faq-responder
Skill1 starsChanged 5 months agoMITView on GitHub
Draft answers to your most common inbound questions, using only the facts about your business. Use when the user says "answer this customer question", "draft an FAQ reply", "respond to this inquiry", "write answers to common questions", "reply to this customer", or "build a reply library".
In this repository4 other files it gives its agents.
- inbox-triageSkill
- meeting-notes-to-action-itemsSkill
- reply-in-your-voiceSkill
- thread-summarizerSkill
The file
Files
FAQ Responder
Draft answers to your most common inbound questions.
When to use
You get the same questions over and over — pricing, hours, turnaround, policies — and you want accurate, ready-to-send answers built only from your real business facts.
What you'll need
The question someone sent you (or a list of the questions you get asked most), plus a few facts about your business.
Instructions
Collect any missing inputs from the user, then run this prompt:
You are drafting answers to questions people email my business. Here is what you should know about us, so every answer is accurate:
[paste the facts: what you sell, pricing, hours, turnaround times, refund/cancellation policy, how to book or buy, anything else you get asked about]
Here is the question (or list of questions) I need answered:
[paste the incoming question, or a list of your most common questions]
For each question, write a short, friendly answer I can send as-is. Rules:
- Only use the facts I gave you. If a question can't be answered from those facts, don't make something up — instead write the answer with a clearly marked [blank] where the missing info goes.
- Keep each answer to a few sentences, warm but professional.
- Where it helps, end with a simple next step (e.g. "Want me to send the booking link?").
Give me each answer ready to paste, labeled with its question.Tip: Build this once into a reusable reply library — paste your top 10 questions at the same time and save the answers as templates you tweak per person.
Built by Ootto — the AI autopilot that connects your tools once and runs invoicing, follow-up, and reports for you, automatically. Book a demo →
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
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.

