data-analysis

Frame decision-driven analysis problems for structured data sources.

415|44|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/notque/claude-code-toolkit --skill data-analysis-notque
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: data-analysis
Source: https://github.com/notque/claude-code-toolkit/tree/main/skills/data-analysis
Command: npx skills add https://github.com/notque/claude-code-toolkit --skill data-analysis-notque

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Decision-makers often struggle to extract actionable insights from structured data without a clear framing of the decision. This Skill enforces a decision-first approach, forcing framing before any data interpretation to ensure insights are aligned with business options and outcomes.

Core Features & Use Cases

  • Frames the decision and evidence requirements to guide analyses of CSV/JSON/database exports, API responses, logs, and other structured data.
  • Locks metric definitions and population scope before loading data to preserve auditability and prevent post-hoc tuning.
  • Manages a phased workflow (FRAME, DEFINE, EXTRACT, ANALYZE, CONCLUDE) with an artifact trail saved at each phase.
  • Applies statistical rigor gates to ensure results are reliable, interpretable, and actionable, with explicit limitations documented.

Quick Start

Provide a dataset file path and your decision question to begin a framed, phased analysis.

Frequently Asked Questions about data-analysis

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

FAQPage Schema
How do I frame a decision-driven data analysis problem for structured datasets?▼

Decision-driven data analysis requires locking metric definitions and population scope before loading data. This approach forces you to frame the business decision first, guiding extraction and modeling for CSV, JSON, databases, or APIs to produce auditable artifacts.

How do I run a valid A/B test and cohort comparison from raw logs or database exports?▼

Running a valid A/B test or cohort comparison requires defining populations and time windows before extraction. The analysis applies four statistical rigor gates across the process to ensure results are reliable, interpretable, and actionable.

What is the best way to prevent post-hoc tuning when analyzing CSV or JSON data for trend analysis?▼

Preventing post-hoc tuning during trend analysis requires locking metric definitions before extracting data. By enforcing a phased workflow of FRAME, DEFINE, EXTRACT, ANALYZE, and CONCLUDE, the process preserves auditability and prevents bias.

Does this data analysis approach work with API responses and CSV files?▼

Yes, this data analysis approach works with API responses, CSV files, JSON, databases, and logs. It applies structured extraction and statistical rigor gates to these formats for decisions like anomaly detection, trend analysis, and cohort comparisons.

How do I document limitations and ensure auditability for statistical anomaly detection?▼

Ensuring auditability for anomaly detection requires saving an artifact trail at each phase of the analysis. The process enforces statistical rigor gates and explicitly documents limitations to produce reliable, interpretable, and actionable outcomes.