- Home
- Skills
- Workflow Automation
- list clean and compare
More screenshots
Works with the AI Agents you already use
list clean and compare
Clean, validate, and compare messy Excel/CSV lists using deterministic Python scripts with full audit logs.
$5
list clean and compare
Example session with this skill installed
Profile members_2024.xlsx and tell me what needs fixing. Country code is +44 and the 'Email' column should never be empty.
- Read your context and instructions
- Compiled the list clean
- Generated the document
I have analyzed members_2024.xlsx. The header was detected at row 1, and I identified 152 rows across 6 columns.
members_2024.xlsx · ⚠️ 4 things to decide
Fixed: 42 cells (22 Phone numbers, 12 Date formats, 8 Name casing)
Duplicates: 2 exact (merge recommended), 5 possible (typos in 'Last Name')
Problems: 3 invalid emails, 7 missing emails (required field)
| Column | Detected Type | Issues Found |
|---|---|---|
| First Name | Text | Mixed CAPITALS and lowercase |
| Last Name | Text | Extra trailing spaces |
| 7 empty cells, 3 malformed addresses | ||
| Phone | Phone | Missing +44 prefix, inconsistent separators |
| Join Date | Date | Mixed DD/MM/YY and MM-DD-YYYY formats |
| Member ID | Code | Stored as number (leading zeros at risk) |
Next steps
- Would you like me to merge the 2 exact duplicates?
- Review the 5 "possible" duplicates: 'John Smit' vs 'John Smith' and 'Sara O'Connor' vs 'Sara O Connor'.
- Run the
cleancommand to generate thecleaned.xlsxfile with the audit log.
members_2024.xlsx
PDF · document
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
Messy spreadsheets with inconsistent formatting, duplicate entries, and hidden errors waste hours of manual work. This skill automates the tedious process of cleaning Excel and CSV files while ensuring data integrity through deterministic Python scripts and detailed change logs.
What it does
- Standardizes formatting by fixing irregular casing, trimming whitespace, and unifying date formats to YYYY-MM-DD.
- Validates data to identify invalid emails, malformed phone numbers, and missing required values.
- Detects duplicates using both exact matches and similarity algorithms to catch typos or near-misses.
- Performs list comparison between two versions to track who is new, who left, and exactly which cells changed.
- Preserves data by never modifying original files and outputting results to a dedicated directory with full audit trails.
How it works
- Profiling phase where the agent analyzes the file structure to detect headers, column types, and data quality issues.
- Cleaning phase where the user provides configuration for phone country codes and required fields to generate a cleaned output.
- Deduplication phase where exact matches are merged and potential typos are flagged for human review.
- Comparison phase where two lists are mapped and cross-referenced to identify additions, removals, and updates.
Frameworks & tools
The skill uses a standalone Python 3.8+ script utilizing the standard library for deterministic processing. It handles .xlsx and .csv formats natively.
Why this beats prompting it yourself
Standard LLM prompts often hallucinate data or silently truncate large lists when "cleaning" text. This skill uses executable code to ensure every single row is processed accurately with a permanent log of every change made.
Use cases
- Cleaning membership directories for clubs or non-profit associations.
- Reconciling monthly sales reports to find new leads and churned customers.
- Normalizing employee contact lists for HR system migrations.
Known limitations
Does not support legacy .xls files directly; users must save them as .xlsx or .csv first. Requires a Python 3.8 environment for execution.
Requires Python 3.8 or higher. Cannot process legacy .xls files directly without conversion to .xlsx or .csv. No network access for external API validation.
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
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 1 month ago
Requires
Permissions
No special permissions declared or detected