agentleFS
ntaffziintaffzii/Skill-Agents/skills/thai/thai-customer-service/SKILL.md

thai-customer-service

Skill4 starsChanged 3 months agoMITView on GitHub

Use this skill for any task drafting a Thai-language customer-service reply — apologies, status updates, refund/return scripts, or auto-replies for LINE OA, Facebook Page, Shopee, Lazada, Instagram DM, TikTok Shop, or similar channels. Trigger on "reply ลูกค้า", "ตอบแชท", "LINE OA", "Shopee ตอบลูกค้า", "ขอโทษลูกค้า", "refund script", "customer service Thai". If the message is internal (to a colleague, not a customer), this skill's apology-ladder register doesn't apply — use plain professional Thai instead.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Does not cover legal liability language for safety-related complaints — escalate those to a human/legal review rather than auto-generating …

    line 60

≈ “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

Thai Customer Service Replies

Overview

Using the same apology intensity for a 1-day shipping delay and a wrong/damaged item both under- and over-shoots — Thai customer-service register has a graded apology ladder, and picking the wrong rung reads as either dismissive or oddly dramatic. This skill maps severity to the right phrase and gives channel-specific tone guidance, since a LINE OA reply and a Shopee platform-mediated reply don't read the same even for an identical situation.

When to use

  • Reply ลูกค้าที่ร้องเรียน/บ่น/ขอเงินคืน บน LINE OA, Facebook Page, Shopee, Lazada, IG DM, TikTok Shop
  • เขียนข้อความแจ้งสถานะ (delay, order update, restock)
  • ร่าง auto-reply / FAQ response ที่ยังต้องฟังดูเป็นมนุษย์ ไม่ใช่บอทแข็งๆ
  • Choosing the right apology intensity for a given severity of complaint

When NOT to use

  • Internal communication to a colleague or vendor — that's a different register, not the customer-facing apology ladder
  • Formal written complaint response requiring legal review (e.g. involving compensation liability) — draft here for tone, but have anything with real financial/legal exposure reviewed

Core knowledge

Apology ladder — match intensity to severity, don't default to the strongest phrase every time (it reads as insincere when overused) or the mildest (reads as dismissive for a real failure):

PhraseSeverityExample trigger
ขออภัย(ค่ะ/ครับ)ในความไม่สะดวกMildMinor delay, small inconvenience, a question that took a while to answer
ขออภัยเป็นอย่างยิ่งModerateOrder delay beyond promised window, out-of-stock after order confirmed
ขอโทษอย่างสูงHighWrong item sent, damaged item, billing error, clearly the seller's fault
ขอแสดงความเสียใจอย่างยิ่งSevereMajor failure, safety/health concern, repeated failure after prior complaint

Pair the apology with a concrete next step every time — an apology with no resolution offered reads as empty regardless of which rung is used.

Channel tone differences:

ChannelTypical register
LINE OAMost personal/warm of the group — emoji, stickers, first-name-adjacent tone common; closest to a 1:1 chat
Facebook Page / MessengerPersonal but slightly more public-facing (comments are visible) — keep resolution details in DM, acknowledge publicly
Shopee / Lazada / TikTok Shop (marketplace chat)More procedural — platform policies constrain what can be promised (refund timing, dispute process); stick to what the seller can actually control and reference the platform's own return/refund flow rather than inventing terms
Instagram DMCasual-personal, similar to LINE OA but often shorter messages

Structure for a complaint reply: (1) acknowledge specifically what went wrong — not a generic "we're sorry for any inconvenience" that doesn't reference the actual issue, (2) apologize at the matched severity, (3) state the concrete resolution and timeline, (4) close with a way to follow up if unresolved.

Common mistakes

  1. Using ขอโทษอย่างสูง or ขอแสดงความเสียใจอย่างยิ่ง for a trivial delay — reads as performative rather than sincere.
  2. Using only ขออภัยในความไม่สะดวก for a genuinely serious failure (wrong item, damaged goods) — reads as dismissive.
  3. A generic apology with no acknowledgment of the specific problem the customer described.
  4. Promising a resolution the seller can't actually deliver on a marketplace platform (e.g. an instant refund that has to go through the platform's dispute process).
  5. Matching LINE OA's warm, emoji-heavy tone on a marketplace platform where the register expected is more procedural.
  6. Public reply on Facebook/IG comments revealing personal order details that should move to DM.

Known limitations

  • Exact refund/return timelines and policies are platform- and seller-specific (Shopee, Lazada, and TikTok Shop each have their own dispute-resolution windows that change over time) — this skill supplies tone and structure, not current platform policy figures; verify those against the seller's own account/platform dashboard.
  • Does not cover legal liability language for safety-related complaints — escalate those to a human/legal review rather than auto-generating a final response.

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.