Claude Skill

data-quality-agent

Detect duplicates, missing values, schema drift, and inconsistencies across datasets. Use before migrations, reporting, or model training.

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download navinspire-ia-navin-navin_skills_data-quality-agent-e9c73a3.zip · 0 KB

navinspire-ia/navin 31 4 forks AGPL-3.0 Updated 4d ago

Part of navinspire-ia/navin — 182 skills

Install

skills CLI npx skills add https://github.com/Navinspire-ia/navin/tree/main/navin/skills/data-quality-agent

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install navinspire-ia-navin@llmmart

Git git clone https://github.com/Navinspire-ia/navin.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole navinspire-ia/navin collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Data Quality Agent

Overview

Profile first, fix second. Quantify issues.

Checks

Null rates / required fields
Duplicate business keys
Type / format violations
Referential integrity orphans
Distribution spikes / drift vs baseline

Leads studio CSV (when applicable)

For sales/prospects-*.csv also verify:

Required columns: company, website, source, confidence
Valid website URLs; prefer source URLs over free-text when claiming public evidence
No duplicate domains; confidence in {high, medium, low, unverified}
No email marked verified without enrichment proof
Prefer running lead-qualification/scripts/score_leads.py --validate-only then full score

Workflow

Identify datasets and grain (what is one row).
Profile columns; compute issue counts.
Prioritize by blast radius (joins, finance, PII, outbound lists).
Propose remediations; apply only with approval on prod data.
Leave a short DQ report with metrics.

Files (navin)

SKILL.md 1.2 KB

---
name: data-quality-agent
description: Detect duplicates, missing values, schema drift, and inconsistencies across datasets. Use before migrations, reporting, or model training.
metadata: {"navin":{"emoji":"🧹","category":"data"}}
---

# Data Quality Agent

## Overview

Profile first, fix second. Quantify issues.

## Checks

- Null rates / required fields
- Duplicate business keys
- Type / format violations
- Referential integrity orphans
- Distribution spikes / drift vs baseline

## Leads studio CSV (when applicable)

For `sales/prospects-*.csv` also verify:

- Required columns: company, website, source, confidence
- Valid website URLs; prefer source URLs over free-text when claiming public evidence
- No duplicate domains; confidence in {high, medium, low, unverified}
- No email marked verified without enrichment proof
- Prefer running `lead-qualification/scripts/score_leads.py --validate-only` then full score

## Workflow

1. Identify datasets and grain (what is one row).
2. Profile columns; compute issue counts.
3. Prioritize by blast radius (joins, finance, PII, outbound lists).
4. Propose remediations; apply only with approval on prod data.
5. Leave a short DQ report with metrics.