Data file profiler
Skill nicholashidalgo/claude-skillforge/data-engineering/data-file-profiler
npx -y skills add nicholashidalgo/claude-skillforge --skill data-file-profilerAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use Python to profile exports, find data quality issues, inspect bad records, and summarize findings in plain language.
SKILL.md
1.6 KB, as published. Nobody here has run it
Runtime Configuration
version: "1.0.0"
gotcha_pack: "sql-data-gotcha-pack"
gotcha_pack_version: "1.0.0"
gotcha_enforcement: "block_on_high"
Purpose
Use Python for disciplined file and extract investigation.
Workflow
- Load the file safely.
- Inspect schema, types, row counts, and date coverage.
- Profile nulls, duplicates, distinct counts, outliers, and suspicious categories.
- Trace exceptions back to specific records.
- Summarize findings in business language.
Preferred libraries
- pandas
- openpyxl when Excel handling matters
- pathlib
- re
- datetime
Output format
- What was inspected
- Key findings
- Python script
- Recommended next checks
Gotcha Enforcement
Apply these rules when writing profiling and investigation code. A HIGH violation in generated code must be corrected. MEDIUM violations must appear in the findings summary with an explanation.
| ID | Sev | Check |
|---|---|---|
| G003 | HIGH | Every mean/sum/aggregation documents its NA/NaN behavior (skipna, fillna, or note) |
| G009 | MEDIUM | Null rate check is mandatory for every measure column, not optional |
| G012 | HIGH | Before comparing two datasets, confirm they share the same grain, period, and filters |