# Csv Analyzer

> Analyze CSV and Excel files — statistics, filtering, grouping, and data previews. Use when: user asks to read, analyze, query, summarize, or explore tabular data in CSV, TSV, or Excel files. NOT for: database queries, writing new files, or non-tabular formats.

- **Type:** Skill
- **Install:** `agentstack add skill-ericwang915-pythonclaw-csv-analyzer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ericwang915](https://agentstack.voostack.com/s/ericwang915)
- **Installs:** 0
- **Category:** [Databases](https://agentstack.voostack.com/c/databases)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ericwang915](https://github.com/ericwang915)
- **Source:** https://github.com/ericwang915/PythonClaw/tree/main/pythonclaw/templates/skills/data/csv_analyzer
- **Website:** https://github.com/ericwang915/PythonClaw

## Install

```sh
agentstack add skill-ericwang915-pythonclaw-csv-analyzer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# CSV Analyzer Skill

Analyze tabular data files (CSV, TSV, Excel) using pandas.

## When to Use

✅ **USE this skill when:**
- "Show me what's in data.csv"
- "First 20 rows of sales.xlsx"
- "Statistics for revenue column"
- "Filter rows where age > 30"
- "Average sales by region"
- User wants to explore, summarize, filter, or aggregate tabular data

## When NOT to Use

❌ **DON'T use this skill when:**
- Database queries (SQL) → use database tools
- Writing new CSV/Excel files → use code or spreadsheet tools
- Non-tabular formats (JSON, XML, etc.) → use appropriate parsers

## Usage/Commands

```bash
python {skill_path}/analyze.py PATH [command] [options]
```

Commands:
- `info` (default) — column types, shape, missing values
- `head` — first N rows (default 10)
- `stats` — descriptive statistics for numeric columns
- `query` — filter rows with a pandas query expression
- `groupby` — group-by aggregation
- `columns` — list column names and types

Options:
- `--rows N` — number of rows for head (default 10)
- `--query "col > 100"` — pandas query expression
- `--groupby COL` — column to group by
- `--agg mean|sum|count|min|max` — aggregation function (default: mean)
- `--format json` — output as JSON
- `--columns "col1,col2"` — select specific columns

### Examples

- "Show me what's in data.csv" → `python {skill_path}/analyze.py data.csv info`
- "First 20 rows of sales.xlsx" → `python {skill_path}/analyze.py sales.xlsx head --rows 20`
- "Average sales by region" → `python {skill_path}/analyze.py data.csv groupby --groupby region --columns sales --agg mean`

## Notes

- Install dependencies: `pip install pandas openpyxl`
- openpyxl required for Excel (.xlsx) support

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ericwang915](https://github.com/ericwang915)
- **Source:** [ericwang915/PythonClaw](https://github.com/ericwang915/PythonClaw)
- **License:** MIT
- **Homepage:** https://github.com/ericwang915/PythonClaw

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ericwang915-pythonclaw-csv-analyzer
- Seller: https://agentstack.voostack.com/s/ericwang915
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.