)
- Thicknesses: wall T=?, lid T=? (confidence)
- Radii/chamfers: R=? (confidence)

4) Material hints (visual)
- Main: matte plastic / brushed metal / glass / rubber
- Color palette: #... (optional)
- Surface details: label area / logo recess / grip texture (optional)

5) What MUST be confirmed by user (minimal)
- One anchor dimension (e.g. height in mm)
- Any critical functional dimension (e.g. opening diameter)
```

### How the agent extracts dimensions from images (Vision-assisted mode)

Rules (keep it honest and low-friction):
- Never claim exact dimensions from a single photo without a scale anchor.
- Use relative ratios when scale is unknown (e.g. `W/H = 0.62`).
- If multiple views exist, cross-check ratios (front vs side).
- Mark each inferred dimension with confidence.

Recommended extraction steps:
1. Identify silhouette bounding box in each view.
2. Estimate aspect ratios (H:W, H:D).
3. Detect key features and their relative placement:
   - Lid height as % of total height
   - Handle thickness vs body width
   - Spout position from top edge
4. If a scale reference exists:
   - Derive pixel-to-mm scale (approx)
   - Convert key dimensions to mm
5. Ask for ONE anchor if missing:
   - "Please confirm one value: overall height (mm) or overall width (mm)."

### A universal "Ecommerce Spec" mapping

For ecommerce, focus on what reduces returns:
- Overall dimensions (H/W/D)
- Opening size / usable volume (if applicable, only if user provides)
- Fit-critical sizes (case, holder, accessory compatibility)
- Material + finish (matte/gloss, metal vs plastic)
- Included parts (caps, seals, accessories)

### Output: Final `spec.json`

After user confirms the minimal anchor(s), generate `spec.json`:
- Use mm
- Put unknowns into `open_questions`
- Preserve a `reference_images` array with notes and assumptions

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular