skills.rest
cyyeh
cyyehCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

data-validation

Validate data analyses for methodological errors, bias, and reproducibility gaps.

1|Updated Feb 19, 2026
Search Tags:#qa#data quality#data validation#bias detection#reproducibility#analysis review#sanity checks
One-click install
npx skills add https://github.com/cyyeh/duckdb-data-agent --skill data-validation-cyyeh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-validation
Source: https://github.com/cyyeh/duckdb-data-agent/tree/main/plugins/data/skills/data-validation
Command: npx skills add https://github.com/cyyeh/duckdb-data-agent --skill data-validation-cyyeh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a structured pre-delivery QA workflow to find methodological errors, calculation mistakes, and biases in data analyses so stakeholders receive accurate, reproducible results.

Core Features & Use Cases

  • Pre-delivery checklist: Step-by-step checks for source verification, freshness, completeness, null handling, deduplication, and filter validation.
  • Calculation and join validation: Guidance to verify aggregation logic, denominators, date alignment, and correct join types to prevent inflated or incorrect metrics.
  • Reasonableness and sanity checks: Magnitude, trend continuity, cross-references, and red-flag detection to spot implausible results.
  • Reproducibility templates: Documentation and code doc examples to ensure others can recreate the analysis and understand assumptions and limitations.
  • Use cases: QA SQL reports before distribution, validate dashboards and KPIs, detect survivorship or selection bias in cohorts.

Quick Start

Ask the agent to run the pre-delivery QA checklist on my analysis, verify joins and aggregations, and produce a reproducibility note with any issues found.

Frequently Asked Questions about data-validation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I detect survivorship and selection bias in cohort analyses?▼

To validate SQL reports and dashboards, apply a structured pre-delivery QA checklist that verifies source freshness, null handling, aggregation logic, denominators, and join types to prevent inflated or incorrect metrics.

How do I ensure reproducibility in my data analysis and SQL queries?▼

Sanity checks on aggregated data involve verifying magnitude, trend continuity, cross-referencing metrics, and detecting red flags to spot implausible results before releasing analyses to stakeholders.

What inputs do I need to provide to validate data analyses and perform QA reviews?▼

Yes, you can validate calculation and join logic by verifying aggregation formulas, checking date alignment, and confirming correct join types to catch calculation and aggregation mistakes in data analyses.

How do I document data analysis assumptions and limitations for reproducibility?▼

Data validation QA reviews require access to query text, sample records or table schemas, and summary metrics to effectively check joins, denominators, and perform sanity validations.

Related Skills

Explore More Data & Analytics Skills→
kevinnguyen271090kevinnguyen271090
15

databases

Design and optimize MongoDB and PostgreSQL databases for schema, queries, and performance.

Community
Intermediate
mheersmheers

showboat

Generate demo.md files interleaving notes, executable code blocks, and captured outputs.

Community
Intermediate
davekim917davekim917
1

analytics

Analyze dashboards, metrics, and BI artifacts for clarity and accuracy.

Community
Advanced
tonone-aitonone-ai
69

flux-health

Detect data quality issues and pipeline health across databases and warehouses.

Official
Intermediate