Identify non-obvious signals, hidden patterns, and clever correlations in datasets using investigative data analysis techniques. Use when analyzing social media exports, user data, behavioral datasets, or any structured data where deeper insights are desired. Pairs with personality-profiler for enhanced signal extraction. Triggers on requests like "what patterns do you see", "find hidden signals", "correlate these datasets", "what am I missing in this data", "analyze across datasets", "find non-obvious insights", or when users want to go beyond surface-level analysis. Also use proactively when you notice interesting anomalies or correlations during any data analysis task.
View on GitHubskills/data-sleuth/SKILL.md
February 5, 2026
Select agents to install to:
npx add-skill https://github.com/petekp/agent-skills/blob/main/skills/data-sleuth/SKILL.md -a claude-code --skill data-sleuthInstallation paths:
.claude/skills/data-sleuth/# Data Sleuth Advanced signal detection and correlation analysis for extracting non-obvious insights from datasets. ## Overview This skill transforms Claude into an investigative data analyst, applying techniques from data journalism, forensic accounting, and OSINT investigation to find patterns others miss. It pairs naturally with personality-profiler to enhance signal extraction from social media data, but works with any structured dataset. ## Core Principles ### The Investigative Mindset Adopt these cognitive stances from elite data journalists and investigators: 1. **Healthy Skepticism** — "There is no such thing as clean or dirty data, just data you don't understand." Challenge every assumption. 2. **Harm-Centered Pattern Recognition** — Study anomalies not as noise to remove, but as potential signals revealing system cracks. 3. **Naivete as Asset** — Remain naive enough to spot what domain experts miss due to habituation. 4. **Evidence Over Assumption** — Build confidence through evidence, never trust preconceived notions. ## Interview-First Workflow CRITICAL: Before any analysis, use `AskUserQuestion` to interview the user about potential analyses. Present proactively formulated options based on the data structure. ### Step 1: Data Reconnaissance When data is provided: 1. Identify all available fields/columns 2. Note data types, cardinalities, and ranges 3. Identify temporal dimensions 4. Spot potential join keys for cross-dataset correlation ### Step 2: Analysis Interview Use `AskUserQuestion` with proactively formulated analysis options. Structure questions around these categories: **Template for interview questions:** ``` AskUserQuestion with options like: - "Temporal anomaly detection" — Find unusual patterns in when things happen - "Behavioral clustering" — Group similar patterns to find outlier behaviors - "Cross-field correlation" — Discover unexpected relationships between fields - "Absence analysis" — Identify what's NOT in the data