Audit CSV Data Quality Before Analysis
For data-analysis undergraduates and small-data researchers, this Skill runs a read-only local audit on a single CSV file and returns a structured Markdown quality checklist.
Free
Works with the AI Agents you already use
Audit CSV Data Quality Before Analysis
Example session with this skill installed
请帮我检查这个 CSV 文件的数据质量,找出缺失值、重复行和格式问题。
students.csv:
id,name,email,age,enroll_date,city
1,Alice Smith,alice.smith@example.com,21,2024-09-01,Beijing
2,Bob Johnson,,22,2024-09-01,Shanghai
3,Carol Wang,carol.wang@example.com,NA,2024-09-02,Guangzhou
3,Carol Wang,carol.wang@example.com,NA,2024-09-02,Guangzhou
4,David Chen,david.chen@example.com,23,2024-13-40,Shenzhen
- Read your context and instructions
- Compiled the audit csv data
- Generated the data export
CSV Data Quality Report
File: students.csv | Encoding: UTF-8 | Data rows: 5 | Columns: id, name, email, age, enroll_date, city
| Check | Status | Count | Location |
|---|---|---|---|
| Encoding | ✅ | 0 | utf-8, no replacement characters |
| Structure | ✅ | 0 | 6 columns, no ragged rows |
| Missing values | ⚠️ | 2 | email row 2 (empty); age rows 3, 4 (NA) |
| Duplicate rows | ⚠️ | 1 | rows 3 and 4 identical |
| Format validation | ❌ | 1 | enroll_date row 5: 2024-13-40 (expected ISO date YYYY-MM-DD) |
| Whitespace hygiene | ✅ | 0 | — |
Overall verdict: ❌ FAIL
Review the problem details above and fix the flagged cells before re-auditing. The audit is read-only; the original file was not modified.
students.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
For data-analysis undergraduates and small-data researchers, this Skill runs a read-only local audit on a single CSV file and returns a structured Markdown quality checklist.
Who it is for
- Data-analysis undergraduates preparing course assignments and lab datasets.
- Small-data researchers who tidy modest CSV files before analysis.
- Students and learners organizing small spreadsheets for homework, projects, or reports.
Key features
- Detect encoding and structural problems. Identify the file encoding (UTF-8 / UTF-8-BOM / GBK), report U+FFFD replacement characters, check the header and per-row field counts, recognize the delimiter, and flag empty files.
- Scan missing values and duplicates. Count empty cells, whitespace-only cells, and placeholders such as N/A, NA, null,
-, and?per column; detect fully duplicated rows and duplicates on a chosen primary-key column. - Validate formats and issue a verdict. Check numeric parseability, ISO dates (YYYY-MM-DD), emails, and URLs; locate problem cells by row number; count leading/trailing whitespace; compare actual columns against expected columns; return an overall PASS / WARN / FAIL judgment.
What it does not do
- It does not clean, rewrite, delete, or modify the original CSV file; the audit runs in read-only mode.
- It rejects non-CSV inputs such as images or JSON files.
- It does not replace human judgment: the checklist flags candidate issues for you to review.
Does not support binary Excel (.xls/x), JSON, or PDF. Strictly read-only; cannot modify or fix data. Requires Python 3 environment to execute the audit script.
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
Requires