AgentSkillsCN

analysis

数据探索与洞察生成：开展探索性分析、运用统计方法、提供可视化指引。适用于数据集的深入挖掘、模式发现，以及业务洞见的提炼与输出。 适用场景如下： - “对这些数据进行分析” - “数据中隐藏着怎样的规律？” - “从这些数据中提炼出哪些洞察？” - “探索性数据分析” - “这些数据究竟向我们揭示了什么？”

SKILL.md
--- frontmatter
name: analysis
description: |
  Data analysis and insights generation: exploratory analysis, statistical methods, visualization guidance.
  Use when exploring datasets, finding patterns, or generating business insights.

  Use when:
  - "analyze this data"
  - "what patterns are in the data"
  - "generate insights from"
  - "exploratory data analysis"
  - "what does this data tell us"

Data Analysis Skill

Explore datasets, identify patterns, and generate actionable insights.

Quick Start

bash
/wicked-data:analysis explore data/sales.csv

This will:

  1. •Profile the data
  2. •Generate descriptive statistics
  3. •Identify patterns and trends
  4. •Suggest visualizations
  5. •Provide initial insights

After exploration, ask specific questions:

  • •"What's the trend in sales over time?"
  • •"Which customer segments are most valuable?"
  • •"Are there any anomalies in the data?"

Analysis Workflow

1. Profile & Understand

bash
/wicked-data:numbers sales.csv

Key questions:

  • •What's the grain? (one row per what?)
  • •What's the date range?
  • •What are the key metrics?
  • •Any obvious data quality issues?

2. Explore Patterns

Basic explorations:

  • •Distributions (histograms, percentiles)
  • •Categorical breakdowns (frequency tables)
  • •Time trends (daily/monthly aggregations)
  • •Correlations (relationship between metrics)

3. Segment Analysis

Common segmentations:

  • •RFM: Recency, Frequency, Monetary value
  • •Cohorts: Group by signup/first purchase month
  • •Geographic: By region, country, city
  • •Behavioral: By usage patterns

4. Anomaly Detection

Detection methods:

  • •Statistical outliers (>3 standard deviations)
  • •Unusual patterns (volume spikes/drops)
  • •Temporal anomalies (day-of-week deviations)

Insight Generation

Pattern: Observation → Insight → Action

Bad (just observations):

  • •Average order value is $45
  • •60% of customers are in the US

Good (insights with actions):

code
### Insight: Weekend Shopping Behavior
**Observation**: Sales peak on Friday (+40% vs weekday avg)
**Insight**: Customers shop for weekend needs on Friday.
**Action**: Launch "Friday Flash Sale" campaign (+15% expected)
**Confidence**: HIGH (consistent over 6 months)

Visualization Guidance

Data TypeComparisonBest Chart
Time seriesTrend over timeLine chart
CategoricalCompare valuesBar chart
DistributionShow spreadHistogram, Box plot
RelationshipCorrelationScatter plot
CompositionPart of wholeStacked bar, Pie
GeographicLocation dataMap (choropleth)

Integration

wicked-data:numbers - Primary tool for data queries:

bash
/wicked-data:numbers data.csv

wicked-kanban - Document insights as tasks wicked-mem - Store analysis patterns for reuse

Best Practices

  • •Start simple: Begin with basic aggregations before complex models
  • •Validate assumptions: Check data quality, verify calculations
  • •Tell a story: Lead with the "so what?" and make it actionable
  • •Be honest about uncertainty: Note limitations, quantify confidence

Common Pitfalls

  • •Correlation ≠ Causation: Ice cream and drownings both increase in summer
  • •Simpson's Paradox: Aggregate trend may reverse when segmented
  • •Survivorship Bias: Include failed cases for balanced view
  • •Cherry-picking: Report all patterns, not just favorable ones

Reference

For detailed content: