# Data Analysis

> Analyze data using Python with pandas, matplotlib, and numpy.

- **Type:** Skill
- **Install:** `agentstack add skill-yujiachen-y-agent-bundle-data-analysis`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [yujiachen-y](https://agentstack.voostack.com/s/yujiachen-y)
- **Installs:** 0
- **Category:** [Cloud & Infrastructure](https://agentstack.voostack.com/c/cloud-infrastructure)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [yujiachen-y](https://github.com/yujiachen-y)
- **Source:** https://github.com/yujiachen-y/agent-bundle/tree/main/demo/data-analyst-e2b/skills/data-analysis
- **Website:** https://agent-bundle.com/

## Install

```sh
agentstack add skill-yujiachen-y-agent-bundle-data-analysis
```

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

## About

# Data Analysis

You are given a data analysis task by the user. Follow these steps:

1. **Write** a Python script to `/workspace/analysis.py` that:
   - Creates or reads the data as described by the user
   - Performs the requested analysis using pandas/numpy
   - Prints summary statistics to stdout
   - Saves any charts to `/workspace/chart.png` using matplotlib (use `savefig`, not `show`)

2. **Run** the script in the sandbox using Bash:
   ```
   cd /workspace && python3 analysis.py
   ```

3. **Read** the Bash output to get the printed results.

4. Return a clear summary of the findings, referencing any generated files.

Rules:

- Always use `/workspace/` as the working directory.
- Use `matplotlib.use('Agg')` before importing pyplot (no display server).
- Save figures with `plt.savefig('/workspace/chart.png', dpi=100, bbox_inches='tight')`.
- If the user provides CSV data inline, write it to `/workspace/data.csv` first.
- If the Bash command fails, return the error output and suggest fixes.

## Source & license

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

- **Author:** [yujiachen-y](https://github.com/yujiachen-y)
- **Source:** [yujiachen-y/agent-bundle](https://github.com/yujiachen-y/agent-bundle)
- **License:** MIT
- **Homepage:** https://agent-bundle.com/

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-yujiachen-y-agent-bundle-data-analysis
- Seller: https://agentstack.voostack.com/s/yujiachen-y
- 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%.