Label Support Tickets in Arabic and English at Once
Tag 200 bilingual tickets in seconds, with categories that work in both languages.
Your team writes in Arabic and English, but your tagging system only works properly in one language. Reports get messy because the same issue gets labelled differently depending on which language the customer used.
That is the gap this drop closes. It is a operations skill built for Claude, and it takes about ten minutes to set up the first time. After that it runs in under a minute.
Who should use it
Support managers who handle tickets in Arabic and English and need consistent categorisation across both
How it works
The skill file does five things, in this order.
1. Export your raw ticket data. Pull the last 200 ticket subjects and bodies into a spreadsheet, keeping both Arabic and English entries.
2. Define your bilingual categories. Write five to eight category pairs that your team actually uses, like Billing/الفوترة or Technical Issue/مشكلة تقنية.
3. Batch label in one pass. Feed Claude the full list with your category pairs and ask it to tag each ticket in both languages simultaneously.
4. Check the edge cases. Scan for tickets where Arabic colloquial terms or English transliterations confused the category assignment.
5. Build a reference table. Save the category pairs and sample tickets as a reference document your team can update when new patterns emerge.
What comes back
A tagged dataset where every ticket has a consistent category regardless of language, and a reusable taxonomy your team can apply going forward.
The mistake to avoid
Arabic support tickets often mix languages mid-sentence or use transliterated English words. Tell Claude to treat these as Arabic tickets and flag them separately so you can see how common code-switching is in your queue.
Running it
Save this as SKILL.md inside a folder named after the skill, then drop the folder into your Claude Code skills directory or upload it to a Claude Project. Claude reads the frontmatter to decide when the skill applies, so keep the description line intact. For a one-off run, paste the prompt block directly.
Where this fits
On its own, one skill saves an hour a week. The compounding happens when three or four of them run in sequence on the same input, the same transcript that produces a scope of work also produces the follow-up email and the project brief. That is the point at which it stops being a prompt and starts being an internal tool. If you want that wired into the systems your team already uses, that is the work 67 Digital does.
In the file
I need to label support tickets that come in Arabic and English with consistent categories in both languages.
Here are my category pairs:
{list your categories in both languages, e.g. Billing / الفوترة, Technical Issue / مشكلة تقنية}
Below is a list of ticket subjects and snippets. Some are in Arabic, some in English, some mix both.
For each ticket:
1. Assign the most relevant category from my list
2. Provide both the English and Arabic category name
3. If the ticket mixes languages or uses transliterated terms, note that in a separate column
4. If none of my categories fit well, suggest a new bilingual pair
Return results in a table with columns: Ticket ID, Ticket Text, Category (EN), Category (AR), Language Notes, Suggested New Category.
Tickets:
{paste your ticket list here, with ID numbers}
If you see repeated issues that do not fit my existing categories, list them at the end with proposed bilingual category names.