跳到主内容
智客 ZICQ

技能库 智客分类:文档办公 data-analysis

Data Analysis

分析电子表格数据,产生洞察力,创建可视化,并从Excel/CSV数据中构建报告.

6896 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

分析电子表格数据,产生洞察力,创建可视化,并从Excel/CSV数据中构建报告.

何时用

官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Data Analysis Assistant、Overview、How to Use、Getting Started、Analysis Types、Output Formats。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Analyze spreadsheet data, generate insights, create visualizations, and build reports from Excel/CSV data.

Data Analysis AssistantOverviewHow to UseGetting StartedAnalysis TypesOutput FormatsData OverviewDataset OverviewColumn SummaryData Quality IssuesStatistical AnalysisStatistical Summary

· 许可:MIT

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
data-analysis
description
Analyze spreadsheet data, generate insights, create visualizations, and build reports from Excel/CSV data.
许可
MIT
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「data-analysis」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-873f1623c271c5c2-%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90.html
请存为 .cursor/skills/data-analysis/SKILL.md 或 .claude/skills/data-analysis/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/claude-office-skills/skills' --list

npx skills add 'https://github.com/claude-office-skills/skills' --skill 'data-analysis'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

═══════════════════════════════════════════════════════════════════════════════

CLAUDE OFFICE SKILL - Enhanced Metadata v2.0

═══════════════════════════════════════════════════════════════════════════════

Basic Information

name: data-analysis description: "Analyze spreadsheet data, generate insights, create visualizations, and build reports from Excel/CSV data." version: "1.0.0" author: claude-office-skills license: MIT

Categorization

category: finance tags:

  • data
  • analysis
  • spreadsheet
  • excel
  • visualization
  • insights department: All

AI Model Compatibility

models: recommended: - claude-sonnet-4 - claude-opus-4 compatible: - claude-3-5-sonnet - gpt-4 - gpt-4o

MCP Tools Integration

mcp: server: office-mcp tools: - read_xlsx - analyze_spreadsheet - create_chart - pivot_table optional_tools: - create_xlsx - xlsx_to_json

Skill Capabilities

capabilities:

  • data_analysis
  • statistical_analysis
  • visualization
  • trend_detection
  • reporting

Input/Output Specification

input: required: - type: file formats: [xlsx, csv, xls] description: The spreadsheet data to analyze optional: - type: text name: analysis_goal description: Specific questions or analysis goals - type: text name: output_format description: Preferred output format (report, chart, summary)

output: primary: type: report format: markdown sections: - data_overview - key_insights - visualizations - recommendations

Language Support

languages:

  • en
  • zh

Related Skills

related_skills:

  • excel-automation
  • report-generator
  • xlsx-manipulation

Data Analysis Assistant

Analyze data in spreadsheets, uncover insights, and create compelling visualizations.

Overview

This skill helps you:

  • Understand and explore your data
  • Perform statistical analysis
  • Generate insights and recommendations
  • Create charts and visualizations
  • Write formulas and queries

How to Use

Getting Started

  1. Share your spreadsheet or data file
  2. Describe what you want to analyze
  3. Get insights, formulas, or visualizations

Analysis Types

Exploratory Analysis

"What patterns do you see in this data?"
"Give me an overview of this dataset"
"What are the key statistics?"

Specific Questions

"What was the total revenue by region?"
"Which products had the highest growth?"
"Is there a correlation between X and Y?"

Visualization Requests

"Create a chart showing sales trends"
"Make a comparison chart of Q1 vs Q2"
"Show the distribution of customer ages"

Output Formats

Data Overview

## Dataset Overview

**Rows**: 1,234
**Columns**: 15
**Date Range**: Jan 2025 - Dec 2025

### Column Summary
| Column | Type | Non-null | Unique | Sample Values |
|--------|------|----------|--------|---------------|
| date | Date | 100% | 365 | 2025-01-01 |
| revenue | Number | 98% | 890 | $1,234.56 |
| region | Text | 100% | 5 | North, South |

### Data Quality Issues
- [X] rows have missing values in [column]
- [Y] potential duplicates detected

Statistical Analysis

## Statistical Summary

### [Metric Name]
- **Mean**: X
- **Median**: Y
- **Std Dev**: Z
- **Min/Max**: A / B

### Key Findings
1. [Finding with statistical support]
2. [Finding with statistical support]

### Recommendations
- [Action based on analysis]

Insight Report

## Analysis Report: [Topic]

### Executive Summary
[2-3 sentence overview of key findings]

### Key Metrics
| Metric | Value | Change |
|--------|-------|--------|
| Total Revenue | $X | +Y% |
| Avg Order Value | $Z | -W% |

### Trends
1. **[Trend 1]**: [Description with data]
2. **[Trend 2]**: [Description with data]

### Recommendations
1. [Actionable recommendation]
2. [Actionable recommendation]

Common Analysis Workflows

Sales Analysis

1. "Show total sales by month"
2. "Which products are top performers?"
3. "What's the customer segment breakdown?"
4. "Compare this year vs last year"
5. "Forecast next quarter based on trends"

Customer Analysis

1. "What's the customer distribution by segment?"
2. "Calculate customer lifetime value"
3. "Which customers are at risk of churning?"
4. "What's the acquisition cost vs LTV ratio?"

Financial Analysis

1. "Calculate profit margins by product"
2. "What's the expense breakdown?"
3. "Show cash flow trends"
4. "Compare budget vs actual"

Formula Generation

Request Formulas

"Write a formula to calculate year-over-year growth"
"Create a VLOOKUP to match customer data"
"Make a dynamic sum based on criteria"

Formula Output

## Formula: [Purpose]

### Excel/Google Sheets
```excel
=SUMIFS(Sales[Amount], Sales[Region], "North", Sales[Date], ">="&DATE(2025,1,1))

Explanation

  • SUMIFS: Sums values meeting multiple criteria
  • First argument: Column to sum
  • Subsequent pairs: Criteria column + criteria value

Usage

Place in cell [X] where you want the result.


## Visualization Recommendations

### Choose the Right Chart
| Data Type | Best Chart |
|-----------|------------|
| Trends over time | Line chart |
| Part of whole | Pie/Donut chart |
| Comparison | Bar chart |
| Distribution | Histogram |
| Correlation | Scatter plot |
| Geographic | Map chart |

### Chart Specifications
```markdown
## Recommended Chart: [Type]

**Data Series**:
- X-axis: [Column] (e.g., Date)
- Y-axis: [Column] (e.g., Revenue)
- Series: [Column] (e.g., Region)

**Formatting**:
- Title: "[Descriptive title]"
- Colors: Use consistent color scheme
- Labels: Show values on data points

**Chart Description**:
[What this chart shows and why it's useful]

Advanced Analysis

Pivot Table Design

## Pivot Table: [Purpose]

**Rows**: [Field 1], [Field 2]
**Columns**: [Field 3]
**Values**: SUM of [Field 4], AVG of [Field 5]
**Filters**: [Field 6]

Expected Output:
| Region | Q1 | Q2 | Q3 | Q4 | Total |
|--------|----|----|----|----|-------|
| North | $X | $X | $X | $X | $X |
| South | $X | $X | $X | $X | $X |

Cohort Analysis

## Cohort Analysis

**Cohort Definition**: Customers grouped by [first purchase month]
**Metric**: [Retention rate / Revenue / etc.]
**Time Period**: [12 months]

| Cohort | M0 | M1 | M2 | M3 | ... |
|--------|-----|-----|-----|-----|-----|
| Jan 25 | 100%| 45% | 32% | 28% | ... |
| Feb 25 | 100%| 48% | 35% | 30% | ... |

Best Practices

For Better Analysis

  1. Clean data first: Handle missing values, duplicates
  2. Define metrics clearly: What exactly are you measuring?
  3. Consider context: Industry benchmarks, seasonality
  4. Validate findings: Cross-check with other data sources

For Better Visualizations

  1. Keep it simple: One main message per chart
  2. Label clearly: Title, axes, legend
  3. Use appropriate scale: Don't truncate misleadingly
  4. Consider colorblind users: Use patterns or distinct colors

Limitations

  • Cannot directly execute code on your data
  • Large datasets may need sampling
  • Complex statistical models need specialized tools
  • Real-time data requires live connections
  • Cannot guarantee 100% accuracy on OCR'd data

相关技能

文档办公

Ontology

为结构化的代理内存和可堆肥技能所打入的知识图. 在创建/征服实体(Person, project, Task, Evention, Document)时使用,链接相关对象,强制约束,规划多步动作作为图变,或技能需要共享状态时使用. 触发到"记住","我知道什么","链接X到Y",…

文档办公

Nano Pdf

使用纳米-pdf CLI编辑带有自然语言指令的PDF.

文档办公

Word / DOCX

创建,检查,并编辑有可靠样式的Microsoft Word文档和DOCX文件,编号,跟踪更改,表格,章节,并进行相容性检查. 当 (1) 任务涉及 Word 或 ".docx " 时使用; (2) 文件包括跟踪的更改,评论,字段,表格,模板,或页面布局限制; (3) 文档必须在不…

文档办公

Api Gateway

通过 Maton 网关调用第三方 API, 它为用户已经连接的应用程序注入证书 。 当用户命名一个连接的应用程序和其中的具体行动时使用此技能——读取一个邮箱,查询一个CMM,归档一个问题,更新一个电子表格,通过一个连接的搜索或刮取提供者运行一个查询. 每一次通话都到用户连接的应用…