Open Data Investigation Analyst
Uncover hidden stories in open datasets with rapid pattern analysis
What You Can Do
Analyze open datasets at scale to surface newsworthy patterns, validate data quality, and generate structured findings. You'll identify anomalies, correlations, and trends that often go unnoticed, then transform raw numbers into compelling narratives backed by rigorous analysis.
Features
Rapidly scan datasets to identify statistically significant patterns, correlations, and outliers that may signal important stories
Validate dataset integrity, flag missing values, inconsistencies, and potential data entry errors before analysis
Transform findings into structured data stories with clear headlines, supporting evidence, and implications
Process CSV, JSON, Excel, and other structured formats; handles messy real-world data cleaning automatically
Verify that claims are statistically sound, calculate confidence levels, and flag overreaching conclusions
Pinpoint unusual data points that warrant investigation or represent potential story angles
Maintain clear citations to original data sources and government agencies; verify dataset provenance
Generate structured reports with visualizable metrics, methodology notes, and data download links
Example Output
Analysis Report: Housing Affordability Crisis Accelerating
Finding: Median rent-to-income ratio exceeded 35% in 247 US counties for the first time in 5 years (HUD open dataset, 2025).
Pattern Identified: Fastest growth in tier-2 cities (Austin +18%, Raleigh +16%) previously known for affordability.
Data Quality: 3 counties excluded due to incomplete reporting; methodology note included.
Story Angle: "The Affordability Paradox: Why Tech Hubs Are Pricing Out Their Own Workers"
Second Example: Environmental Violations Spike Before Inspections
Analyzing EPA enforcement data reveals facilities report 42% MORE violations after regulatory announcements. Statistical confidence: 94%. Hypothesis: increased reporting vs. actual behavior change pending further investigation.
What's Included
- Dataset Analysis Framework: Structured workflow for ingesting, cleaning, exploring, and validating public datasets
- Data Validation Checklist: Comprehensive quality checks: missing data, duplicates, outliers, format inconsistencies, temporal gaps
- Story Structure Template: Proven narrative format for data journalism: finding → evidence → implications → next steps
- Statistical Methods Guide: Reference for appropriate tests, confidence intervals, and significance thresholds for different data types
- Findings Report Generator: Markdown-based template that auto-generates formatted reports with sources, methodology, and caveats
- Public Data Source Directory: Curated list of vetted open datasets (government, NGO, academic) organized by topic and quality
Who It's For
- Data Journalists
- Investigative Reporters
- Policy Researchers & Analysts
- NGO & Nonprofit Program Officers
- Academic Researchers
Best For
- Discovering newsworthy trends in government datasets
- Validating data integrity before publication
- Structuring raw data findings into narrative stories
- Identifying anomalies that warrant deeper investigation
- Building databases of multi-year patterns for longitudinal analysis
You might also like
You can instantly generate engaging captions, story arcs, and pitch-ready copy for your sports photography. Whether you're covering a championship game, developing a photo essay series, or submitting work to media outlets, this skill crafts deadline-ready narratives that showcase your images and hook editors. Transform raw photos into publication-quality coverage with professional storytelling that brings readers into the defining moments of athletic competition.
by manwithstyle
You can design comprehensive Datadog monitoring strategies that transform raw metrics into actionable intelligence. Claude helps you architect dashboards that surface critical insights, configure intelligent alerts that reduce false positives, and build escalation workflows that speed up incident response. The result: measurably lower MTTR and a team that trusts your alerts.
by manwithstyle
You can transform complex datasets into compelling interactive narratives that maintain coherence while inviting exploration. This skill helps you architect data-driven stories where insights unfold naturally through guided discovery points, keeping readers engaged without limiting their agency. Readers navigate your narrative with purpose, uncovering patterns and relationships that would remain hidden in static presentations.
by manwithstyle
Transform breaking news briefs into compelling visual story frameworks that guide photographers toward impactful coverage. You'll receive multiple narrative angles, detailed shot lists organized by scene and purpose, and complete assignment briefs with sourcing guidance. Each output ensures comprehensive emotional and contextual storytelling from first frame to final edit.
by manwithstyle
Analyze Docker container logs instantly to identify root causes of failures, crashes, and resource bottlenecks. Get actionable recommendations for resource allocation, network configuration, and architectural improvements that eliminate production issues before they cascade.
by manwithstyle
Systematically analyze your AWS accounts to identify cost optimization opportunities, security gaps, and performance bottlenecks. You'll receive prioritized, actionable recommendations tailored to your architecture, from EC2 right-sizing to unused resource cleanup and security hardening.
by manwithstyle
This skill walks you through a structured data analysis workflow—from initial exploration and claim verification to identifying compelling story angles and building evidence-backed narratives. You'll learn to spot anomalies, validate statistics, and construct defensible arguments that stand up to scrutiny. It's designed for journalists who want to move beyond surface-level data work into serious investigative storytelling.
by manwithstyle
Accelerate your beat reporting by organizing research, identifying story angles, discovering sources, and developing narrative frameworks. You can quickly synthesize complex topics, spot emerging trends, and prepare comprehensive story outlines that anchor your reporting. This skill helps you go deeper on your beat with less time spent on research logistics.
by manwithstyle