What makes Scientific Drawing notable?

1K downloads. Trust evidence available

How should Scientific Drawing 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

Scientific Drawing

科研绘图工具 - 支持技术路线图、流程图、原理图、架构图等科研图形绘制。基于 Python matplotlib/pillow，支持 SVG/PNG 高清输出。 Skill: Scientific Drawing Owner: jirboy Summary: 科研绘图工具 - 支持技术路线图、流程图、原理图、架构图等科研图形绘制。基于 Python matplotlib/pillow，支持 SVG/PNG 高清输出。 Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-16T12:30:10.725Z | auto - 首次发布科研绘图技能，专为基金申请和论文写作场景设计。 - 支持多种科研图类型：技术路线图、流程图、原理图、架构图、甘特图等。 - 基于 Python matplotlib/pillow，输出高清 PNG/SVG 图像，默认 300 DPI。 - 提供丰富请求示例与详细参数说明，支持中文文本和自定义配色方案。 - 涵盖科研绘图最佳实践和常见注意事项。 Archive index: Archive v1.0.0: 5 f

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.0k

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. 1K 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: 1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.0release · observed Apr 16, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s172kehers3wd9ajz7fymawqnn843cz8:scientific-drawing

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-jirboy-scientific-drawing/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

5,744 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: scientific-drawing
description: "科研绘图工具 - 支持技术路线图、流程图、原理图、架构图等科研图形绘制。基于 Python matplotlib/pillow，支持 SVG/PNG 高清输出。"
metadata:
  {
    "openclaw": { "emoji": "🎨" }
  }
---

# 科研绘图技能

专为科研基金申请、论文写作设计的绘图工具。

## 🎯 适用场景

### 基金申请书
- 技术路线图
- 研究内容框架图
- 试验装置原理图
- 年度计划甘特图

### 学术论文
- 算法流程图
- 系统架构图
- 数据可视化图表
- 对比结果图

## 🛠️ 使用方法

### 1. 直接描述需求（推荐）

告诉 SuperMike：
> "帮我画一个技术路线图，包含：文献调研→理论分析→试验设计→数据分析→论文撰写"

或
> "画一个振动台子结构试验的原理图，包含振动台、物理子结构、数值子结构、作动器"

### 2. 指定详细参数

```
绘制技术路线图：
- 标题：基于机器学习的结构损伤识别研究
- 模块：数据采集、特征提取、模型训练、损伤识别、结果验证
- 风格：横向流程/纵向层级
- 颜色：蓝色系/绿色系
- 输出：PNG 高清 (300 DPI)
```

## 📊 支持的图形类型

| 类型 | 用途 | 示例 |
|------|------|------|
| **流程图** | 技术路线、算法流程 | 方框 + 箭头 |
| **层级图** | 系统架构、模块关系 | 树状结构 |
| **原理图** | 试验装置、物理模型 | 几何图形组合 |
| **时序图** | 试验步骤、时间线 | 甘特图形式 |
| **对比图** | 方法对比、结果展示 | 多子图布局 |
| **数据图** | 折线图、柱状图、散点图 | 数据可视化 |

## 🎨 输出规格

### 默认配置
- **格式**: PNG (可指定 SVG/PDF)
- **分辨率**: 300 DPI (印刷级)
- **尺寸**: A4 横向/纵向 (可自定义)
- **字体**: 中文支持 (SimHei/Arial)

### 基金申请推荐
- 技术路线图：A4 横向，宽 1200px
- 原理图：A4 纵向，宽 800px
- 对比图：根据内容自适应

## 📝 绘图流程

**SuperMike 的工作流：**

1. **需求分析** - 理解图形类型、内容、风格
2. **草图设计** - 规划布局、模块、连接关系
3. **代码生成** - 编写 Python 绘图脚本
4. **图形渲染** - 执行代码生成图像
5. **质量检查** - 确认清晰度、文字可读性
6. **交付优化** - 根据反馈调整

## 🔧 技术实现

### 依赖库
```python
import matplotlib.pyplot as plt
import matplotlib.patches as patches
from PIL import Image, ImageDraw, ImageFont
import numpy as np
```

### 绘图模板

**流程图模板：**
```python
def draw_flowchart(title, steps, connections, output_path):
    fig, ax = plt.subplots(figsize=(12, 6))
    # 绘制方框
    # 绘制箭头
    # 添加文字
    plt.savefig(output_path, dpi=300, bbox_inches='tight')
```

**架构图模板：**
```python
def draw_architecture(title, modules, hierarchy, output_path):
    fig, ax = plt.subplots(figsize=(10, 8))
    # 绘制层级框
    # 绘制连接线
    # 添加标签
    plt.savefig(output_path, dpi=300, bbox_inches='tight')
```

## 💡 最佳实践

### 基金申请绘图要点

1. **清晰第一** - 避免过度复杂，重点突出
2. **风格统一** - 所有图用同一套配色方案
3. **文字精简** - 每框不超过 10 个字
4. **箭头明确** - 流程方向清晰
5. **留白适当** - 不要塞得太满

### 配色建议

| 类型 | 主色 | 辅色 | 强调色 |
|------|------|------|--------|
| **技术路线** | #2E86AB (蓝) | #A23B72 (紫) | #F18F01 (橙) |
| **原理图** | #3B5998 (深蓝) | #5D8AA8 (浅蓝) | #DC143C (红) |
| **架构图** | #228B22 (绿) | #32CD32 (浅绿) | #FFD700 (金) |

## ⚠️ 注意事项

1. **中文支持** - 需配置中文字体 (SimHei)
2. **高清输出** - 基金申请至少 300 DPI
3. **格式兼容** - 优先 PNG (通用), 可备 SVG (可编辑)
4. **尺寸控制** - 考虑 Word 文档插入后的显示效果
5. **迭代优化** - 第一版可能不完美，根据反馈调整

## 📋 请求示例

**示例 1：技术路线图**
```
帮我画基金申请的技术路线图：
研究内容：振动台子结构试验的时滞补偿方法
步骤：
1. 文献调研与问题分析
2. 时滞机理建模
3. 自适应补偿算法设计
4. 数值仿真验证
5. 振动台试验验证
6. 工程应用推广
要求：横向流程，蓝色系，A4 横向
```

**示例 2：试验装置原理图**
```
绘制振动台子结构试验原理图：
元素：振动台、物理子结构 (试件)、数值子结构 (计算机)、作动器、传感器
连接：力/位移反馈
标注：边界条件模拟、实时交互
要求：示意图风格，清晰标注各部分
```

**示例 3：算法流程图**
```
画一个自适应时滞补偿算法流程图：
开始→位移指令→时滞预测→补偿计算→作动器加载→响应测量→误差判断→(循环/结束)
要求：纵向流程，包含判断分支
```

---

## 🚀 快速开始

**告诉 SuperMike：**
> "帮我画一个 XXX 图，包含 XXX 内容，要 XXX 风格"

我会：
1. 确认需求细节
2. 生成 Python 绘图代码
3. 执行并输出图像
4. 根据你的反馈调整优化

**输出位置：** `D:\Personal\OpenClaw\figures\`

---

_技能版本：v1.0_  
_创建日期：2026-03-09_  
_

_meta.json

{
  "ownerId": "kn7024ea9mpn20nvh221shx04h8434xe",
  "slug": "scientific-drawing",
  "version": "1.0.0",
  "publishedAt": 1776342610725
}

skill-card.md

## Description:

Scientific Drawing helps agents create research diagrams, including technical roadmaps, flowcharts, schematics, architecture diagrams, Gantt charts, and data visualizations, using Python matplotlib/Pillow with high-resolution PNG and SVG output.

This skill is ready for commercial/non-commercial use.

## Publisher:

[jirboy](https://clawhub.ai/user/jirboy)

### License/Terms of Use:

MIT-0

## Use Case:

Researchers, grant writers, academic authors, and supporting developers use this skill to turn diagram requirements into Python-generated figures for proposals and papers.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Generated drawing helpers write image files to fixed or caller-controlled filesystem paths.

Mitigation: Run the skill in a workspace or sandbox and validate or constrain output paths before executing generated or helper code.

Risk: Figure-generation code depends on local fonts and platform-specific output paths.

Mitigation: Confirm required fonts and redirect output to a controlled project directory before relying on generated figures.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/jirboy/skills/scientific-drawing)

## Skill Output:

**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance, files]

**Output Format:** [Markdown guidance with Python code and generated PNG/SVG/PDF figure files]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Default figure output is 300 DPI; helper scripts use matplotlib/Pillow and a fixed local output directory unless adjusted.]

## Skill Version(s):

1.0.0 (source: server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d 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.