- Home
- Skills
- Data & Databases
- csv quality auditor by JoeJery
csv quality auditor by JoeJery
Audit CSV files for duplicates, missing values, and type errors without modifying the source.
Free
Works with the AI Agents you already use
csv quality auditor by JoeJery
Example session with this skill installed
Run a quality check on inventory_log.csv. Column 'sku' must not be empty, and 'price' and 'quantity' should be numeric.
- Read your context and instructions
- Compiled the csv quality auditor
- Generated the data export
I have completed the audit of inventory_log.csv. I scanned 1,200 rows and identified 14 issues. No changes were made to the original file.
CSV Quality Audit Report
| Issue Type | Row Number | Column | Description |
|---|---|---|---|
| Missing Value | 42 | sku | Required column is empty |
| Type Mismatch | 128 | price | Value 'TBD' is not numeric |
| Type Mismatch | 135 | quantity | Value '10 units' contains non-numeric characters |
| Duplicate Row | 450 | - | Exact match of row 449 |
| Column Count | 892 | - | Found 14 fields, expected 12 |
| Missing Value | 1002 | sku | Required column is empty |
Total Rows Scanned: 1,200
Total Issues Found: 14
Needs human confirmation
- Column
warehouse_idcontains no nulls; should this be marked as a required column in future audits? - Column
discount_ratecontains mostly floats; should this be strictly numeric?
Verdict: The file contains structural errors and type mismatches that should be addressed before analysis.
Next steps
- Review row 892 for delimiter errors or extra commas.
- Standardize the
pricecolumn to ensure all values are numeric. - Remove the duplicate entry at row 450.
inventory_log.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Data analysis often fails because of silent CSV corruption. This skill audits your datasets for missing values, duplicates, and type mismatches before they break your pipeline.
What it does
- Structure validation flags rows that do not match the header's column count.
- Null detection identifies empty or whitespace-only cells across all columns.
- Deduplication check scans for exact-match duplicate rows.
- Type verification checks if values in specified columns can be parsed as numbers.
- Constraint inference flags potential required columns for human confirmation.
How it works
- You provide a CSV file and optionally specify which columns should be numeric or mandatory.
- The skill scans the file row by row without altering the source data.
- It identifies violations based on standard data quality rules or your specific constraints.
- It generates a structured report summarizing row counts, errors, and inferred rules.
Frameworks & tools
This skill works with standard CSV formats and follows pre-defined validation rules for headers and data types.
Why this beats prompting it yourself
Manual prompting often misses edge cases like whitespace-only cells or inconsistent field counts in large files. This skill follows a strict scan-and-report workflow that ensures every row is checked against the header structure.
Use cases
- Audit third-party datasets before importing them into a SQL database.
- Verify data exported from a legacy system for type inconsistencies.
- Check for duplicate entries in a customer mailing list.
- Validate CSV structure before running expensive machine learning training.
Known limitations
Does not support file repair or cleaning. Large files may hit context window limits depending on the model used. Only supports standard CSV delimiters.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Data & Databases.
Cannot clean, fix, or overwrite files. If a file cannot be parsed as a standard CSV, the process stops. Large files may be limited by the model's context window.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account