- Home
- Skills
- E-commerce
- Product Feed Fix Kit
More screenshots
Works with the AI Agents you already use
Product Feed Fix Kit
Audit ecommerce CSV feeds for missing data, price errors, and ID collisions using a local Python validation script.
$7
Product Feed Fix Kit
Example session with this skill installed
Audit this products.csv file. The destination is Shopify. Columns are 'ID', 'Item Name', and 'MSRP'. Ensure prices are in USD and no IDs are missing.
- Read your context and instructions
- Compiled the product feed fix
- Generated the data export
I have analyzed the provided products.csv and mapped your columns to the required canonical fields. I materialised the validation script and ran a baseline audit against your USD price policy.
Feed Audit Results
| Metric | Value |
|---|---|
| Total Input Records | 450 |
| Records Ready for Import | 412 |
| Records Held for Review | 38 |
| Policy Violations | 42 |
| Price Normalizations | 15 |
feed-review.md
- Scope: Validation of ID (from 'ID'), Title (from 'Item Name'), and Price (from 'MSRP').
Critical Issues: 12 records held due to missing 'ID' values. 26 records held due to malformed 'MSRP' strings (e.g., "TBD", "12,50").
- Changes: 15 records had whitespace trimmed from 'Item Name' per standard normalization.
- Duplicate Check: No duplicate IDs detected in this batch.
candidate-feed.csv
ID,Item Name,MSRP
SKU-001,Wireless Mouse,25.00
SKU-002,Mechanical Keyboard,89.99
SKU-003,USB-C Cable 6ft,12.50
issues.json
[
{
"record": 45,
"field": "price",
"code": "MALFORMED_CURRENCY",
"detail": "Value '12,99' contains invalid decimal separator; expected dot-decimal."
},
{
"record": 112,
"field": "id",
"code": "MISSING_REQUIRED",
"detail": "Identifier field is empty."
}
]
Next steps
- Review
review-rows.csvto manually fix the 38 records with missing IDs or malformed prices. - Verify the
ready-feed.csvin a sandbox environment before your final Shopify import. - Update the source CSV with corrected values and rerun this audit to clear the remaining issues.
products.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
Clean up messy product catalogs before they break your import. This skill audits product CSV feeds to find missing attributes, duplicate identifiers, malformed prices, and URL syntax errors. It transforms raw, untrusted data into a structured correction bundle without modifying your source file or connecting to live store APIs.
What it does
- Data validation checks for missing IDs, titles, and prices against a strict local policy.
- Normalization applies authorized trims and stock aliases while preserving original column order.
- Issue logging generates detailed JSON reports of every changed cell and held record.
- Conflict detection identifies duplicate IDs and variant collisions, holding them for manual review.
- Syntax verification validates URL formats and currency strings without external pings.
How it works
- Scope and Policy: Provide your CSV and destination requirements to define the baseline validation rules.
- Materialize: The agent prepares a standalone Python script and a policy JSON based on your catalog rules.
- Audit Execution: The script runs locally to generate a candidate feed, a ready feed, and a review list for held rows.
- Analysis: Review the generated
feed-review.mdand JSON logs to see exactly why records were flagged or changed.
Frameworks & tools
Built for Python 3.10 environments using standard libraries. It processes local CSV files using explicit delimiters and UTF-8 encoding.
Why this beats prompting it yourself
Generic prompts often hallucinate fixes or miss hidden duplicates in large files. This skill uses an executable script to ensure every record is accounted for, providing a verifiable audit trail where "ready" plus "held" always equals your input count.
Use cases
- Auditing a vendor CSV before importing it into Shopify or Magento.
- Cleaning up inconsistent currency and price formatting across thousands of rows.
- Identifying duplicate SKU entries that would cause database collisions.
- Preparing a localized feed by filtering records against specific attribute policies.
Known limitations
Does not perform image analysis, GTIN validity checks, or live site connectivity. Large files are processed in memory. It verifies URL syntax but does not check if links are live or reachable.
In-memory processing only; no production-scale database support. URL checks are syntax-only. No live reachability, image content, or GTIN validity verification.
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 19 days ago
Requires