# Skill 008

> A robust tool for cleaning, standardizing, and preparing CSV data files for analysis. Ideal for ensuring accuracy in datasets before use in reports or financial models.

- **Type:** Skill
- **Install:** `agentstack add skill-legendtkl-agentic-skill-router-skill-008`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [legendtkl](https://agentstack.voostack.com/s/legendtkl)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [legendtkl](https://github.com/legendtkl)
- **Source:** https://github.com/legendtkl/agentic-skill-router/tree/main/experiments/dci-compare/skillrouter-skills/skill-008
- **Website:** https://legendtkl.github.io/agentic-skill-router/

## Install

```sh
agentstack add skill-legendtkl-agentic-skill-router-skill-008
```

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

## About

# Requirements for Outputs

## General CSV File Handling

### Cleanliness Standards
- All CSV files must be delivered free of duplicate entries and with consistent formatting.
- Ensure all string values are trimmed of whitespace and standardize case (e.g., all lowercase).

### Standardization Rules
- Dates should be formatted to YYYY-MM-DD.
- Numerical values should not contain commas or currency symbols.
- Replace any missing values with "N/A" or appropriate placeholders.

## Data Cleaning Techniques

### Deduplication
- Implement algorithms to detect and remove duplicate rows based on key columns.
- Example code snippet:
```python
import pandas as pd

def remove_duplicates(file_path):
    df = pd.read_csv(file_path)
    df_cleaned = df.drop_duplicates()
    return df_cleaned
```

### Formatting Strings
- Normalize string values by removing leading or trailing whitespace and converting to lowercase before analysis.
- Example code snippet:
```python
def format_strings(df):
    df['column_name'] = df['column_name'].str.strip().str.lower()
    return df
```

### Handling Missing Data
- Replace missing values with specified placeholders or use interpolation if appropriate.
- Example code snippet:
```python
def handle_missing_data(df):
    df.fillna('N/A', inplace=True)
    return df
```

## Documentation Requirements

### Data Source Citation
- Ensure all cleaned data is accompanied by a citation of the original data source: "Source: [System/Document], [Date], [Specific Reference]."

### Change Log
- Maintain a change log documenting any alterations made during the cleaning process, including date and reason for changes.

## Source & license

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

- **Author:** [legendtkl](https://github.com/legendtkl)
- **Source:** [legendtkl/agentic-skill-router](https://github.com/legendtkl/agentic-skill-router)
- **License:** MIT
- **Homepage:** https://legendtkl.github.io/agentic-skill-router/

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-legendtkl-agentic-skill-router-skill-008
- Seller: https://agentstack.voostack.com/s/legendtkl
- 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%.