BI Data Quality Investigator
Trace, quantify, and fix data quality issues systematically
What You Can Do
You'll systematically diagnose data quality problems by developing structured root cause analysis frameworks, calculating the true business impact, and creating reproducible validation tests. This skill walks you through hypothesis-driven investigation, data lineage analysis, and remediation planning — turning data issues into documented fixes and preventive measures.
Features
Structured methodology to trace issues from symptom to source with competing hypotheses
Calculate downstream effects and business cost of data quality problems
Create SQL/Python tests that verify fixes and prevent regression
Track data flow across pipelines to identify contamination points
Generate metrics-based health reports by source, table, and dimension
Systematically test competing root causes with evidence
Document fix procedures, verification steps, and stakeholder communication
Example Output
Investigation Summary
- Issue: Revenue dashboard shows $500K discrepancy vs. GL records
- Root cause: Timezone conversion error in ETL pipeline (UTC vs. EST)
- Impact: $500K in unreconciled transactions affecting monthly close
- Validation test: SQL query comparing GL dates before/after conversion
Remediation Playbook
- Apply timezone fix to ETL transformation
- Backfill affected 90-day period using validation query
- Deploy updated pipeline with regression test
- Monitor dashboard reconciliation daily for 2 weeks
Quality Scorecard
| Data Source | Completeness | Timeliness | Accuracy |
|---|---|---|---|
| Billing API | 99.8% | 2h lag | 99.2% |
| GL Extract | 100% | 24h lag | 99.9% |
What's Included
- SKILL.md: Core investigation framework with decision trees and templates
- Root cause analysis template: Structured worksheet for tracing issues
- Data quality validation checklist: Questions to verify each hypothesis
- Impact assessment worksheet: Calculate affected records and business cost
- SQL/Python validation script templates: Ready-to-run quality tests
- Investigation report template: Stakeholder-ready documentation
Who It's For
- Data engineers — Investigating pipeline failures and data contamination
- BI analysts — Troubleshooting dashboard inconsistencies and metric discrepancies
- Data quality managers — Conducting audits and compliance validations
- Analytics leads — Assessing data reliability for critical decision-making
- Database administrators — Investigating data corruption or sync issues
Best For
- Diagnosing unexplained metric discrepancies between systems
- Creating proactive data quality testing frameworks
- Quantifying business impact of data issues for stakeholders
- Building data governance standards and quality SLAs
- Training teams on systematic root cause investigation
You might also like
You can build production-grade vector search systems that retrieve semantically similar documents in sub-millisecond time using AgentDB's optimized HNSW indexing. The skill enables you to implement RAG pipelines, semantic search engines, and intelligent knowledge bases with configurable embedding dimensions, distance metrics (cosine, Euclidean, dot product), and similarity thresholds—all with built-in quantization and caching for massive performance gains.
by moonwell-fi
You'll build comprehensive data quality test suites that validate transformations, detect anomalies, and document standards across your dbt and SQL pipelines. This skill generates production-ready test configurations, anomaly detection protocols, and validation rules that catch data issues before they impact analytics.
by moonwell-fi
You can design multi-dimensional evaluation strategies tailored to your model's specific capabilities and use cases, create representative test sets that expose edge cases and failure modes, implement automated scoring mechanisms for reproducible results, and generate benchmark comparison reports that contextualize performance within industry standards. This skill transforms ad-hoc testing into systematic, evidence-based model assessment—essential for production deployment decisions and ongoing performance monitoring.
by moonwell-fi
You can convert complex datasets and business metrics into polished, executive-ready reports that stakeholders trust and act on. Claude generates data-driven narratives, executive summaries, actionable insights, and visualization recommendations tailored to your audience's priorities. Your reports will tell a cohesive story that connects metrics to business outcomes, eliminating confusion and accelerating decision-making.
by moonwell-fi
This skill walks you through the complete dataset preparation workflow for fine-tuning Claude models. You'll validate training data quality, detect and fix formatting errors, identify data imbalances, and generate validation reports to ensure your fine-tuned model performs reliably in production.
by moonwell-fi
This skill provides a systematic framework for preparing training data, benchmarking model performance, identifying deployment risks, and calculating true ROI before committing fine-tuning investments. You'll validate datasets, run structured evaluations against baseline Claude models, test edge cases, and iterate toward production-ready fine-tuned versions. The framework ensures your fine-tuned models deliver meaningful improvements while maintaining safety and cost-effectiveness.
by moonwell-fi
Diagnose root causes of model performance failures, select optimal evaluation metrics based on your use case and data characteristics, and design comprehensive evaluation strategies. You'll get systematic workflows for analyzing failure modes, statistical significance testing, threshold optimization, and cross-validation planning—turning vague model problems into actionable fixes.
by moonwell-fi
You can search Wikidata using four complementary methods: keyword search via the Action API for label-based lookups, semantic/hybrid search through the Vector Database for fuzzy concept matching, direct entity retrieval via Special:EntityData for instant JSON data, and SPARQL queries through WDQS for complex graph relationships and reporting. Each method is optimized for different use cases—from quick entity lookups to multi-table data analysis across millions of linked facts.
by diegosouzapw