This is a bootstrapping tool for data teams who are tired of explaining their warehouse schema to Claude every single conversation. It walks you through schema discovery, asks targeted questions about your metrics and terminology (like "when you say 'user' what do you actually mean?"), then generates a company-specific data analyst skill with reference files. You can run it once to create the initial skill or use iteration mode to add new domains. The real value is capturing tribal knowledge about gotchas, standard filters, and metric calculations so future Claude sessions already know that ARR excludes test accounts and the users table has three different ID columns. Saves you from writing this documentation yourself.
npx -y skills add anthropics/knowledge-work-plugins --skill data-context-extractor --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