lightest-data-analysis

Analyze tabular datasets for reproducible exploratory analysis and evidence-based findings.

4|Updated Jun 4, 2026
One-click install
npx skills add https://github.com/lijiandao/lightest-skills --skill lightest-data-analysis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lightest-data-analysis
Source: https://github.com/lijiandao/lightest-skills/tree/main/optional/lightest-data-analysis
Command: npx skills add https://github.com/lijiandao/lightest-skills --skill lightest-data-analysis

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill turns raw tables into reproducible data analysis, helping you verify schema, grain, quality, and metrics before drawing conclusions.

Core Features & Use Cases

  • Exploratory analysis: Profile CSV, Excel, JSON, and Parquet data with missingness, duplicates, types, and distribution checks.
  • Metric and KPI analysis: Compute grouped summaries, YoY or MoM changes, funnels, cohorts, and time-series trends with explicit denominators.
  • Hypothesis-driven investigation: Validate root-cause hypotheses, compare segments, and produce evidence-backed findings with clear limitations.
  • Use Case: If sales dropped last month, use this Skill to confirm the data grain, audit the dataset, test plausible drivers, and write a findings summary that is fully traceable.

Quick Start

Ask the assistant to analyze your dataset with this skill and it will profile the file, verify grain and quality, compute the relevant metrics, and produce a reproducible findings summary.

Frequently Asked Questions about lightest-data-analysis

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

FAQPage Schema
How do I perform reproducible exploratory data analysis on a CSV file?

Reproducible exploratory data analysis profiles your CSV by checking missingness, duplicates, and distributions to verify schema and data quality before drawing conclusions.

Can I analyze time series data and calculate KPI metrics with explicit denominators?

Time series analysis computes grouped summaries, YoY or MoM changes, and cohort trends with explicit denominator tracking to ensure accurate KPI metrics.

How do I test root-cause hypotheses for a sudden metric drop in my dataset?

Hypothesis-driven investigation validates root-cause hypotheses by comparing segments and producing evidence-backed findings with clear limitations for your dataset.

Does this data analysis approach work with JSON and Parquet formats?

Data analysis supports schema intake and grain validation for JSON and Parquet formats alongside CSV and Excel workflows to audit quality and compute metrics.

What guardrails prevent errors during tabular dataset analysis?

Guardrails prevent hallucinated columns, many-to-many join inflation, and unsupported causal claims by enforcing filter disclosure and denominator tracking during analysis.

How do I audit data quality and validate the grain of a tabular dataset?

Data quality auditing profiles tabular datasets to validate grain, log cleaning steps, and verify types and distributions to ensure reproducible findings.