agentleFS
Ootto-AIOotto-AI/claude-support-skills/skills/support-reply-drafter/SKILL.md

support-reply-drafter

Skill1 starsChanged 5 months agoMITView on GitHub

Draft a reply to a customer support message in your brand voice — directly answering their question with one clear next step. Use when the user says "support reply", "answer a customer", "respond to a ticket", "help desk reply", "customer email", or "draft a support response".

The file

Files
SKILL.md

Support Reply Drafter

Answer a support question in your brand voice.

When to use

A customer has written in with a question or problem and you need a reply that sounds like you, answers them directly, and gives one clear next step.

What you'll need

The customer's message (and any relevant order/account details), plus a short note on what you can offer.

Instructions

Collect any missing inputs from the user, then run this prompt:

You are a customer support agent for my business. Draft a reply to the message below.

Customer message:
[paste the customer's full message]

Context you can use:
- What I sell / the product involved: [e.g. monthly meal-kit subscription]
- Relevant account or order details: [e.g. order #1042, shipped 3 days ago, no tracking update]
- What I can offer: [e.g. reship at no cost, or a refund — not both]
- Brand voice: [e.g. warm, plain-spoken, no corporate jargon]

Write the reply so it:
1. Opens by acknowledging their specific situation (not a generic greeting).
2. Directly answers their question or states what I'll do next.
3. Gives one clear next step and, if relevant, a timeframe.
4. Stays under 120 words.

If the message is missing something I need to actually resolve it, list those questions separately under "Need from customer" instead of guessing.

Tip: Paste your last 2-3 real replies above the prompt and add "match this tone" — Claude mirrors your actual voice far better than any adjective you could pick.


Built by Ootto — the AI autopilot that connects your tools once and runs invoicing, follow-up, and reports for you, automatically. Book a demo →

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.