Back to Details

analyze

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

/analyze - Answer Data Questions

/analyze - 解答数据问题

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Answer a data question, from a quick lookup to a full analysis to a formal report.
若遇到不熟悉的占位符或需要查看已连接的工具，请参阅 CONNECTORS.md。
解答各类数据问题，涵盖快速查询、完整分析到正式报告等场景。

Usage

使用方法

/analyze <natural language question>
/analyze <自然语言问题>

Workflow

工作流程

1. Understand the Question

1. 理解问题

Parse the user's question and determine:
  • Complexity level:
    • Quick answer: Single metric, simple filter, factual lookup (e.g., "How many users signed up last week?")
    • Full analysis: Multi-dimensional exploration, trend analysis, comparison (e.g., "What's driving the drop in conversion rate?")
    • Formal report: Comprehensive investigation with methodology, caveats, and recommendations (e.g., "Prepare a quarterly business review of our subscription metrics")
  • Data requirements: Which tables, metrics, dimensions, and time ranges are needed
  • Output format: Number, table, chart, narrative, or combination
解析用户的问题，确定：
  • 复杂程度:
    • 快速解答：单一指标、简单筛选、事实类查询（例如：“上周有多少用户注册？”）
    • 完整分析：多维度探索、趋势分析、对比研究（例如：“转化率下滑的原因是什么？”）
    • 正式报告：包含方法论、注意事项和建议的全面调研（例如：“准备一份订阅指标的季度业务回顾报告”）
  • 数据需求：所需的表、指标、维度和时间范围
  • 输出格式：数字、表格、图表、叙述性内容或组合形式

2. Gather Data

2. 收集数据

If a data warehouse MCP server is connected:
  1. Explore the schema to find relevant tables and columns
  2. Write SQL query(ies) to extract the needed data
  3. Execute the query and retrieve results
  4. If the query fails, debug and retry (check column names, table references, syntax for the specific dialect)
  5. If results look unexpected, run sanity checks before proceeding
If no data warehouse is connected:
  1. Ask the user to provide data in one of these ways:
    • Paste query results directly
    • Upload a CSV or Excel file
    • Describe the schema so you can write queries for them to run
  2. If writing queries for manual execution, use the 
    sql-queries
    skill for dialect-specific best practices
  3. Once data is provided, proceed with analysis
若已连接数据仓库MCP服务器：
  1. 探索数据架构，找到相关的表和列
  2. 编写SQL查询语句以提取所需数据
  3. 执行查询并获取结果
  4. 若查询失败，调试并重试（检查列名、表引用、特定SQL方言的语法）
  5. 若结果不符合预期，在继续前进行合理性检查
若未连接数据仓库：
  1. 请用户通过以下方式提供数据：
    • 直接粘贴查询结果
    • 上传CSV或Excel文件
    • 描述数据架构，以便为用户编写可执行的查询语句
  2. 若为手动执行编写查询语句，请使用
    sql-queries
    技能以遵循特定方言的最佳实践
  3. 数据提供后，继续进行分析

3. Analyze

3. 分析数据

  • Calculate relevant metrics, aggregations, and comparisons
  • Identify patterns, trends, outliers, and anomalies
  • Compare across dimensions (time periods, segments, categories)
  • For complex analyses, break the problem into sub-questions and address each
  • 计算相关指标、聚合值和对比结果
  • 识别模式、趋势、异常值和反常现象
  • 跨维度（时间段、细分群体、类别）进行对比
  • 对于复杂分析，将问题拆解为子问题并逐一解决

4. Validate Before Presenting

4. 呈现前验证

Before sharing results, run through validation checks:
  • Row count sanity: Does the number of records make sense?
  • Null check: Are there unexpected nulls that could skew results?
  • Magnitude check: Are the numbers in a reasonable range?
  • Trend continuity: Do time series have unexpected gaps?
  • Aggregation logic: Do subtotals sum to totals correctly?
If any check raises concerns, investigate and note caveats.
在分享结果前，执行以下验证检查：
  • 行数合理性：记录数量是否合理？
  • 空值检查：是否存在可能影响结果的意外空值？
  • 数值范围检查：数值是否在合理范围内？
  • 趋势连续性：时间序列是否存在意外缺口？
  • 聚合逻辑检查：分项总计是否与总和一致？
若任何检查发现问题，需展开调查并标注注意事项。

5. Present Findings

5. 呈现分析结果

For quick answers:
  • State the answer directly with relevant context
  • Include the query used (collapsed or in a code block) for reproducibility
For full analyses:
  • Lead with the key finding or insight
  • Support with data tables and/or visualizations
  • Note methodology and any caveats
  • Suggest follow-up questions
For formal reports:
  • Executive summary with key takeaways
  • Methodology section explaining approach and data sources
  • Detailed findings with supporting evidence
  • Caveats, limitations, and data quality notes
  • Recommendations and suggested next steps
快速解答场景：
  • 直接给出答案并附上相关背景
  • 附上所用查询语句（折叠或放在代码块中）以确保可复现
完整分析场景：
  • 先列出关键发现或洞察
  • 用数据表和/或可视化图表提供支持
  • 标注方法论和注意事项
  • 提出后续建议问题
正式报告场景：
  • 包含关键要点的执行摘要
  • 解释方法和数据源的方法论部分
  • 带有支持证据的详细发现
  • 注意事项、局限性和数据质量说明
  • 建议和后续步骤

6. Visualize Where Helpful

6. 按需可视化

When a chart would communicate results more effectively than a table:
  • Use the 
    data-visualization
    skill to select the right chart type
  • Generate a Python visualization or build it into an HTML dashboard
  • Follow visualization best practices for clarity and accuracy
当图表比表格更能有效传达结果时：
  • 使用
    data-visualization
    技能选择合适的图表类型
  • 生成Python可视化内容或构建HTML仪表盘
  • 遵循可视化最佳实践以确保清晰准确

Examples

示例

Quick answer:
/analyze How many new users signed up in December?
Full analysis:
/analyze What's causing the increase in support ticket volume over the past 3 months? Break down by category and priority.
Formal report:
/analyze Prepare a data quality assessment of our customer table -- completeness, consistency, and any issues we should address.
快速解答：
/analyze 12月有多少新用户注册？
完整分析：
/analyze 过去3个月支持工单量增长的原因是什么？按类别和优先级拆分分析。
正式报告：
/analyze 准备一份客户表的数据质量评估报告——涵盖完整性、一致性及需要解决的问题。

Tips

提示

  • Be specific about time ranges, segments, or metrics when possible
  • If you know the table names, mention them to speed up the process
  • For complex questions, Claude may break them into multiple queries
  • Results are always validated before presentation -- if something looks off, Claude will flag it
  • 尽可能明确时间范围、细分群体或指标
  • 若知晓表名，请告知以加快处理速度
  • 对于复杂问题，Claude可能会将其拆分为多个查询
  • 结果在呈现前都会经过验证——若发现异常，Claude会进行标记