data-visualization
v1.0.0AI智能数据可视化;支持多种图表类型(柱状图、折线图、饼图、散点图、直方图、箱线图、小提琴图、面积图、热力图、平行坐标图、旭日图等),根据数据特征自动分析并推荐最佳图表组合,生成精美交互式HTML仪表板
MIT-0
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (智能数据可视化) match the included artifacts: SKILL.md describes using plotly/pandas/numpy and the repository contains a Python script to read CSV/Excel, analyze data, recommend charts and build an HTML dashboard — all expected for this purpose.
Instruction Scope
SKILL.md directs the agent to analyze user-provided tabular data and run scripts/generate_chart.py to produce an HTML dashboard. That scope is appropriate; note the script reads arbitrary input files supplied by the user (expected) — review inputs for sensitive content before sending them to the skill.
Install Mechanism
There is no install spec; dependencies are standard Python packages (plotly, pandas, numpy) declared in SKILL.md. No arbitrary downloads, external installers, or archive extraction are used.
Credentials
The skill declares no environment variables, no credentials, and no config paths. The script operates on local input files only, so requested access is proportional to the stated functionality.
Persistence & Privilege
Flags show normal behavior (always:false, agent can invoke autonomously). The skill does not request persistent elevated privileges or modify other skills; nothing indicates it will alter system/agent configuration.
Assessment
This skill appears to be a straightforward local data-visualization tool. Before installing/running it: 1) review the full scripts/generate_chart.py to confirm there are no network calls or unexpected behaviors (the provided excerpt shows none, but the file is truncated in the manifest), 2) run it in a sandbox or with non-sensitive example data first, and 3) ensure the listed Python dependencies (plotly, pandas, numpy) come from your trusted package sources. If you plan to feed sensitive data, confirm the script does not transmit data externally and consider running it offline.Like a lobster shell, security has layers — review code before you run it.
latest
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
SKILL.md
数据可视化Skill
任务目标
- 本Skill用于:AI智能分析数据特征,自动推荐最佳图表组合,生成精美的交互式HTML可视化仪表板
- 能力包含:智能数据分析、多种图表类型支持(柱状图、折线图、饼图、散点图、直方图、箱线图、小提琴图、面积图、热力图、平行坐标图、旭日图等)、自动图表推荐、综合仪表板生成
- 触发条件:用户需要将数据可视化展示、不确定用什么图表类型、需要快速生成专业可视化效果
前置准备
- 依赖说明:
plotly pandas numpy
操作步骤
-
数据准备与分析
- 用户提供数据(可以是表格数据、CSV格式或结构化数据)
- AI智能分析数据特征(数据类型、维度、关系、相关性等)
- AI根据数据特征自动推荐最合适的图表类型组合
-
图表生成
- 调用
scripts/generate_chart.py生成交互式HTML可视化仪表板 - AI自动选择最佳图表类型(支持10+种图表类型)
- 所有图表统一展示在一个美观的页面中
- 调用
-
输出与优化
- 生成单个HTML文件,包含多种交互式图表
- 支持鼠标悬停、缩放、平移等交互功能
- 响应式设计,适配不同屏幕尺寸
资源索引
- 必要脚本:见 scripts/generate_chart.py(用途:根据数据生成指定类型的图表)
- 领域参考:见 references/chart-types.md(何时读取:需要了解不同图表类型的适用场景和数据格式要求时)
- 领域参考:见 references/data-format.md(何时读取:需要了解输入数据的格式规范时)
注意事项
- AI会自动分析数据特征并推荐最佳图表组合
- 支持的图表类型:柱状图、折线图、饼图、散点图、直方图、箱线图、小提琴图、面积图、热力图、平行坐标图、旭日图等
- 图表类型选择基于数据特征(数值列数量、分类列数量、数据分布、相关性等)
- 图表支持缩放、平移等交互操作
- 生成最多15个图表,按优先级排序
使用示例
示例1:AI自动分析并生成仪表板
- 功能说明:AI分析数据特征,自动推荐并生成最佳图表组合
- 执行方式:AI智能分析+脚本自动生成
- 示例命令:python scripts/generate_chart.py --input sales.csv --output dashboard.html
- 输出内容:单个HTML文件,包含AI推荐的多种图表(柱状图、折线图、饼图、散点图、热力图等)
示例2:支持的图表类型
- 柱状图:类别对比、值计数分布
- 折线图:时间序列趋势分析
- 饼图:占比分析
- 散点图:变量相关性分析
- 直方图:数值分布分析
- 箱线图:数据分布差异对比
- 小提琴图:分布密度展示
- 面积图:趋势变化可视化
- 热力图:相关性矩阵展示
- 平行坐标图:多维度数据展示
- 旭日图:层级数据分析
Files
4 totalSelect a file
Select a file to preview.
Comments
Loading comments…
