<< All versions
Skill v1.0.1
currentAutomated scan100/100chrispangg/deepagentsdk/data-analysis
4 files
──Details
PublishedSeptember 29, 2026 at 09:02 PM
Content Hashsha256:97aad0740873e95e...
Git SHAfeaaa05ef7de
Bump Typepatch
──Files
Files (1 file, 2.1 KB)
SKILL.md2.1 KBactive
SKILL.md · 99 lines · 2.1 KB
version: "1.0.1" name: data-analysis description: Analyze CSV and tabular data, create summaries, and generate insights
Data Analysis Skill
This skill provides step-by-step workflows for analyzing tabular data (CSV, TSV, etc.).
When to Use This Skill
Use this skill when the user:
- Wants to analyze CSV or tabular data
- Needs data summaries or statistics
- Asks for insights from datasets
- Wants to parse structured data files
Workflow
1. Understand the Data Source
First, determine where the data is:
- Is it in a file? Get the file path
- Is it provided inline? Store it in the filesystem first
- Does it need to be fetched? Use appropriate tools
2. Read and Parse the Data
Use read_file to load the data. Look for:
- Column headers (first row usually)
- Data types in each column
- Missing or null values
- Data format (CSV, TSV, etc.)
3. Analyze the Data
Perform these analyses based on user needs:
Basic Statistics:
- Row count
- Column count
- Value ranges (min, max)
- Missing value counts
Data Quality:
- Check for duplicates
- Identify anomalies
- Validate data types
Insights:
- Trends or patterns
- Correlations
- Key findings
4. Create Summary Report
Structure your summary as:
# Data Analysis Report## Dataset Overview- Rows: [count]- Columns: [count]- Columns: [list]## Key Statistics[Relevant statistics based on data type]## Data Quality[Any issues found]## Insights[Key findings and patterns]## Recommendations[Suggested next steps]
Example
User request: "Analyze this sales data: sales.csv"
Your approach:
- Read sales.csv using read_file
- Parse the CSV structure (headers, data types)
- Calculate: total sales, average order value, top products
- Check for: missing data, date ranges, outliers
- Generate summary report with insights
Best Practices
- Always validate data before analysis
- Handle missing values gracefully
- Provide context for statistics (what do they mean?)
- Suggest visualizations when appropriate
- Ask clarifying questions if data structure is unclear