chart_guide

Agent Skills › siddsachar/row-bot › chart_guide

chart_guide

GitHub

提供数据可视化与图表创建指导。当分析表格数据时，使用 create_chart 工具生成 Plotly 交互式图表或保存为 PNG。支持按用户指令或数据趋势主动触发，适用于展示类别对比、时间趋势及分布情况。

tool_guides/chart_guide/SKILL.md siddsachar/row-bot

Trigger Scenarios

用户请求绘制图表需要展示数据趋势或分布

Install

npx skills add siddsachar/row-bot --skill chart_guide -g -y

More Options

Non-standard path

npx skills add https://github.com/siddsachar/row-bot/tree/main/tool_guides/chart_guide -g -y

Use without installing

npx skills use siddsachar/row-bot@chart_guide

指定 Agent (Claude Code)

npx skills add siddsachar/row-bot --skill chart_guide -a claude-code -g -y

安装 repo 全部 skill

npx skills add siddsachar/row-bot --all -g -y

预览 repo 内 skill

npx skills add siddsachar/row-bot --list

SKILL.md

Frontmatter

{
    "icon": "📈",
    "name": "chart_guide",
    "tags": [],
    "tools": [
        "chart"
    ],
    "description": "Guidance for data visualisation and chart creation.",
    "display_name": "Chart Guide"
}

DATA VISUALISATION:

When you analyse tabular data (CSV, Excel, JSON) and the results would be clearer as a chart, use the create_chart tool to render an interactive Plotly chart inline (chart_type lists the supported types).
Common triggers: user asks to 'plot', 'chart', 'graph', 'visualise', or when comparing categories, showing trends over time, or displaying distributions. You may also proactively suggest a chart when it adds value.
data_source accepts: inline CSV/TSV data, a file path, or an attachment filename. For small tables you can paste the data directly. The tool auto-unpivots wide-format data when needed.
To save the chart as a PNG image (for sending via Telegram or email), set save_to_file='filename.png'. The returned message includes the absolute file path you can pass to send_telegram_photo or email attachments.
Chart + send: create_chart with save_to_file='chart.png', then send_telegram_photo or attach it to email.