skills.rest
Simplified-Reasoning
Simplified-ReasoningOFFICIAL
Explore all skills by this author →
WebsiteGitHub

Data Analysis

Convert raw data into validated insights with uncertainty and caveats.

58|1|Updated May 13, 2026
Search Tags:#data analysis#visualization#cohort analysis#funnel analysis#kpi#statistical rigor#metric contracts
One-click install
npx skills add https://github.com/Simplified-Reasoning/Pi-Bench --skill data-analysis-simplified-reasoning
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Data Analysis
Source: https://github.com/Simplified-Reasoning/Pi-Bench/tree/main/data/law_trainee/skills/data-analysis-1.0.2
Command: npx skills add https://github.com/Simplified-Reasoning/Pi-Bench --skill data-analysis-simplified-reasoning

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Data Analysis helps you turn messy numbers into clear, evidence-backed conclusions so you can make better decisions instead of chasing misleading charts or poorly defined metrics.

Core Features & Use Cases

  • Metric contracts: Define grain, numerator/denominator, filters, and time windows so KPI comparisons stay valid.
  • Statistical rigor and pitfalls checks: Validate uncertainty, avoid common errors (e.g., p-hacking, Simpson’s paradox), and stress-test claims.
  • Decision briefs and chart selection: Produce stakeholder-ready outputs with the right visuals for the specific question (trend, cohorts, funnels, anomalies).

Example: When you suspect a funnel drop-off after a feature change, use this skill to lock the metric definition, quantify the change with uncertainty, and recommend the next experiment or investigation step.

Quick Start

Use the Data Analysis skill to analyze your SQL or spreadsheet export for the funnel stage with the biggest unexplained drop-off between two time windows.

Frequently Asked Questions about Data Analysis

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

FAQPage Schema
How do I debug ambiguous KPI metrics in SQL or spreadsheet exports?▼

You can analyze funnel drop-offs by locking metric definitions, quantifying the change with uncertainty, and recommending the next experiment. This approach validates raw data and outputs evidence with caveats and recommended next actions.

What is the best way to avoid common statistical paradoxes during data analysis?▼

To avoid statistical paradoxes during data analysis, apply statistical rigor and pitfall checks. This validates uncertainty, prevents errors like p-hacking and Simpson's paradox, and stress-tests claims before converting raw data into decision-ready insights.

Can I use this for cohort analysis and anomaly review in exported tables?▼

No specific dependencies are required. You can apply this directly to SQL, spreadsheets, notebooks, dashboards, and exported tables to convert raw data into validated insights without needing external tools.

How do I select the right charts for executive reporting and decision briefs?▼

To select the right charts for executive reporting, match the visualization to the specific question being asked. This produces decision briefs with appropriate trend, cohort, funnel, or anomaly visuals alongside evidence and recommended next actions.

Related Skills

Explore More Data & Analytics Skills→
dlt-hubdlt-hub
53

view-data

Query and explore dlt pipeline data using Python and ibis expressions.

Official
Intermediate
ISAQQSAIISAQQSAI

Data Analysis

Analyze data to produce decision briefs with uncertainty and recommended actions.

Community
Advanced
GPTtangGPTtang
4

data-analysis

Analyze data with statistical tests and identify analytical pitfalls.

Community
Intermediate
antgroupantgroup
16

Data Analysis

Analyze data with hypothesis testing and metric validation for business decisions.

Official
Advanced