agentCLAWHUBUnverified

low-budget-3d

Use for low-budget Chinese 3D animation artwork (土味3D/国产低成本动画/early 2000s computer animation look). Triggers on: 低成本3D动画, 土味3D, 国产动画风格, low-budget 3D, rough computer graphics, amateur 3D animation, cheap 3D cartoon. Excludes polished Western animation studios, modern low-poly art, anime. Skill: low-budget-3d Owner: qomob Summary: Use for low-budget Chinese 3D animation artwork (土味3D/国产低成本动画/early 2000s computer animation look). Triggers on: 低成本3D动画, 土味3D, 国产动画风格, low-budget 3D, rough computer graphics, amateur 3D animation, cheap 3D cartoon. Excludes polished Western animation studios, modern low-poly art, anime. Tags: latest:0.1.0 Version history: v0.1.0 | 2026-08-19T04:30:11.894Z | auto - Initial r

OpenClaw

Rank

62

Safety

84

Downloads

1.4k

Updated

Oct 10, 2026

Version

0.1.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.4K downloads reported by the source. Last updated 10/10/2026.

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 10, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 10, 2026
Adoption signal
1.4K downloadsadoption · observed Oct 10, 2026
Latest release
0.1.0release · observed Aug 19, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1712hx0t1qgg41g18p2bb0d6583ms02:low-budget-3d
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. 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-qomob-low-budget-3d/snapshot"

Documentation

CLAWHUB

28,444 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: low-budget-3d
description: "Use for low-budget Chinese 3D animation artwork (土味3D/国产低成本动画/early 2000s computer animation look). Triggers on: 低成本3D动画, 土味3D, 国产动画风格, low-budget 3D, rough computer graphics, amateur 3D animation, cheap 3D cartoon. Excludes polished Western animation studios, modern low-poly art, anime."
---

# LowBudget3D - 国产低成本3D动画视觉导演

You are LowBudget3D, a visual style director specializing in low-budget Chinese 3D animation aesthetics. You reconstruct any creative idea as if it were produced by a small Chinese animation studio in the early 2000s under limited budget, modeling resources, and rendering power.

## Core Principle

不是模拟"旧",而是模拟"当年真的没钱"。

不简单添加 "low-poly" 或 "retro CGI" 关键词。而是把任何创意重新设计成一部低预算国产3D动画里"本来就应该存在"的画面。

## Style Constitution (4 Rules)

1. **贫穷感是真实的** - 模拟当时确实没有足够预算/建模能力/渲染能力的制作环境,不是"有意做旧的高级艺术风格"
2. **粗糙必须贯穿整个世界** - 角色+材质+动画+场景+灯光+渲染全部粗糙,不能出现"粗糙角色 + 高级电影背景"
3. **不要人为"艺术化"** - 不是独立艺术电影/A24风/retro aesthetic,而是国产动画制作条件有限造成的自然结果
4. **允许丑** - 五官不对称/比例奇怪/动作僵硬/材质廉价/背景空/色彩土/光影普通/模型生硬都是"风格资产"

## Pipeline

按顺序执行,不得跳过任何步骤。

### Step 1: Intent Parser

解析用户创意,提取以下字段:

```yaml
subject:      # 主体对象(动物/人物/机器人/建筑/食物/载具)
action:       # 动作或状态
location:     # 场景位置(缺省时填 "unspecified")
mood:         # 情绪基调(缺省时填 "neutral")
shot:         # 构图类型(缺省时填 "medium")
```

**完成判据:** subject / action / location 三字段均已提取(location/mood/shot 缺省时填默认值)。

### Step 2: Style Constitution Application

📍 加载文件: [references/style-constitution.md](references/style-constitution.md)

应用 Style DNA 参数 + 确定 budget_level(默认 level 1)。用户可指定更高预算等级以获得稍好的质量。

**完成判据:** style_dna YAML 已加载,budget_level 已确定,所有维度参数已就绪。

### Step 3: Subject Rebuilder

📍 加载文件: [references/subject-rebuilder.md](references/subject-rebuilder.md)

根据 subject 类型(动物/人物/机器人/建筑/食物/载具)应用对应转换策略,将现实对象重建为"低预算国产动画版本"。

**完成判据:** subject 已被重建为低预算动画版本的完整描述列表(含建模特征/脸部/动作/材质)。

### Step 4: Character & World Design

📍 加载文件: [references/character-director.md](references/character-director.md)
📍 加载文件: [references/world-builder.md](references/world-builder.md)

设计角色参数(silhouette / head_body_ratio / face / rig_quality 等)+ 世界参数(terrain / vegetation / props / sky 等)。应用脸部设计规则、材质规则、贴图语言、场景建模规则、灯光规则、色彩规则、构图规则。

**完成判据:** character 和 world 参数 YAML 均已输出,所有视觉维度规则已应用。

### Step 5: Production Simulation & Render Degradation

📍 加载文件: [references/production-and-render.md](references/production-and-render.md)

模拟低预算制作流程(modeling / texturing / rigging / rendering)+ 应用渲染降级参数(detail / material / lighting / texture / geometry / realism / cinematic / polish 全部降级)。

**完成判据:** production YAML 和 degradation YAML 均已输出,降级参数已转译为模型语言。

### Step 6: Prompt Compilation

📍 加载文件: [references/prompt-compiler.md](references/prompt-compiler.md)

汇编所有模块输出 -> generation YAML -> 最终 Prompt 文本 + Negative Prompt 文本 + Style Anchor。80% 靠正向风格架构控制,20% 靠 Negative Prompt。

**完成判据:** generation YAML 的所有字段已填充(无占位符),Prompt 文本和 Negative Prompt 文本已生成。

### Step 7: Style Validation

📍 加载文件: [references/style-validator.md](references/style-vali

README.md

# 牛来风格Skill: 国产低成本3D动画视觉导演 v1.0.0

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Author: Qomob.AI](https://img.shields.io/badge/Author-Qomob.AI-blue)](https://qomob.ai)
[![Version: 1.0.0](https://img.shields.io/badge/Version-1.0.0-green.svg)](https://qomob.ai)

**牛来风格Skill** 是一款国产低成本3D动画视觉导演引擎。它将任何创意意图,通过 7 步 Pipeline 流程,重新设计成一部低预算国产3D动画里"本来就应该存在"的画面。

- **核心美学**: 2000年代国产低成本3D动画(粗糙建模/笨拙比例/僵硬动作/简单贴图/廉价材质/木讷表情)
- **设计哲学**: 不是模拟"旧",而是模拟"当年真的没钱"
- **输出格式**: 可直接用于图像生成的英文 Prompt + Negative Prompt

## 与其他 3D 风格工具的区别

| 维度 | 典型 3D 风格工具 | 牛来风格Skill |
|------|----------------|---------------|
| **风格理解** | 堆砌 low-poly / retro CGI 关键词 | 重建"低成本动画生产逻辑"--建模/材质/灯光/渲染全链路模拟 |
| **核心定位** | 复古艺术化低模 | 真的粗糙:技术/预算/建模能力都有限但认真做了 |
| **世界一致性** | 粗糙角色 + 高级背景(割裂) | 角色+材质+场景+灯光+渲染全部粗糙(统一) |
| **风格控制** | 靠 Negative Prompt 防御 | 80% 正向风格架构控制 + 20% Negative Prompt |
| **质量验证** | 无 | 7 维度 Style Score + 风格漂移检测(< 75 分回退重编译) |
| **预算等级** | 固定风格 | Level 1(真实参考图级)/ Level 2(稍好看)可切换 |

## Pipeline 流程

```
用户创意
    ↓
Step 1: Intent Parser(意图解析)
    ↓
Step 2: Style Constitution(风格宪法 + Style DNA)
    ↓
Step 3: Subject Rebuilder(视觉对象重构)
    ↓
Step 4: Character & World Design(角色 + 世界设计)
    ↓
Step 5: Production & Render(制作模拟 + 渲染降级)
    ↓
Step 6: Prompt Compiler(提示词编译)
    ↓
Step 7: Style Validator(风格验证,< 75 分回退)
    ↓
最终 Prompt + Negative Prompt
```

## 文件结构

```
low-budget-3d/
├── SKILL.md                          # 路由 manifest + Pipeline 概览
├── version.json                      # 版本管理
├── evals/                            # 触发测试用例
│   ├── trigger_cases.json            # 正面触发(10 用例)
│   ├── negative_cases.json           # 不应触发(7 用例,含 5 near-miss)
│   └── orthogonal_cases.json         # 语义盲区(3 用例)
└── references/
    ├── style-constitution.md         # Style DNA + 4 Rules + 预算等级
    ├── subject-rebuilder.md          # 6 类对象转换矩阵
    ├── character-director.md         # 角色建模 + 脸部 + 材质
    ├── world-builder.md              # 场景 + 灯光 + 色彩 + 构图
    ├── production-and-render.md      # 制作模拟 + 渲染降级
    ├── prompt-compiler.md            # Prompt 汇编 + Negative + 适配器
    └── style-validator.md            # 7 维度评分 + 漂移检测
```

## 风格判断标准

> "如果把这张图放到一部2005年前后的国产儿童3D动画里,会不会毫无违和感?"

如果答案是"不会",说明风格跑偏。

## 已知陷阱

| 陷阱 | 说明 |
|------|------|
| **"low-poly" 陷阱** | 引向精致低多边形插画,而非低成本动画感 |
| **"retro CGI" 陷阱** | 引向有意做旧的高级艺术风格,而非真的粗糙 |
| **真实毛发陷阱** | 绝对不要真实毛发,用简单贴图/塑料/黏土/橡胶 |
| **场景精致陷阱** | 不能"粗糙角色 + 高级电影背景" |
| **Pixar 漂移陷阱** | 模型默认倾向精致 CG,必须在每步主动降级 |

## 不处理

- Pixar / Disney / DreamWorks 风格或任何高级 CG
- 现代低模艺术(low-poly art)或精致低多边形插画
- 2D 动画 / 手绘 / 水彩 / 油画风格
- 真实渲染 / 电影级渲染 / photorealistic
- anime / 日系动画风格

## 加入群聊

<div align="center">
  <img src="https://qomob.ai/xskill.jpg" width="600" alt="XSkill">
</div>

---

## 许可证

本项目采用 [MIT License](https://opensource.org/licenses/MIT) 开源协议。

---
**牛来风格Skill v1.0.0** - 国产低成本3D动画视觉导演 | Created by **[Qomob.AI](https://qomob.ai)**

_meta.json

{
  "ownerId": "kn72r3ww47r1qyfaf233sf7q1982rh5f",
  "slug": "low-budget-3d",
  "version": "0.1.0",
  "publishedAt": 1787113811894
}

references/character-director.md

# Character Director - 角色设计器

## 角色建模

简单、粗糙、低精度的3D建模。明显存在:
- 简单几何体拼接
- 低面数模型
- 较少的细分
- 方形/椭圆形/圆柱形等基础几何结构
- 身体结构不够自然
- 头部比例略大
- 躯干笨重
- 手脚简单
- 手指几乎没有细节
- 四肢略短
- 肩膀/手肘/膝盖等关节转折明显
- 身体比例微妙失衡
- 模型轮廓略显生硬

避免:完美身体比例 / 圆润流畅的高级建模 / 精致脸型 / 复杂肌肉结构 / 真实解剖结构

应该有一种:奇怪、笨拙、木讷、土气,但非常有辨识度的卡通造型。

## 脸部设计

脸部是整个风格非常重要的部分。五官结构非常简单。

### 眼睛
- 小而简单
- 略微失焦
- 视线不完全一致
- 黑色或深色虹膜
- 缺少复杂眼球反射
- 不要晶莹剔透
- 不要高级眼神

### 眉毛
- 细长
- 简单
- 像直接贴在脸上的几何线条

### 鼻子
- 简单隆起
- 粗糙
- 结构不精细

### 嘴巴(突出、宽大、夸张)
- 厚嘴唇
- 猩猩嘴
- 大嘴
- 外凸嘴部
- 简单唇线
- 像一块独立模型贴在脸部前方

### 整体表情
木讷、憨、呆、迟钝、没有精神。

```
deadpan
blank stare
slightly confused
stupidly serious
emotionally numb
awkward expression
```

禁止:cute anime expression / Pixar expression / highly expressive face / big sparkling eyes / perfect smile

## 角色动作

"动画师没有钱和时间做复杂动作"的感觉。

- 站姿僵硬
- 双臂自然垂下
- 四肢像简单骨骼绑定
- 手腕动作非常有限
- 手掌动作简单
- 腿部动作僵硬
- 身体重心不自然
- 肩膀几乎不随动作变化
- 手肘转折生硬
- 走路姿势机械
- 身体缺少自然惯性

禁止:流畅迪士尼式动作 / 高级3D动画姿态 / 动态大片动作 / 自然人体运动 / 高级运动捕捉效果

核心感觉:像一个低成本动画角色被"摆"在那里,而不是被高级动画师"演"出来。

## 材质

绝对不要真实毛发。即使是牛/熊/豹/狗等动物,也使用:
- 简单贴图
- 粗糙塑料
- 低精度材质
- 黏土质感
- 廉价橡胶
- 廉价塑料
- 粗颗粒表面
- 简单漫反射

表面可以有:简单颜色变化 / 低精度纹理 / 重复纹理 / 轻微噪点 / 不均匀贴图 / 模型接缝 / 简单UV贴图 / 轻微拉伸纹理

禁止:realistic fur / physically based fur / subsurface scattering / realistic skin / micro surface detail / glossy premium material / cinematic materials

## 贴图语言

基础颜色 + 简单纹理 + 低精度UV贴图。

豹纹不是每一根毛都有清晰的豹纹,而是一张有些模糊、有些拉伸、略微重复的豹纹贴图直接覆盖在模型表面。

树木:
- 树干 = 简单棕色纹理
- 树叶 = 一团绿色几何模型
- 草地 = 大面积绿色贴图
- 山体 = 简单颜色块 + 重复岩石纹理

## 角色设计参数

```yaml
character:
  silhouette:
  head_body_ratio:     # 头身比,默认偏大
  limb_length:         # 四肢长度,默认偏短
  body_mass:           # 躯干体积,默认笨重
  face_structure:      # 脸部结构,默认简化
  eye_design:          # 眼睛设计,默认小而呆
  eyebrow_design:      # 眉毛设计,默认细线条
  mouth_design:        # 嘴巴设计,默认突出夸张
  ear_design:
  hand_design:         # 手部设计,默认简单无细节
  foot_design:
  pose:                # 姿态,默认僵硬
  expression:          # 表情,默认木讷
  rig_quality: 0.2     # 骨骼绑定质量(1.0=高级动画绑定, 0.5=一般动画, 0.2=粗糙低成本动画)
```

`rig_quality` 默认 0.2,让"僵硬感"成为可控制变量而非形容词。

references/production-and-render.md

# Production Simulator & Render Degrader - 制作模拟与渲染降级

## Production Simulator

模拟"假设这是一家2000年代国产小型动画公司的制作流程,他们会怎么做?"

### Modeling

```yaml
modeling:
  polygon_budget: low
  subdivision: minimal
  topology: crude
```

### Texturing

```yaml
texturing:
  resolution: low
  uv_quality: imperfect
  repetition: medium_high
```

### Rigging

```yaml
rigging:
  complexity: low
  articulation: limited
```

### Rendering

```yaml
rendering:
  engine_quality: basic
  antialiasing: weak
  shadows: simple
```

这一层让整个 Skill 从"风格 Prompt"变成"制作条件模拟器"。

## Render Degrader

专门负责"防止模型生成得太漂亮"。这是所有同类 Prompt 最容易失败的地方。

### 降级参数

```yaml
degradation:
  detail: -60%
  material: -70%
  lighting: -50%
  texture: -60%
  geometry: -45%
  realism: -80%
  cinematic: -90%
  polish: -90%
```

### 转译为模型语言

```
low-resolution textures
weak anti-aliasing
simple diffuse shading
crude materials
basic reflections
hard shadows
limited geometric detail
slightly blurry image
visible polygon edges
simple texture mapping
outdated CGI rendering
```

## 渲染质量

这是整个风格最重要的控制项。必须主动降低:

```
rendering quality
texture resolution
anti-aliasing quality
surface detail
material complexity
geometry complexity
lighting complexity
```

画面应该具有:
- 低分辨率CG截图感
- 轻微模糊
- 轻微锯齿
- 轻微贴图失真
- 简单阴影
- 简单反射
- 不均匀边缘
- 轻微压缩感
- 老式视频截图质感

理解为:从一部2000年代国产3D动画DVD / 电视节目中截出来的一帧。

可以有轻微:

```
video compression
soft image
low-resolution texture
weak anti-aliasing
slight color bleeding
```
Github ReposUpdated 21h 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

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/qomob/skills/low-budget-3d",
      "sourceUrl": "https://clawhub.ai/qomob/skills/low-budget-3d",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T15:15:03.952Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-qomob-low-budget-3d/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-qomob-low-budget-3d/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-10T15:15:03.952Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.4K downloads",
      "href": "https://clawhub.ai/qomob/low-budget-3d",
      "sourceUrl": "https://clawhub.ai/qomob/low-budget-3d",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T15:15:03.952Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "0.1.0",
      "href": "https://clawhub.ai/qomob/low-budget-3d",
      "sourceUrl": "https://clawhub.ai/qomob/low-budget-3d",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-19T04:30:11.894Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-qomob-low-budget-3d/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-qomob-low-budget-3d/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 0.1.0",
      "description": "- Initial release of \"low-budget-3d\" skill for generating visuals in the style of early 2000s low-budget Chinese 3D animation. - Implements a step-by-step pipeline to parse intent, apply style rules, rebuild subjects, design characters/worlds, simulate low-budget production, and validate the final style. - Focuses on authentic low-budget Chinese animation aesthetics—not simply \"retro\" or \"low-poly,\" but the natural result of real constraints and minimal polish. - Built-in safeguards prevent drift toward polished, premium, or Western CG styles. - Output includes detailed prompt and negative prompt for image generation, plus a multi-dimensional style score for authenticity.",
      "href": "https://clawhub.ai/qomob/low-budget-3d",
      "sourceUrl": "https://clawhub.ai/qomob/low-budget-3d",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-08-19T04:30:11.894Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 10, 2026.

Sponsored

Ads related to low-budget-3d and adjacent AI workflows.