agentCLAWHUBUnverified

SQL Dataviz

Convert SQL query results into production-grade visual charts including bar, line, pie, map, KPI, AI insights, and interactive HTML dashboards with base64 PN... Skill: SQL Dataviz Owner: moniq888 Summary: Convert SQL query results into production-grade visual charts including bar, line, pie, map, KPI, AI insights, and interactive HTML dashboards with base64 PN... Tags: latest:1.0.1 Version history: v1.0.1 | 2026-03-27T10:33:33.832Z | user - 修正协作工具名称,将“report-generator”统一为“sql-report-generator”以匹配实际 Skill 名称 - 数据分析流程示意图和协作流程文档细节微调,增强 Skill 协作关系说明 - 文档其余内容未变,功能和接口保持不变 v1.0.0 |

OpenClaw

Rank

62

Safety

84

Downloads

990

Updated

Oct 11, 2026

Version

1.0.1

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
1.0.1release · observed Mar 27, 2026
Handshake status
UNKNOWNsecurity

What changed

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

  • Release 1.0.1release

    - 修正协作工具名称,将“report-generator”统一为“sql-report-generator”以匹配实际 Skill 名称 - 数据分析流程示意图和协作流程文档细节微调,增强 Skill 协作关系说明 - 文档其余内容未变,功能和接口保持不变

    Observed Mar 27, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s1774kyr593ezfy7qtq3g4k9t983g3a1:sql-dataviz
  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-moniq888-sql-dataviz/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

143,210 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

# sql-dataviz - SQL 数据可视化 Skill

## ⚠️ 使用前必读

本 Skill 需要 Python 依赖。**首次使用前必须安装依赖**:

```bash
skillhub_install install_skill sql-dataviz
```

工具会自动检测 Python3 环境、pip 可用性,并安装所有依赖。

### 依赖安装方式

| 方式 | 命令 | 适用场景 |
|------|------|---------|
| **自动安装(推荐)** | `skillhub_install install_skill sql-dataviz` | 一键安装,自动处理 |
| **手动安装** | `pip install -r requirements.txt` | 熟悉 Python 环境的用户 |

### 无依赖使用(受限模式)

如果无法安装依赖,本 Skill 提供以下**降级能力**:

✅ **可用功能**:
- 图表选型建议(基于业务场景推荐图表类型)
- 数据格式规范说明
- 可视化设计原则指导
- 配色方案推荐

❌ **不可用功能**:
- 图表生成(PNG/base64 输出)
- 交互式 HTML 图表
- Dashboard 构建
- 与 sql-master / sql-report-generator 联动

---

## 🔗 Skill 协作关系

本 Skill 与 **sql-master**、**sql-report-generator** 组成完整的数据分析流水线:

```
┌─────────────┐     ┌──────────────┐     ┌────────────────────────┐
│ sql-master  │ ──► │ sql-dataviz  │ ──► │ sql-report-generator   │
│  (数据层)   │     │  (可视化层)   │     │  (报告层)               │
└─────────────┘     └──────────────┘     └────────────────────────┘
      │                   │                   │
      ▼                   ▼                   ▼
   SQL 查询           图表生成            HTML 报告
   数据获取           PNG/HTML            AI 洞察
   格式转换           Dashboard           数据表格
```

### 协作模式

| 模式 | 组合 | 适用场景 |
|------|------|---------|
| **单独使用** | sql-dataviz | 已有数据,仅需图表可视化 |
| **数据可视化** | sql-master + sql-dataviz | SQL 查询 → 图表输出 |
| **可视化报告** | sql-dataviz + sql-report-generator | 图表 → 报告(无 SQL) |
| **完整流程** | sql-master + sql-dataviz + sql-report-generator | 完整数据分析报告 |

### 🥇 最优使用方式:三 Skill 串联

```python
from scripts.unified_pipeline import UnifiedPipeline

result = (
    UnifiedPipeline("销售分析")
    .from_file("sales.csv")                                    # sql-master: 数据获取
    .query("SELECT region, SUM(sales) as total FROM data GROUP BY region")
    .interactive_chart("bar", x_col="region", y_col="total")   # sql-dataviz: 可视化
    .insights(value_cols=["total"])                            # AI 洞察
    .report(title="销售报告", output="report.html")            # sql-report-generator: 报告
)
```

### 决策指南

```
你需要什么?
├─ 仅图表可视化 → sql-dataviz 单独使用
├─ SQL + 图表 → sql-master + sql-dataviz
├─ 图表 + 报告(无 SQL)→ sql-dataviz + sql-report-generator
└─ 完整分析报告 → sql-master + sql-dataviz + sql-report-generator ✅ 推荐
```

---

## 新增功能:交互式 HTML 图表(Plotly)

### `scripts/interactive_charts.py`

基于 Plotly 的 12 种交互式图表,输出自包含 HTML(支持 hover / zoom / pan):

```python
from scripts.interactive_charts import InteractiveChartFactory, DashboardBuilder

factory = InteractiveChartFactory(theme="powerbi")

# 12 种图表类型
html = factory.create_line(data)          # 折线图
html = factory.create_bar(data)           # 柱形图
html = factory.create_pie(data)           # 饼图(环形)
html = factory.create_scatter(data)       # 散点图
html = factory.create_heatmap(data)       # 热力图
html = factory.create_funnel(data)        # 漏斗图
html = factory.create_area(data)          # 面积图
html = factory.create_treemap(data)       # 树状图
html = factory.create_gauge(data)         # 仪表盘
html = factory.create_combo(data)         # 组合图(柱

sql-dataviz/SKILL.md

# sql-dataviz - SQL 数据可视化 Skill

## 概述

将 SQL 查询结果转化为**生产级可视化图表**。集成 Power BI 原生的 24+ 种视觉对象,支持对比、趋势、分布、占比、地理、指标监控、AI 智能分析等全场景。

所有图表以 **base64 编码的 PNG/SVG** 方式输出,可直接嵌入报告、邮件、Web 应用。

## 核心能力

### 1. 对比与趋势分析(8种)
- **簇状柱形图** - 多系列分类对比
- **堆积柱形图** - 整体+部分占比对比
- **100%堆积柱形图** - 统一尺度结构对比
- **簇状条形图** - 长分类名称对比
- **堆积条形图** - 区域/渠道层级对比
- **100%堆积条形图** - 横向结构占比
- **折线图** - 连续数据趋势
- **平滑折线图** - 弱化波动的趋势

### 2. 高级趋势(5种)
- **组合图** - 双指标(柱+折线)
- **面积图** - 累计总量展示
- **堆积面积图** - 多系列累计贡献
- **瀑布图** - 增减项影响分析
- **丝带图** - 排名变动追踪

### 3. 部分与整体(4种)
- **饼图** - 单维度占比
- **圆环图** - 中心标签占比
- **树状图** - 层级数据展示
- **漏斗图** - 流程转化分析

### 4. 分布与关系(4种)
- **散点图** - 两变量相关性
- **气泡图** - 三变量分析
- **点图** - 分类数据分布
- **高密度散点图** - 海量数据聚类

### 5. 地理空间(3种)
- **填充地图** - 区域数据热力
- **形状地图** - 自定义边界分析
- **ArcGIS 地图** - 专业空间分析

### 6. 指标监控(3种)
- **卡片图** - 单一关键指标
- **KPI 视觉对象** - 目标达成率
- **仪表盘图** - 指标健康度

### 7. AI 智能分析(4种)
- **分解树** - 多维度根因分析
- **关键影响因素** - 驱动因子权重
- **异常检测** - 自动异常标注
- **智能叙事** - 自然语言摘要

## 使用方式

### 基础用法

```python
from sql_dataviz import ChartFactory

# 创建图表工厂
factory = ChartFactory()

# 从 SQL 结果生成图表
data = {
    'categories': ['Q1', 'Q2', 'Q3', 'Q4'],
    'series': [
        {'name': '销售额', 'data': [100, 150, 120, 200]},
        {'name': '成本', 'data': [60, 80, 70, 100]}
    ]
}

# 生成簇状柱形图(base64)
chart_b64 = factory.create_clustered_column(data)

# 输出为 HTML 可嵌入
html = f'<img src="data:image/png;base64,{chart_b64}" />'
```

### 高级用法 - 组合分析

```python
# 多图表联动
dashboard = factory.create_dashboard({
    'title': '季度业绩分析',
    'charts': [
        {'type': 'clustered_column', 'data': sales_data, 'position': (0, 0)},
        {'type': 'pie', 'data': channel_data, 'position': (1, 0)},
        {'type': 'line', 'data': trend_data, 'position': (0, 1)},
        {'type': 'heatmap', 'data': region_data, 'position': (1, 1)}
    ]
})
```

## 依赖安装

### 自动安装(推荐)

```bash
# 使用 SkillHub 一键安装
skillhub_install install_skill sql-dataviz
```

### 手动安装

```bash
# 1. 安装 Python 依赖
pip install matplotlib seaborn plotly pandas numpy

# 2. 安装可选的地理数据库
pip install geopandas shapely

# 3. 验证安装
python -c "import matplotlib; print(matplotlib.__version__)"
```

## 文件结构

```
sql-dataviz/
├── SKILL.md                          # 本文件
├── charts/
│   ├── __init__.py
│   ├── comparison.py                 # 对比类图表
│   ├── trend.py                      # 趋势类图表
│   ├── composition.py                # 占比类图表
│   ├── distribution.py               # 分布类图表
│   ├── geographic.py                 # 地理类图表
│   ├── kpi.py                        # 指标监控
│   ├── ai_analysis.py                # AI 智能分析
│   └── base.py                       # 基类与工具函数
├── scripts/
│   ├── install_deps.sh               # 依赖安装脚本
│   └── demo.py                       # 演示脚本
└── references/
    ├── POWERBI_CHARTS.md             # Power BI 图表参考
    └── COLOR_SCHEMES.md              # 大厂配色方案
```

## 配置选项

### 主题与样式

```python
# 内置主题
factory.set_theme('powerbi')      # Power BI 官方配色
factory.set_theme('alibaba')      # 阿里巴巴配色
factory.set_theme('tencent')      # 腾讯配色
f

_meta.json

{
  "ownerId": "kn76k6338wpqydkxgdztg6vb9x83hz20",
  "slug": "sql-dataviz",
  "version": "1.0.1",
  "publishedAt": 1774607613832
}

references/bar-charts.md

# 条形图 & 横向条形图

适用场景:分类比较、排名展示。

---

## 纵向条形图(类别 ≤ 10)

```python
import matplotlib.pyplot as plt
import numpy as np

plt.rcParams['font.sans-serif'] = ['SimHei', 'Microsoft YaHei']
plt.rcParams['axes.unicode_minus'] = False

fig, ax = plt.subplots(figsize=(10, 6))

bars = ax.bar(df['category'], df['value'],
              color='#3b82f6', width=0.6, edgecolor='white')

# 柱顶标注数值
for bar in bars:
    h = bar.get_height()
    ax.text(bar.get_x() + bar.get_width()/2, h + max(df['value'])*0.01,
            f'{h:,.0f}', ha='center', va='bottom', fontsize=10)

ax.set_title('各品类销售额', fontsize=15, fontweight='bold', pad=12)
ax.set_xlabel('品类')
ax.set_ylabel('销售额(万元)')
ax.set_ylim(0, max(df['value']) * 1.15)  # 留出标注空间
ax.grid(axis='y', alpha=0.3, linestyle='--')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

plt.tight_layout()
plt.savefig('bar_chart.png', dpi=150, bbox_inches='tight')
```

---

## 横向条形图(排名 / 类别多 / 名称长)

```python
# 按值排序,最大值在顶部
df_sorted = df.sort_values('value', ascending=True)

fig, ax = plt.subplots(figsize=(10, max(6, len(df_sorted) * 0.4)))

# 高亮 Top 1
colors = ['#ef4444' if i == len(df_sorted)-1 else '#3b82f6'
          for i in range(len(df_sorted))]

bars = ax.barh(df_sorted['name'], df_sorted['value'],
               color=colors, height=0.6)

# 右侧标注数值
for bar in bars:
    w = bar.get_width()
    ax.text(w + max(df_sorted['value'])*0.01, bar.get_y() + bar.get_height()/2,
            f'{w:,.0f}', va='center', fontsize=10)

ax.set_title('Top 用户消费排名', fontsize=15, fontweight='bold', pad=12)
ax.set_xlabel('消费金额(元)')
ax.set_xlim(0, max(df_sorted['value']) * 1.12)
ax.grid(axis='x', alpha=0.3, linestyle='--')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

plt.tight_layout()
plt.savefig('bar_horizontal.png', dpi=150, bbox_inches='tight')
```

---

## 分组条形图(多系列对比)

```python
# df 列:month, group_a, group_b, group_c
categories = df['month'].tolist()
x = np.arange(len(categories))
width = 0.25
PALETTE = ['#3b82f6', '#10b981', '#f59e0b']

fig, ax = plt.subplots(figsize=(12, 6))

for i, (col, label) in enumerate([('group_a', 'PC端'), ('group_b', '移动端'), ('group_c', '小程序')]):
    offset = (i - 1) * width
    bars = ax.bar(x + offset, df[col], width, label=label,
                  color=PALETTE[i], edgecolor='white')

ax.set_xticks(x)
ax.set_xticklabels(categories)
ax.legend()
ax.set_title('各渠道月度订单量对比', fontsize=15, fontweight='bold')
ax.grid(axis='y', alpha=0.3, linestyle='--')
ax.spines['top'].set_visible(False)
ax.spines['right'].set_visible(False)

plt.tight_layout()
plt.savefig('grouped_bar.png', dpi=150, bbox_inches='tight')
```

---

## 堆叠条形图(占比构成)

```python
fig, ax = plt.subplots(figsize=(12, 6))
PALETTE = ['#3b82f6', '#10b981', '#f59e0b', '#ef4444']

bottom = np.zeros(len(df))
for i, col in enumerate(['cat_a', 'cat_b', 'cat_c', 'cat_d']):
    ax.bar(df['month'], df[col], bottom=bottom,
           label=col, color=PALETTE[i], edgecolor='white', linewidth=0.5)
    bottom += df[col].val

references/canvas-render.md

# Canvas 内嵌渲染

在对话中直接渲染图表,无需保存文件,用户即时看到结果。

---

## 什么时候用 Canvas 渲染

- 用户想在对话里直接看图,不想保存文件
- 快速验证图表效果
- 演示/汇报场景,需要即时展示

---

## 使用方式

通过 `canvas` 工具的 `eval` action 执行 JavaScript,渲染 Chart.js 图表。

### 折线图示例

```javascript
// canvas eval 内容
const ctx = document.getElementById('chart').getContext('2d');
new Chart(ctx, {
  type: 'line',
  data: {
    labels: ['1月', '2月', '3月', '4月', '5月', '6月'],
    datasets: [{
      label: '订单量',
      data: [1200, 1900, 1500, 2100, 2400, 2800],
      borderColor: '#3b82f6',
      backgroundColor: 'rgba(59,130,246,0.1)',
      borderWidth: 2,
      fill: true,
      tension: 0.4,
      pointRadius: 4
    }]
  },
  options: {
    responsive: true,
    plugins: {
      title: { display: true, text: '月度订单量趋势', font: { size: 16 } },
      legend: { position: 'top' }
    },
    scales: {
      y: { beginAtZero: true, grid: { color: 'rgba(0,0,0,0.05)' } }
    }
  }
});
```

### Canvas HTML 模板

```html
<!DOCTYPE html>
<html>
<head>
  <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
  <style>
    body { font-family: 'Microsoft YaHei', sans-serif; padding: 20px; background: #fff; }
    .chart-container { max-width: 800px; margin: 0 auto; }
  </style>
</head>
<body>
  <div class="chart-container">
    <canvas id="chart"></canvas>
  </div>
  <script>
    // 在这里放图表代码
  </script>
</body>
</html>
```

---

## Chart.js 常用图表类型

| type 值 | 图表类型 |
|---------|---------|
| `'line'` | 折线图 |
| `'bar'` | 条形图(纵向) |
| `'bar'` + `indexAxis: 'y'` | 横向条形图 |
| `'pie'` | 饼图(慎用) |
| `'doughnut'` | 环形图 |
| `'scatter'` | 散点图 |
| `'bubble'` | 气泡图 |
| `'radar'` | 雷达图 |

---

## 多系列条形图示例

```javascript
new Chart(ctx, {
  type: 'bar',
  data: {
    labels: ['Q1', 'Q2', 'Q3', 'Q4'],
    datasets: [
      {
        label: 'PC端',
        data: [3200, 4100, 3800, 5200],
        backgroundColor: '#3b82f6'
      },
      {
        label: '移动端',
        data: [5100, 6200, 7100, 8900],
        backgroundColor: '#10b981'
      }
    ]
  },
  options: {
    responsive: true,
    plugins: {
      title: { display: true, text: '各渠道季度订单量' }
    },
    scales: { y: { beginAtZero: true } }
  }
});
```

---

## 注意事项

- Canvas 渲染依赖网络加载 Chart.js CDN,离线环境需本地引入
- 数据量大时(>1000 点),建议先聚合再渲染,避免卡顿
- 中文字体在 Canvas 中需要系统已安装对应字体
- 复杂统计图(箱线图、小提琴图)建议用 Python matplotlib 生成图片,再展示
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

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/moniq888/skills/sql-dataviz",
      "sourceUrl": "https://clawhub.ai/moniq888/skills/sql-dataviz",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T21:34:47.045Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-moniq888-sql-dataviz/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-moniq888-sql-dataviz/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-11T21:34:47.045Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "990 downloads",
      "href": "https://clawhub.ai/moniq888/sql-dataviz",
      "sourceUrl": "https://clawhub.ai/moniq888/sql-dataviz",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-11T21:34:47.045Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.0.1",
      "href": "https://clawhub.ai/moniq888/sql-dataviz",
      "sourceUrl": "https://clawhub.ai/moniq888/sql-dataviz",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-03-27T10:33:33.832Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-moniq888-sql-dataviz/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-moniq888-sql-dataviz/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.0.1",
      "description": "- 修正协作工具名称,将“report-generator”统一为“sql-report-generator”以匹配实际 Skill 名称 - 数据分析流程示意图和协作流程文档细节微调,增强 Skill 协作关系说明 - 文档其余内容未变,功能和接口保持不变",
      "href": "https://clawhub.ai/moniq888/sql-dataviz",
      "sourceUrl": "https://clawhub.ai/moniq888/sql-dataviz",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-03-27T10:33:33.832Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 13, 2026.

For crawlers

This page is free to read. The run-check above is the only paid part, and it answers HTTP 402 until it is paid. Everything else here is public.

  • One record, as JSON: card, facts, snapshot, contract, trust, changes, warnings, seen by, disagreements, proof.
  • Every agent, one feed: /.well-known/ai-catalog.json
  • What this site sells, and the price: /.well-known/x402
  • Paid run-check: /api/v1/agents/clawhub-moniq888-sql-dataviz/run-check

Sponsored

Ads related to SQL Dataviz and adjacent AI workflows.