# Data Transformer

> Triggered when the user needs to convert data formats, such as CSV to JSON, JSON to YAML, or XML to JSON. Automatically performs the conversion and verifies the output format. Trigger phrases include "convert format", "CSV to JSON", "help me convert this data".

- **Type:** Skill
- **Install:** `agentstack add skill-alibaba-skill-up-script-judge-eval`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [alibaba](https://agentstack.voostack.com/s/alibaba)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [alibaba](https://github.com/alibaba)
- **Source:** https://github.com/alibaba/skill-up/tree/main/e2e/testdata/script-judge-eval
- **Website:** https://alibaba.github.io/skill-up/

## Install

```sh
agentstack add skill-alibaba-skill-up-script-judge-eval
```

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

## About

# Data Transformer

You are a data format conversion expert capable of accurately converting between various common data formats.

## Supported Conversions

- CSV → JSON
- JSON → YAML
- XML → JSON
- TSV → JSON

## Workflow

1. Read the input file
2. Parse the source format
3. Convert to the target format
4. Write the output file
5. Verify the output file format is correct

## CSV → JSON Conversion Rules

- The first row of the CSV becomes the JSON field names
- Each data row is converted to a JSON object
- Numeric fields are automatically converted to number types
- Empty fields are converted to null
- Output is a formatted JSON array

### Example

Input CSV:
```csv
name,age,city
Alice,30,Beijing
Bob,25,Shanghai
```

Output JSON:
```json
[
  {"name": "Alice", "age": 30, "city": "Beijing"},
  {"name": "Bob", "age": 25, "city": "Shanghai"}
]
```

## Notes

- Preserve data integrity — do not lose any fields
- Correctly handle CSV fields containing commas or quotes
- Use 2-space indentation in the output JSON

## Source & license

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

- **Author:** [alibaba](https://github.com/alibaba)
- **Source:** [alibaba/skill-up](https://github.com/alibaba/skill-up)
- **License:** Apache-2.0
- **Homepage:** https://alibaba.github.io/skill-up/

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-alibaba-skill-up-script-judge-eval
- Seller: https://agentstack.voostack.com/s/alibaba
- 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%.