Data Viz Kit

Use when producing any chart, data report page, KPI tile, or visual data deliverable for Chinese business audiences. Provides chart-choice rules, Chinese number and period conventions (万/亿, 同比/环比, 涨跌色), a validated light/dark palette, and a zero-dependency Python kit that renders self-contained HTML reports. 中文触发词:图表规范、选图、配色、数据可视化、HTML 数据报告。

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add shisuidata/ss-data-skills --skill data-viz-kit
Manual install
git clone --depth 1 https://github.com/shisuidata/ss-data-skills.git /tmp/ss-data-skills
mkdir -p ~/.claude/skills
cp -r /tmp/ss-data-skills/skills/data-viz-kit ~/.claude/skills/data-viz-kit

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Data Viz Kit

## 目标

让所有数据交付物的图表**一次做对**:选对图形、数字格式符合中文业务习惯、颜色经过计算校验、亮暗模式都可读,并且能直接产出一个可以发给老板的自包含 HTML 报告。

这个 Skill 是其他分析和汇报类 Skill 的视觉底座。它不负责分析本身,只负责“把结论画对、画好看”。

## 使用场景

使用这个 Skill,当你要:

- 为分析结论画图(趋势、对比、构成、分布、实验效果)
- 生成一份 HTML 数据报告、周报页面或实验报告
- 设计指标卡、结论横幅、表格视图
- 审查一张已有图表是否误导、是否难读
- 给看板或 PPT 定配色和数字格式规范

## 不适用场景

- 决定分析什么、怎么归因:先用对应的分析 Skill(如 `funnel-analysis`、`ab-test-analysis`)
- PPT 叙事结构:使用 `data-presentation-architect`
- 看板是否支持决策的整体审查:使用 `dashboard-reviewer`,本 Skill 只补充图表层面的意见
- 品牌视觉设计、营销海报

## 输入信息

最少输入:

- 要表达的结论(一句话)
- 数据(表格、JSON、CSV 或已计算好的数值)

推荐输入:

- 受众(管理层 / 业务 / 技术 / 金融交易类)
- 指标方向:越高越好还是越低越好
- 涨跌色约定:好坏色(默认)还是红涨绿跌
- 输出形式:HTML 报告、单张图、给 BI 工具的配置建议

## 上下文建议

推荐使用 [报告上下文模板](../../context/templates/report-context.md) 说明受众和决策场景;汇报类任务同时参考 [PPT 汇报上下文模板](../../context/templates/presentation-context.md)。

受众决定涨跌色约定和信息密度。缺少受众时按“业务负责人 + 好坏色约定”处理,并在输出中写明假设。

## 工作流程

按顺序做,颜色永远最后考虑:

1. **先写结论句**:这张图要让读者记住哪一句话?写不出来就先别画。
2. **选图形**:按 [选图规则](references/chart-choice.md) 从“数据的任务”出发选图,有时答案是一个指标卡而不是图。
3. **定数字格式**:按 [中文业务约定](references/cn-conventions.md) 处理万/亿、百分点、同比环比、周口径和涨跌色。
4. **上色**:按颜色承担的任务分配(分类 / 顺序 / 发散 / 状态),使用 [拾穗配色](references/palette.md),不要自创颜色。
5. **校验**:改过配色就运行 `python3 scripts/check_palette.py`,FAIL 必须修。
6. **生成**:能执行代码时,用 `scripts/sskit_viz.py` 生成 HTML(见下方“工具”),不要手写 SVG 坐标。
7. **对照反模式检查**:逐条过一遍 [常见错误](references/chart-choice.md#常见错误)。

## 工具

`scripts/` 下的脚本只依赖 Python 3.9+ 标准库:

| 文件 | 作用 |
| --- | --- |
Read the full skill on GitHub

Details

Skill name
data-viz-kit
Path
skills/data-viz-kit/SKILL.md
License
MIT
Repo updated
8 November 2026

FAQ

What does the Data Viz Kit skill do?

Use when producing any chart, data report page, KPI tile, or visual data deliverable for Chinese business audiences. Provides chart-choice rules, Chinese number and period conventions (万/亿, 同比/环比, 涨跌色), a validated light/dark palette, and a zero-dependency Python kit that renders self-contained HTML reports. 中文触发词:图表规范、选图、配色、数据可视化、HTML 数据报告。

How do I install the Data Viz Kit skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add shisuidata/ss-data-skills --skill data-viz-kit. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Data Viz Kit popular?

It lives in shisuidata/ss-data-skills, which has 9 GitHub stars and 0 forks.

Related skills

Ab Test Analysis

9

shisuidata/ss-data-skills

Use when designing, checking, or interpreting A/B tests and experiments. Computes significance, confidence intervals, sample ratio mismatch, power, CUPED, and sample size with a bundled zero-dependency script, then judges validity risks, guardrails, and ship/iterate/rollback decisions and renders an HTML experiment report. 中文触发词:A/B 实验、AB 测试、实验解读、显著性、样本量计算、能不能全量。

Testing & QA

Business Root Cause Analysis

9

shisuidata/ss-data-skills

Use when diagnosing business metric changes or anomalies such as GMV decline, conversion drop, retention loss, churn increase, revenue change, lead decline, or active user fluctuation with a structured root cause analysis plan. 中文触发词:指标归因、为什么下降、异常排查、GMV 下滑、指标波动原因。

Marketing, Sales & Business

Daily Report Writer

9

shisuidata/ss-data-skills

Use when writing a concise daily report, daily worklog, standup update, shift handoff, or end-of-day summary for data analysis, data development, BI, governance, or operations work. 中文触发词:日报、日终同步、站会发言、值班交接。

Writing & Content

Exploratory Data Analysis

9

shisuidata/ss-data-skills

Use when exploring a dataset before formal analysis, modeling, reporting, or dashboarding. Runs a bundled zero-dependency data health check on CSV files that infers field types, detects encoding, pseudo-nulls, numbers stored as text, leading-zero IDs, duplicate keys, partition-vs-event-time drift, missing dates, and orphan join keys, ranks issues P0/P1/P2, and renders an HTML report; then interprets grain, usability, and next analysis directions. 中文触发词:数据探索、EDA、数据体检、数据摸底、拿到一份新数据。

Data & Analytics

Data Requirement Clarifier

9

shisuidata/ss-data-skills

Use when a vague data analysis or data development request needs to be turned into a clear, buildable task. Clarifies business goal, metrics, dimensions, time range, data sources, output format, acceptance criteria, risks, and open questions. 中文触发词:需求澄清、模糊需求、临时取数、需求拆解、业务想看。

Data & Analytics

Stream Pipeline Designer

9

shisuidata/ss-data-skills

Use when designing or reviewing a real-time data pipeline with Flink, Spark Structured Streaming, Kafka, or CDC. Advises on time semantics, watermarks, state management, exactly-once guarantees, throughput, backpressure, and real-time to batch alignment. 中文触发词:实时数仓、Flink、Kafka、实时管道、背压、Watermark、CDC。

Data & Analytics

Browse the most popular Claude skills, all data & analytics skills, or write your own with the skills generator.