// E-commerce

Shopify Product CSV Preflight

Catch Shopify product CSV handle, title, SKU, image URL, and overwrite risks before import.

We earn a commission on eligible purchases after a new Agensi signup through these links. We also sell our own skills on Agensi.

Get it on Agensi Browse all skills $5 one-time

Format: Agent skill, not a browser app. You need an AI agent that can load its instructions and use the required tools.

Package requirements: Normalized UTF-8 JSON input documented in the package. Python 3.10 or newer on Windows, macOS, or Linux. Local files only; no live account or provider connection.

You get: findings.csv with stable codes and record identifiers review-manifest.csv with every reviewed item

Licence and purchase details

Review the package licence at the destination.

Review the offer and access method at your chosen marketplace. Agensi provides connected-agent access, not a download. Buying a skill does not include an AI-agent subscription or setup service.

Agensi access: This product’s bundled-script workflow through Agensi has not been verified here. Tests of other products do not establish this package’s compatibility. Local setup examples apply to separately obtained downloadable packages.

See tested hosts, versions and workflow limits.

What problem does Shopify Product CSV Preflight solve?

A single missing handle, reused handle, malformed image URL, or incomplete overwrite column set can reject rows or damage a product update.

Use it to

Review a supplier product CSV before Shopify import.
Catch handle collisions before a new-product load.
Expose overwrite omissions before replacing existing product data.

What it returns

findings.csv with stable codes and record identifiers
review-manifest.csv with every reviewed item
result.json with READY, REVIEW, or BLOCK gate
report.md with a human-readable decision handoff

A representative input and result

fixture-backed sample

input {"mode":"new","rows":[{"Handle":"linen-shirt","Title":"Linen Shirt","Variant SKU":"LS-01","Image Src":"https://cdn.example/ls.jpg"}]}

result READY; 1 row reviewed; findings.csv, review-manifest.csv, result.json, and report.md written.

Access and approval boundaries

Read access to one user-supplied local JSON evidence file.
Write access only to the selected local output directory.
No browser, network, credential, account, environment-variable, or external-action permission.

Known limitations

It checks normalized CSV row evidence and does not upload to Shopify.
It cannot predict store-specific apps, limits, or unpublished platform changes.
Overwrite review still requires a store owner who understands the intended catalog change.

// choose with context

Is Shopify Product CSV Preflight the right skill?

Best fit

A single missing handle, reused handle, malformed image URL, or incomplete overwrite column set can reject rows or damage a product update.

It returns

findings.csv with stable codes and record identifiers. review-manifest.csv with every reviewed item.

Do not use it as

It checks normalized CSV row evidence and does not upload to Shopify.

Compatibility, access, version, and licence

Reads or accesses: Declared local scope: one owner-selected local JSON input, one owner-selected local output directory.
Compatibility: Normalized UTF-8 JSON input documented in the package. Python 3.10 or newer on Windows, macOS, or Linux. Local files only; no live account or provider connection.
Version: 1.0.0
Licence: Review the package licence and seller terms at the linked destination.

What happens next

Open the Agensi listing, check the current offer and connect a supported agent. Agensi loads the skill through its connector; it no longer provides a download. Approve any purchase before use. Check Agensi’s current connection guide before changing an existing connection.

Questions

Does it change or upload anything?

No. It reads supplied local evidence and writes only to the selected output directory.

Is this an AI judgment?

No. The packaged checker is deterministic and applies documented rules to the supplied input.

What does a ready result mean?

It means no automated finding was produced. The responsible owner still reviews the original source and decides what to do.

How does malformed input behave?

Invalid JSON, duplicate identifiers, missing required arrays, and invalid core values fail closed.

Can I audit the result?

Yes. Every finding carries a stable code, record identifier, severity, source, and message.