- Home
- Skills
- Productivity
- Compare Two CSV Files and Find Every Difference
Works with the AI Agents you already use
Compare Two CSV Files and Find Every Difference
Compare two CSV files to find every added row, removed row and changed cell.
Free
Compare Two CSV Files and Find Every Difference
Example session with this skill installed
Compare two inventory CSV files using sku as the key. Before: A1 Notebook 10, B2 Pen 25. After: A1 Notebook 8, C3 Marker 15.
- Read your context and instructions
- Compiled the compare two csv
- Generated the data export
CSV Difference Report
| Measure | Result |
|---|---|
| Old records | 2 |
| New records | 2 |
| Added records | 1 |
| Removed records | 1 |
| Modified records | 1 |
| Changed cells | 1 |
Added: C3 Marker, stock 15. Removed: B2 Pen, stock 25.
| SKU | Field | Previous | Current |
|---|---|---|---|
| A1 | stock | 10 | 8 |
The output includes five actual files named added_rows.csv, removed_rows.csv, changed_cells.csv, summary.json, and REPORT.md. No existing file is changed. Values are compared as raw text, so 10 and 10.0 are considered different. If key values are missing or duplicated, the script stops and reports the problem. This worked example uses fictional inventory and yields exactly the displayed counts.
added_rows.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
Free CSV comparison agent skill with working Python code. Provide two CSV exports and one unique row key, such as SKU or order ID. Receive five files: added_rows.csv, removed_rows.csv, changed_cells.csv, summary.json, and REPORT.md. Get exact field-level before/after changes, row counts and schema differences. Duplicate or blank keys cause a clear error rather than invented matches. The script does not modify or upload your CSVs. Works offline with Python 3.9+ standard library; includes examples and three tested cases. Good for inventory snapshots, CRM exports and database migration verification. Pair it with our paid missing-data research or CSV dashboard skills if you also need enrichment or visualization.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Productivity.
Requires unique stable row key; exact case-sensitive raw-text comparisons; schema-only differences separated.
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 2 days ago
- Free with an Agensi account
- Software
- Python 3.9+ standard libraryAuthorized local CSV file(s)
Permissions
File Scopes
Local-only processing; no external requests.