$ show nimrodfisher/data-analytics-skills
This repository is a curated skill library for data analysis workflows, designed to be consumed by AI agents (Claude Code, Codex). It contains 31 skills organized into 6 categories: data quality validation, documentation/knowledge management, data analysis/investigation, data storytelling/visualization, stakeholder communication, and workflow optimization. Each skill is defined by a SKILL.md file with YAML frontmatter, a step-by-step process, required inputs/outputs, and optional scripts, reference materials, and asset templates. The scripts are standalone Python CLIs that generate synthetic data for demo purposes and can be adapted to real datasets. The repo is not a deployable application or a data pipeline; it is a structured knowledge base and toolset for performing data analysis tasks programmatically. It covers common analytical patterns such as null counting, duplicate detection, cohort retention, funnel conversion, A/B testing, time series anomaly detection, metric calculation, and more. The codebase is well-organized and follows consistent conventions, but shows signs of staleness (future dates in README and LICENSE, no recent activity). Dependencies are not pinned, and no environment definitions are provided, limiting reproducibility without manual setup.
The LLM identified 6 files worth highlighting for reuse:
A standalone Python CLI that counts null values per column in a CSV/Parquet/Excel dataset, with configurable threshold flags (--warn, --fail) and optional output. Demonstrates a reusable pattern for data quality validation: load data, compute null counts, compare against thresholds, and exit with appropriate status code. The script is self-contained, uses only pandas and numpy, and includes a demo mode that generates synthetic data when run without arguments.
Provides a comprehensive overview of a dataset: shape, column names, data types, missing value counts, and summary statistics. Outputs a formatted text report to console or file. Reusable as a first step in any EDA pipeline. The script is parameterized (--input, --output, --sample-size) and includes a demo mode with synthetic data. Demonstrates a clean pattern for programmatic data profiling.
Builds cohort tables from user-provided data with configurable cohort periods (daily, weekly, monthly) and metrics (retention, revenue, etc.). Outputs a cohort matrix as CSV or Markdown. The script is self-contained, uses pandas for pivot operations, and includes a demo mode. Reusable for any retention analysis task. Demonstrates a clean pattern for cohort construction with flexible aggregation.
Performs A/B test analysis using a two-proportion z-test with pooled standard error and p-value estimation via erfc. Includes Sample Ratio Mismatch (SRM) check using chi-square test. Outputs a formatted report with significance verdict and practical significance. The script is self-contained, uses only numpy and math, and includes a demo mode. Reusable for any A/B test evaluation. Demonstrates a pragmatic statistical testing pattern.
Detects jargon terms in text input against a configurable dictionary and suggests plain language alternatives. Outputs a report with flagged terms and replacement suggestions. Reusable for improving clarity of analysis reports and stakeholder communications. The script is self-contained, uses only standard library and argparse, and includes a demo mode. Demonstrates a pattern for automated communication quality checks.
Packages context for AI sessions by combining multiple input files (task, business context, schema, prior findings, constraints, output format) into a single structured markdown document. Includes token counting via a heuristic (4 chars/token). Reusable for any AI-assisted analysis workflow to ensure complete and concise context. The script is self-contained, uses only standard library, and includes a demo mode. Demonstrates a pattern for structured context preparation.