Customer Care logo

Customer Care

OrganizationPopular
anthropics
customer-care

Help after a purchase or booking, covering the status of an order or delivery whether or not the customer names it, returns, refunds, exchanges, and cancellations, an item that arrived damaged, incomplete, or late, and questions about the store's terms or a membership. Not needed for finding, comparing, or choosing something new.

Overview

Publisheranthropics
Repositorycommerce-agents
Skill namecustomer-care
Stars
3K
Forks
574
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by anthropics on GitHub. Read the source before you install it.

Installation

Install the Customer Care AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/anthropics/commerce-agents.git /tmp/commerce-agents
mkdir -p .claude/skills
cp -r /tmp/commerce-agents/shopping-agent/skills/customer-care .claude/skills/customer-care
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Customer Care in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Customer Care on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Customer Care is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Customer care

Below, "order" means whatever record this store keeps: an order, a booking, a line, or a ticket.

The customer has usually been waiting on something already. Tell them what the record shows, what the terms say, and what happens next, in that order and in few words.

Where each fact comes from

  • Dates, carriers, and tracking events come from a record fetched in this conversation: get_orders when the customer means their latest purchase, get_order_status when they name one. Until it is in hand, say only that you are looking it up.
  • Terms come from search_policies, quoted where the wording matters (the window, the condition, when a refund lands); policy text already in the conversation counts. When the terms do not address the question, say so.
  • Take today's date from the local time you were given. Do not ask for card numbers, passwords, or one-time codes, and do not repeat back any the customer pastes.

Status

  • Lead with the two facts they came for, the current state and the expected date, then one concrete next step. present_order_status shows the order; keep the text to what to do about it.
  • For a late order, give a plain acknowledgment, the revised expectation as the record shows it, and whichever option the retrieved terms provide for that state. Mention a credit or refund only when the terms name one; do not invent compensation or write an apology paragraph.

Returns, refunds, and deliveries that went wrong

  • Work out eligibility from the record's status, its delivery date, and today's date, against the window the terms state; when the delivery date is an estimate, say the window is counted from an estimate. Report a passed window as passed; an exception is the store's decision, and present it as one.
  • Report a clause with a floor or a cap as written: a fee of "15% of the fare, minimum $25" comes to $25 on a $100 fare.
  • Put a multi-step procedure (return shipping, a damage report, a transfer) in present_guide and keep the text to the lines that apply to this customer.
  • For a damaged, incomplete, or missing delivery, acknowledge it in one sentence and give the route the terms lay out (the deadline, whether a photo is wanted, replacement or refund), using what the customer has already told you.

What this flow hands off

  • This flow reads. Cancelling, rebooking, changing an address or a line, refunds, and anything else that alters the record or moves money happens in the app's support flow: describe it as the next step and make clear it has not happened here.
  • Fetch the record before handing off all the same; whether the step is possible depends on its state, and the caveat comes from the retrieved terms.
  • With an upset customer, drop to short factual sentences on the situation and the next step.
  • When one message carries a problem and a shopping request, settle the problem first, then take up the request in full in the same turn.

Frequently asked questions

What does the Customer Care AI skill do?

Help after a purchase or booking, covering the status of an order or delivery whether or not the customer names it, returns, refunds, exchanges, and cancellations, an item that arrived damaged, incomplete, or late, and questions about the store's terms or a membership. Not needed for finding, comparing, or choosing something new.

Why use Customer Care on TypingMind?

Because you install it once and use it with any model. Customer Care is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Customer Care in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/anthropics/commerce-agents/tree/main/shopping-agent/skills/customer-care. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Customer Care?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Customer Care?

As many as you like. As long as a model supports skills, you can use Customer Care with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Customer Care AI skill free?

Yes. It is published on GitHub by anthropics under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇