Works with the AI tools you already use
Claude Code
Cursor
Codex CLI
Muse
OpenClaw+21 moreClaude CodeCursorCodex CLIMuseOpenClaw
Manus
Grok
Grok Bot+18 agentsMessy Spreadsheet Cleanup Planner
Audit messy data and generate structured, auditable cleanup plans with validation rules and implementation steps.
$9.99
Messy Spreadsheet Cleanup Planner
Example session with this skill installed
I have a CSV of 500 leads. Columns: 'Lead Name', 'Phone', 'Date Added', 'Source'. Some names are all caps, dates are a mix of MM/DD and DD/MM, and some phones have country codes while others don't. Create a cleanup plan.
- Read your context and instructions
- Compiled the messy spreadsheet cleanup
- Generated the data export
I have reviewed the lead data structure. The primary risks involve date ambiguity and inconsistent phone formatting which could lead to failed CRM imports.
Spreadsheet Cleanup Snapshot
- Purpose: Lead list preparation for CRM import.
- Columns: Lead Name, Phone, Date Added, Source.
- Constraints: Date ambiguity (mixed formats) and international phone formatting.
Data Quality Findings
| Issue | Column | Evidence/example | Confidence | Risk/impact |
|---|---|---|---|---|
| Case Inconsistency | Lead Name | "JOHN DOE" vs "Jane Smith" | High | Low - Aesthetic |
| Date Ambiguity | Date Added | "01/02/2023" (Jan 2nd or Feb 1st?) | High | High - Data integrity |
| Phone Variation | Phone | "+1 555..." vs "555-..." | High | Med - Import failure |
Proposed Cleanup Rules
| Rule ID | Column | Before | Proposed after | Rationale |
|---|---|---|---|---|
| R-01 | Lead Name | "JOHN DOE" | "John Doe" | Proper Case standardization |
| R-02 | Phone | "5551234567" | "+15551234567" | E.164 format (assuming US locale) |
| R-03 | Date Added | "01/05/2023" | "2023-05-01" | ISO 8601 for unambiguous sorting |
Implementation Sequence
- Backup: Save original
leads_raw.csv. - Standardize Casing: Apply
PROPER()function to Lead Name. - Format Phone: Remove non-numeric characters and prepend country code.
- Resolve Dates: Manually verify 5-10 rows to confirm if 01/05 means May 1st or Jan 5th.
- Validation: Run a check for rows where Phone length is < 10 digits.
Next steps
- Confirm the intended locale (e.g., US vs UK) to resolve date ambiguity.
- Decide if "Source" values should be mapped to a standardized dropdown list.
- Provide a 10-row sample to generate specific Excel/Sheets formulas.
messy-spreadsheet-cleanup-planner.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.
What you get
About this skill
Manually cleaning messy spreadsheets is a recipe for data loss and silent errors. This skill transforms the chaotic process of fixing data into a structured, auditable engineering plan that prevents destructive changes. It systematically identifies inconsistencies, formatting risks, and duplicates while ensuring every transformation is reversible and documented.
What it does
- Data profiling identifies inconsistent capitalization, mixed date formats, and whitespace issues in your sample data.
- Cleanup rule design creates specific before-and-after mapping tables for every proposed transformation.
- Duplicate handling separates exact row matches from ambiguous near-duplicates that require human review.
- Format standardization enforces consistent conventions for phone numbers, currencies, and identifiers without losing leading zeros.
- Validation logic generates formulas or pseudocode to flag invalid entries, missing values, or range violations.
How it works
- Provide a representative sample of your data, the column headers, and the business context.
- The skill audits the sample to identify specific quality issues and risks.
- It generates a comprehensive Cleanup Snapshot and a table of Proposed Cleanup Rules.
- You receive an implementation sequence detailing the order of operations to minimize data risk.
Frameworks & tools
Works with any tabular data format including CSV, Excel (XLSX), Google Sheets, and SQL table exports.
Why this beats prompting it yourself
Generic prompts often lead to "hallucinated" data fixes or dangerous bulk deletions. This skill enforces strict integrity rules, like preserving identifiers as text and mandating an audit trail, which are usually ignored by standard LLM responses.
Use cases
- Preparing legacy CRM data for migration to a new platform.
- Standardizing vendor-supplied inventory lists with inconsistent naming conventions.
- Cleaning up survey results or user-submitted form data for analysis.
- Auditing financial records for duplicate entries and formatting errors.
Known limitations
Does not perform automated bulk editing of external files directly unless the agent has specific filesystem or API tool access. Plans are based on provided samples and may not capture edge cases present in the full dataset.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- Passed all security checks, Safe to install