Skill

Clean CSV Toolkit

Local CSV / TSV / JSONL inspection and cleanup toolkit. Profile a tabular file (row count, auto-detected column types, nulls, distincts, samples), validate i...

Verified: 2026-05-15 (clawhub-ingest-2026-05-15+enrich-capability-skill)

When to use Clean CSV Toolkit

Choose if

You need a fast, local-only CSV/TSV/JSONL profiler and cleanup toolkit that runs on Python stdlib alone (no third-party deps), handles row counts, nulls, distincts, dedupe, JSON-schema validation, format conversion, and head/tail/sample preview — without ever touching an LLM or remote service.

Avoid if

You need locale-aware numeric parsing (Brazilian "1.234,56" or grouped "1,234.56" will be tagged as strings), Excel (.xlsx) support, statistical analysis, or any LLM-assisted cleanup. Also avoid if you want the toolkit to call out to a remote API or load a full dataframe — by design, it does neither.

Risk Flags

  • LOW data_quality Type inference uses regex-shape matching rather than locale-aware parsing — formatted numbers like "1,234.56" are detected as strings. The Markdown writer flattens multi-line cells to single lines.
  • LOW scope README is explicit that the skill does not call any LLM, web service, or remote API; excludes statistical analysis, Excel parsing, and operations outside caller-specified paths.

Cost

Type: Free

Dependencies

Minimum runtime: python3

Distribution

ClawHub
clean-csv-toolkit
License
MIT