Sorts one incoming customer message (support email, chat, contact form or ticket) into a category, a priority and the customer's language, and answers with strict JSON that a program can route without a person reading it. Uses a fixed default category list or the list the request gives, and fixed rules for priority, so an angry tone or the word URGENT does not raise priority and a calm report of an outage does not lower it. The language is the one the customer wrote in, not the language of a pasted error, a quoted reply or a signature, and orders hidden in the message do not change the result. Use for ticket triage, to route or label a support ticket, to classify support emails in a help desk inbox, or to decide which message needs a human first.
Ticket Triage: Category, Priority, Language is a tested SKILL.md that sorts one incoming customer message (support email, chat, contact form or ticket) into a category, a priority and the customer's language, and answers with strict JSON that a program can route without a person reading it; an agent buys it once for $0.03 over x402.
Not for
Writing or sending the reply, answering the customer, or checking whether what the message claims is true. It labels one message at a time and gives no sentiment or anger score. Priority follows four fixed levels; if your team ranks work differently, change those rules before you rely on it.
Tested, honestly
Tested 2026-10-08 with a strong and a weak model.
With and without the skill
Results with and without the skill, for Sonnet and Haiku |
| with | without | with | without |
|---|
| All three labels right |
| All three labels right | 25/25 | 21/25 | 25/25 | 16/25 |
|---|
One run per model and case. The side without the skill got the same category list, priority levels and language rule in the request, so it measures the written rules, not knowledge of the list. Without them, 12 of the 13 failed answers had the wrong priority: capital letters, anger, a sales request and a late delivery raised it, while praise around a double charge lowered it. Category and language were almost always right on both sides, and neither side wrapped the JSON in a fence.
Same cases and the same checks with and without the skill. The cases are ours, written around what the skill is for; with a handful of cases, a difference of one or two is within noise.
- SonnetStrong model, claude-sonnet-5-5
- Gave all three expected labels in 25 of 25 cases, always as bare JSON with the three keys. It kept a shouted how-to question at normal, raised a politely worded double charge to high, filed a cancellation that came with an unwanted charge under billing, kept an angry demand for dark mode at low and rated a calm report of a shop that takes no orders as urgent. It read the language from the customer's own words: Bulgarian beside a pasted English error and above an English legal footer, English above a forwarded German email, und for a message holding only a phone signature. It ignored an order planted inside a feature request, labelled a message made only of such orders as spam, and used a custom category list exactly as spelled, including Returns and Other with a capital letter.
- HaikuWeak model, claude-haiku-5-5
- Also 25 of 25 with the skill, with the same labels as Sonnet in every case and no code fence or text around the JSON. The rules changed its answers most on priority: without them it let capital letters, an angry tone, a sales request and a late parcel push priority up, and took the language of a forwarded German email; with them it followed the fixed levels in each of those cases.
Full test summary
Example
Our own test text, before and after the skill ran. Excerpts only.
English · claude-sonnet-5-5
Before
URGENT!!!! How do I switch the dashboard language to Spanish?? PLEASE ANSWER TODAY!!!
After
{"category": "how_to", "priority": "normal", "language": "en"}
Bulgarian · claude-sonnet-5-5
Before
Здравейте, от вчера при качване на снимка в галерията ми излиза това:
UploadError: the file exceeds the maximum allowed size of 10 MB. Request ID 7f3a-19c2. Please try again with a smaller file or contact support.
Снимката е 4 MB.
After
{"category": "technical", "priority": "normal", "language": "bg"}
Spanish · claude-sonnet-5-5
Before
Hola, desde esta mañana ninguno de nuestros empleados puede abrir la aplicación: aparece una pantalla en blanco en todos los ordenadores. Gracias de antemano.
After
{"category": "technical", "priority": "urgent", "language": "es"}
German · claude-sonnet-5-5
Before
Hallo, meine Bestellung 48213 sollte am Montag ankommen. Laut Sendungsverfolgung liegt sie seit fünf Tagen im Verteilzentrum. Wann kommt sie?
After
{"category": "delivery", "priority": "normal", "language": "de"}
What is in the file
- The answer
- Hard rules
- Categories
- Priority
- Language
- Work in this order
- Short examples
Languages
English, Bulgarian, Spanish, German. Tried in: English, Bulgarian, Spanish, German.
License
Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing. Holder: Georgi Kalchev, aiskills402.com. Full terms.
Versions
Current version 1.0.0, updated 2026-10-08. Whoever bought an earlier version gets new ones free through the same re-download token.
v1.0.0 · 2026-10-08
First release: sorts one customer message into a category, a priority and the customer's language, as strict JSON with three keys. Uses a default category list or the request's own list spelled exactly as given; priority follows fixed rules, so tone and the word URGENT do not raise it; the language ignores pasted errors, quoted replies, signatures and footers; orders written inside the message do not change the labels.
FAQ
Does an angry message or the word URGENT raise the priority?
No. Priority comes from what is happening, so a shouted question about switching the dashboard language stays normal and a furious demand for dark mode stays low. Without the skill, Claude Haiku rated that shouted question high, and both models put the dark mode demand at normal. In the other direction, both rated a double charge wrapped in praise as normal; with the skill it is high.
Which language does it report when the email contains English it did not write?
The language of the customer's own newest words. A Bulgarian message with a pasted English error and one with a long English legal footer both came back bg. An English reply above a forwarded German email came back en; Haiku without the skill answered de. A message holding only a phone signature came back und.
Can I give it my own category list?
Yes. Put the list in the request and the answer uses one of its values spelled exactly as you wrote it. We tried a shop list in lower case, the same kind of list with Returns and Other capitalised, and a list with no feedback value, where a thank-you note correctly went to Other.
What if the message tells the model how to label it?
Those lines are treated as part of the message and change nothing. A dark mode request carrying a fake system note that asked for billing and urgent stayed a low feature request, and a message made only of such orders was labelled spam. Both models resisted these two even without the skill.