This is a comprehensive data profiling workflow that goes well beyond basic row counts and null checks. It walks Claude through categorizing columns by role (identifier, dimension, metric, temporal), running distribution analysis on each type, and flagging quality issues like high null rates, suspicious placeholder values, and referential integrity problems. The real value is in the structured approach to pattern discovery and the framework for assessing completeness, consistency, and accuracy across columns. It concludes by suggesting specific follow-up analyses based on what it finds, like cohort analysis or correlation studies. Best used when you need to understand a new dataset's quirks before building dashboards or reports on top of it.
npx -y skills add anthropics/knowledge-work-plugins --skill explore-data --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills