Data validation

Skill Pratiyush/agent-catalog/skills/skill/data-validation

Marketplace for AI Agent Skills, Prompts, Agents, and MCP servers. Powered by @skillscraft.

Install

npx -y skills add Pratiyush/agent-catalog --skill data-validation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Validate CSV and JSON data files against schemas and quality rules. Use when the user asks to check data quality, validate a dataset, or verify file contents match an expected schema.

The file declares its own license as Apache-2.0. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.8 KB, as published. Nobody here has run it

Data Validation

When to use this skill

Activate when the user wants to:

Check a CSV file for missing headers, type mismatches, or duplicates
Validate JSON against a schema
Run data quality checks before a pipeline or import

Instructions

Identify the file type (CSV or JSON) from the user's request

For CSV files, run:

uv run scripts/validate_csv.py <file-path>

For JSON files, run:
```
uv run scripts/validate_json.py <file-path> --schema <schema-path>
```
Omit --schema if no schema is provided — the script checks structural integrity only.
Parse the JSON output from stdout
Report findings grouped by severity: errors first, then warnings

Output format

Both scripts output JSON to stdout:

{
  "file": "data.csv",
  "valid": false,
  "errors": [
    { "line": 3, "column": "age", "message": "Expected integer, got 'abc'" }
  ],
  "warnings": [
    { "line": 7, "column": "email", "message": "Empty value" }
  ],
  "summary": { "rows": 100, "errors": 1, "warnings": 1 }
}

Gotchas

Python 3.11+ is required — scripts use tomllib and modern type hints
Use uv run (not pip install) to execute scripts with inline dependencies
CSV files must have a header row — headerless files are rejected
JSON schema validation uses JSON Schema draft-07
For custom schema formats, read references/SCHEMA-GUIDE.md