- Home
- Skills
- Research & Analysis
- CSV Data Quality Auditor68855
CSV Data Quality Auditor68855
Audit CSV datasets for missing values, duplicates, and data types to generate structured lab reports.
Free
Works with the AI Agents you already use
CSV Data Quality Auditor68855
Example session with this skill installed
Run a quality audit on data/student_grades.csv with a sample limit of 1000 rows for my lab report.
- Read your context and instructions
- Compiled the csv data quality
- Generated the data export
I have completed the data quality audit for student_grades.csv. The audit processed 1,000 rows as requested.
CSV Data Quality Audit Report
1. Dataset Overview
| Metric | Value |
|---|---|
| Filename | student_grades.csv |
| Total Rows (Sampled) | 1,000 |
| Total Columns | 5 |
| Duplicate Rows | 12 |
2. Missing Value Statistics
| Column Name | Missing Count | Missing Percentage |
|---|---|---|
| student_id | 0 | 0.00% |
| course_code | 0 | 0.00% |
| assignment_score | 45 | 4.50% |
| exam_score | 102 | 10.20% |
| final_grade | 0 | 0.00% |
3. Column Data Types
| Column Name | Inferred Type |
|---|---|
| student_id | int64 |
| course_code | object |
| assignment_score | float64 |
| exam_score | float64 |
| final_grade | object |
4. Boundary & Warnings
Sampling Notice: This audit was limited to the first 1,000 rows. Results may not represent the entire dataset if the source file is larger.
Integrity Warning: 12 duplicate rows were detected; verify if these represent unique submissions or data entry errors.
Missing Data: The exam_score column has over 10% missing values, which may impact statistical significance in your analysis.
Next steps
- Review the 12 duplicate rows to determine if they require removal.
- Address the missing
exam_scorevalues using mean imputation or row exclusion. - Use the inferred types to configure your
read_csvDtype parameters in your notebook.
student_grades.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 lab assignments often stall when students start with corrupted or incomplete datasets. This skill automates basic CSV data quality auditing to ensure academic projects begin with a clear understanding of the underlying data structure.
What it does
- Missing value analysis counts null entries per column and calculates the percentage of missing data.
- Duplicate detection identifies and counts identical rows across the entire dataset.
- Type inference determines the specific pandas data types for every column.
- Dataset overview provides high-level statistics including total row and column counts.
- Sampled auditing handles files up to a defined limit to prevent memory issues during local analysis.
How it works
- Provide the local file path to your CSV and an optional sample limit for larger files.
- The agent reads the file, applying encoding checks and enforcing the row limit.
- The auditor executes a suite of checks based on internal quality rules for missing, duplicate, and typed data.
- Results are formatted into a structured Markdown report using a standardized academic template.
Frameworks & tools
The skill utilizes pandas for data processing and type inference. It generates output in standard GitHub Flavored Markdown.
Why this beats prompting it yourself
Manual prompts often miss specific edge cases like duplicate row counts or precise null percentages across large schemas. This skill uses predefined rules and a consistent template to ensure your lab reports are uniform and technically accurate every time.
Use cases
- Audit CSV files for university data science lab assignments.
- Generate data quality summaries for inclusion in experimental documentation.
- Verify dataset integrity before beginning exploratory data analysis.
- Identify data cleaning requirements for student machine learning projects.
Known limitations
Does not identify business logic outliers or modify files. Not for production systems, high-risk financial data, or files exceeding the sample limit.
Does not identify business logic outliers or modify files. Not for production systems, high-risk financial data, or files exceeding the sample limit.
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 any payment.
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 forever
No account required to browse
Trust & safety
Security scan
Security scan passed today
- Free with an Agensi account