CSV Wrangling with qsv

Standard Workflow Order

Always follow this sequence when processing CSV data:

Setup (Cowork) - If relative paths don't resolve, call mcp__qsv__qsv_get_working_dir and mcp__qsv__qsv_set_working_dir to sync
Index - index (enables fast random access for subsequent commands)
Discover - sniff (detect format, encoding, delimiter) -> headers -> count
Profile - stats --cardinality --stats-jsonl (creates cache used by smart commands)
Inspect - slice --len 5 (preview rows), frequency --frequency-jsonl (value distributions with cache for reuse)
Transform - select, sort, dedup, rename, replace, search, sqlp, etc.
Validate - validate (against JSON Schema), stats (verify results)
Export - tojsonl, table, mcp__qsv__qsv_to_parquet, to (xlsx/sqlite/postgres/ods/datapackage)
Document - describegpt --all (AI-generated Data Dictionary, Description & Tags)