agentleFS
grw-labgrw-lab/skills/product-sheet/SKILL.md

product-sheet

Skill1 starsChanged 35 days agoMITView on GitHub

Turns a raw product CSV into a merchant sheet with a clean slug and a VAT split at the given rate, default 15%. Use when a shop has a spreadsheet of names and prices and needs price excluding VAT, VAT, price including VAT, and a URL slug. The agent writes Arabic titles and short descriptions; the script does the numbers. Not a ZATCA e-invoice.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run the script. It writes the numbers and the slug.

    line 23
  2. Very specific:

    When price_includes_vat is yes, net is gross / (1 + rate), rounded half-up to 0.01, and VAT is gross minus net.

    line 36
  3. Distinctive:

    Do not invent stock, shipping, or compare-at prices.

    line 37
  4. Distinctive:

    Every source row is in the sheet.

    line 41

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Product sheet

Build a sheet a merchant can review before uploading it to a store. The script does slugs and VAT. You write the Arabic title and the one-line description.

When to use

  • A CSV of product names and prices needs a clean sheet.
  • The user asks for Arabic product titles, a short description, or a slug.

When not to use

  • They need a Saudi e-invoice, a QR code, or a ZATCA submission. Use zatca-invoice.
  • They want you to publish into a store dashboard. Hand them the CSV. Do not invent an API.

Workflow

  1. Confirm the columns. Required: name, price. Optional: sku, vat_rate (default 0.15), price_includes_vat (yes or no), description.
  2. Run the script. It writes the numbers and the slug. It does not translate.
python scripts/product_sheet.py products.csv --out sheet.csv
  1. Open sheet.csv. For each row, write title_ar and summary_ar in the merchant's dialect. One sentence for the summary. Keep the product facts that are in the source. Do not add materials, sizes, or claims that are not there.
  2. Slugs stay as the script wrote them unless two products would be confused. Arabic letters and hyphens are fine.
  3. Show the sheet and say which prices already included VAT.

Rules

  • Standard rate in the script is 15% only when vat_rate is empty. If they say a row is zero-rated or exempt, set vat_rate to 0. Do not "correct" that to 15%.
  • When price_includes_vat is yes, net is gross / (1 + rate), rounded half-up to 0.01, and VAT is gross minus net.
  • Do not invent stock, shipping, or compare-at prices.

Done check

  • Every source row is in the sheet.
  • price_ex_vat + vat equals price_inc_vat on each row.
  • Arabic lines do not add a fact the CSV did not have.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.