Skip to content
Skills Library
Data & analytics · Analysis

data-analysis

/data-analysis

Analyze spreadsheet data, generate insights, and create visualizations. Use when a user asks to analyze data, explore a dataset, find trends, generate statistics, create charts from CSV or Excel data, summarize data, or answer questions about tabular data.

Repository
skills ↗
Licence
Apache-2.0
Last repository change
25.10.2026

Assessment and security

98/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene13 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
1
Deprecation

No signals detected. Repository changed on 25.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

Analyze spreadsheet data, generate insights, and create visualizations. Use when a user asks to analyze data, explore a dataset, find trends, generate statistics, create charts from CSV or Excel data, summarize data, or answer questions about tabular data.

Original author description

Analyze spreadsheet data, generate insights, and create visualizations. Use when a user asks to analyze data, explore a dataset, find trends, generate statistics, create charts from CSV or Excel data, summarize data, or answer questions about tabular data.

How it works

  1. Overview
  2. Instructions
  3. Examples
  4. Guidelines
Original SKILL.md headings · 196 lines, 894 words
SKILL.md preview
---
name: data-analysis
description: >-
  Analyze spreadsheet data, generate insights, and create visualizations.
  Use when a user asks to analyze data, explore a dataset, find trends,
  generate statistics, create charts from CSV or Excel data, summarize
  data, or answer questions about tabular data.
license: Apache-2.0
compatibility: "Requires Python 3.11+ (pandas 3.x) with pandas, matplotlib, seaborn; openpyxl for Excel files"
metadata:
  author: terminal-skills
  version: "1.1.0"
  repository: https://github.com/pandas-dev/pandas
  category: data-ai
  tags: "data-analysis, pandas, visualization, statistics, csv"
  use-cases: "Analyze a CSV or Excel file and generate summary statistics, Create charts and visualizations from tabular data, Answer specific questions about patterns and trends in datasets"
  agents: "claude-code, openai-codex, gemini-cli, cursor"
---

# Data Analysis

## Overview

Analyze tabular data from CSV, Excel, or other structured formats. Generate summary statistics, discover patterns, answer specific questions, and produce visualizations. Uses Python with pandas for data manipulation and matplotlib/seaborn for charts.

## Instructions

When a user asks you to analyze data, follow this process:

### Step 1: Verify dependencies

Ensure required Python packages are available (pandas 3.x needs Python 3.11+; on older pandas 2.x use `'ME'` only from 2.2 on):

```bash
python3 -c "import pandas; import matplotlib; import seaborn; print('All packages available')" 2>/dev/null || \
  pip install pandas matplotlib seaborn openpyxl
  # For reproducible, supply-chain-safe installs, pin exact versions in requirements.txt
  # (e.g. pandas==3.0.6) and install with `pip install -r requirements.txt`.
```

### Step 2: Load and inspect the data

Read the file and understand its structure:

```python
import pandas as pd

# Load the data (auto-detect format)
df = pd.read_csv("data.csv")        # For CSV
# df = pd.read_excel("data.xlsx")   # For Excel
# df = pd.read_json("data.json")    # For JSON

# Initial inspection
print(f"Shape: {df.shape[0]} rows x {df.shape[1]} columns")
print(f"\nColumns: {list(df.columns)}")
print(f"\nData types:\n{df.dtypes}")
print(f"\nFirst 5 rows:\n{df.head()}")
print(f"\nMissing values:\n{df.isnull().sum()}")
```

Report the dataset structure to the user before proceeding:
- Number of rows and columns
- Column names and data types
- Missing value counts
- Any obvious data quality issues

### Step 3: Generate summary statistics

```python
# Numeric summary
print(df.describe())

# Categorical summary (pandas 3 stores text as the "str" dtype, so "object" alone misses it)
for col in df.select_dtypes(include=['object', 'string']).columns:
    print(f"\n{col} - unique values: {df[col].nunique()}")
    print(df[col].value_counts().head(10))

# Correlations between numeric columns
print(df.select_dtypes(include='number').corr())
```

### Step 4: Answer specific questions or explore patterns

Based on the user's request, perform targeted analysis:

**Filtering and aggregation:**

```python
# Group by category and compute stats
summary = df.groupby('category').agg(
    count=('id', 'count'),
    avg_value=('value', 'mean'),
    total=('value', 'sum')
).sort_values('total', ascending=False)
```

**Time series analysis:**

```python
df['date'] = pd.to_datetime(df['date'])
# 'ME' = month end; the old 'M' alias raises an error in pandas 3
monthly = df.resample('ME', on='date').agg({'revenue': 'sum', 'orders': 'count'})
```

**Outlier detection:**

```python
Q1 = df['value'].quantile(0.25)
Q3 = df['value'].quantile(0.75)
IQR = Q3 - Q1
outliers = df[(df['value'] < Q1 - 1.5*IQR) | (df['value'] > Q3 + 1.5*IQR)]
print(f"Found {len(outliers)} outliers")
```

### Step 5: Create visualizations

Save charts as image files:

```python
import matplotlib.pyplot as plt
import seaborn as sns

plt.style.use('seaborn-v0_8-darkgrid')
fig, ax = plt.subplots(figsize=(10, 6))

# Bar chart
df.groupby('category')['revenue'].sum().plot(kind='bar', ax=ax)
ax.set_title('Revenue by Category')
ax.set_ylabel('Revenue ($)')
plt.tight_layout()
plt.savefig('chart_revenue_by_category.png', dpi=150)
plt.close()

# Line chart for trends
fig, ax = plt.subplots(figsize=(10, 6))
monthly['revenue'].plot(ax=ax)
ax.set_title('Monthly Revenue Trend')
plt.tight_layout()
plt.savefig('chart_monthly_trend.png', dpi=150)
plt.close()

# Correlation heatmap
fig, ax = plt.subplots(figsize=(8, 6))
sns.heatmap(df.select_dtypes(include='number').corr(), annot=True, cmap='coolwarm', ax=ax)
plt.tight_layout()
plt.savefig('chart_correlation.png', dpi=150)
plt.close()
```

### Step 6: Present findings

Summarize the analysis with:
- Key statistics (totals, averages, medians)
- Notable patterns or trends discovered
- Outliers or anomalies
- Visualizations with descriptions
- Actionable insights or recommendations

## Examples

### Example 1: Analyze sales data

**User request:** "Analyze this sales CSV and tell me what's trending"

**Actions:**

1. Load `sales.csv` and inspect (columns: date, product, category, quantity, price, region)
2. Compute total revenue (quantity * price), group by month
3. Identify top products and categories by revenue
4. Detect growth trends by comparing recent months to prior months
5. Create a monthly revenue trend line chart and a category breakdown bar chart

**Output:** "Sales totaled $2.4M over 12 months. Revenue grew 15% quarter-over-quarter. Electronics is the top category (42% of revenue). The Southwest region underperforms at 8% of total sales despite covering 20% of stores. See the attached charts for trends."

### Example 2: Compare two datasets

**User request:** "Compare last year's performance to this year"

**Actions:**

1. Load both CSV files
2. Align on common columns (date, metric)
3. Compute year-over-year changes for key metrics
4. Highlight improvements and regressions
5. Create a side-by-side comparison chart

**Output:** A comparison table showing each metric with last year vs. this year values, percentage change, and a trend indicator.

### Example 3: Find anomalies in log data

**User request:** "Are there any anomalies in this server metrics CSV?"

**Actions:**

1. Load metrics data (timestamp, cpu_usage, memory, response_time, error_rate)
2. Compute rolling averages and standard deviations
3. Flag data points beyond 2 standard deviations
4. Correlate anomalies across metrics (did CPU spike with errors?)
5. Plot a timeline highlighting anomaly windows

**Output:** "Found 3 anomaly windows: Jan 15 2-4pm (CPU 95%, errors 12x normal), Feb 3 11am (memory spike to 98%), Mar 20 all day (elevated response times). The Jan 15 event correlates with a deployment at 1:55pm."

## Guidelines

- Always inspect the data before analyzing. Report shape, types, and quality to the user.
- Handle missing values explicitly: report them, then decide whether to drop or fill.
- Use appropriate chart types: line for trends, bar for categories, scatter for correlations, heatmap for matrices.
- In scripts and CI run with a non-interactive backend (`matplotlib.use("Agg")` before importing pyplot) so `savefig` works without a display.
- Save all charts as PNG files with descriptive filenames and 150 DPI for readability.
- Present numbers with context: "Revenue is $1.2M" is less useful than "Revenue is $1.2M, up 15% from last quarter."
- For large datasets (100K+ rows), work with samples or aggregations to avoid slow operations.
- Always label chart axes, add titles, and use readable fonts.
- When the user's question is vague ("analyze this"), provide a comprehensive overview covering distribution, trends, correlations, and outliers.
Files in this package (2)
  • SKILL.md 7 KB
  • _scores.json 2 KB

Versions

RepositoryScoreLicence
This page · TerminalSkills/skills98Apache-2.0
DomynAI/domyn-agents100Apache-2.0
bytedance/deer-flow100MIT
quantummetric/qm-plugin-skills100MIT
Sellyew/Workbuddy-workflow100MIT
DougTrajano/pydantic-ai-skills100MIT
microclaw/microclaw100MIT
lynricsy/hyperskills100MIT
DvJ4Y/shipwright100MIT

Database snapshot: 13.11.2026 · package version f29982673a90 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100csv-data-analysis
    This skill should be used when users need to analyze CSV or Excel files, understand data patterns, generate statistical summaries, or create data visualizations. Trigger keywords include "analyze CSV", "analyze Excel", "data analysis", "CSV analysis", "Excel analysis", "data…
  • 100spreadsheet-ops
    Spreadsheet processing and analysis for CSV/Excel; trigger when users ask to merge/clean tabular data, run statistics, add/edit Excel formulas, apply formatting, generate charts, or force workbook recalculation.
  • 90data-analyst
    Analyze a CSV, Excel/Google Sheets export or pasted table. Use when the user shares data and asks for insights, totals, averages, trends, "what does this data say", comparisons between groups, or a chart.
  • 100data-analyst
    Cleans, analyzes and visualizes data from CSV, Excel or JSON files and explains the findings in plain language. Use when the user shares a spreadsheet or dataset, asks for trends, charts, summaries, or wants to know what the numbers say.
  • 100excel-analysis
    Analyze Excel spreadsheets, create pivot tables, generate charts, and perform data analysis. Use when analyzing Excel files, spreadsheets, tabular data, or .xlsx files.
  • 100data-analyst
    Use when analysing data files (CSV, JSON, Excel), writing SQL queries, identifying trends and patterns, building dashboards or charts, summarising metrics, validating data quality, or turning raw data into actionable insights for decision-making.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.