/data--cohort-analysis

/data--cohort-analysis is a Claude Code skill in the Data section. Builds runnable cohort retention SQL on your real schema, plus a guide to reading the retention triangle and spotting misleading patterns.

Author's description

Build a cohort retention analysis: runnable SQL plus an interpretation guide

How to ask for it

/data--cohort-analysis build a cohort retention analysis of my users
/data--cohort-analysis give me SQL to see monthly retention since signup
/data--cohort-analysis explain how to interpret the cohort table you generate

Install

curl -fsSL https://raw.githubusercontent.com/sgomez-dev/claude-skills/main/install.sh | bash

After installing with the script, type /data--cohort-analysis. Using Cursor, Windsurf or Codex? Platform guides

Demo coming soon

/data--csv-wranglerCSV and Excel cleanup
Cleans, dedupes and reshapes a CSV or Excel file with a reusable Python script, saving a clean copy and leaving the original untouched.
Built here
/data--dashboard-specDashboard specification
Writes a Markdown dashboard spec covering audience, key questions, metrics, chart types and layout, ready to build in any BI tool.
Built here
/data--data-contractsData contracts between teams
Defines a YAML data contract between the producer and consumers of a dataset: schema, freshness and quality SLAs, and versioning rules.
Built here
/data--data-quality-auditData quality audit
Audits tables or pipeline output for nulls, duplicates, invalid values, orphaned keys and drift, with runnable SQL and a ranked findings report.
Built here
/data--dbt-modeldbt models with tests
Generates dbt models in staging and marts layers with tests and column docs, following the conventions your dbt project already uses.
Built here
/data--etl-pipelineIdempotent ETL or ELT pipeline
Scaffolds an ETL or ELT pipeline that is safe to re-run, fails loudly, and uses the data tools already in your repo.
Built here

How to ask for it

Install

More from this section