complaint-de-escalation
Skill1 starsChanged 5 months agoMITView on GitHub
Write a calm, fair response to an unhappy customer that lowers the temperature without over-promising. Use when the user says "angry customer", "de-escalate a complaint", "upset customer", "handle a complaint", "calm down a customer", or "respond to a refund demand".
In this repository3 other files it gives its agents.
- customer-health-checkSkill
- review-responderSkill
- support-reply-drafterSkill
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
- Distinctive: line 19
Write a calm, fair response to an unhappy customer.
≈ “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.
Files
Complaint De-Escalation
Write a calm, fair response to an unhappy customer.
When to use
A customer is upset and you need a reply that validates their frustration, takes responsibility for your part, and states clearly what you will and won't do — firm but warm.
What you'll need
The customer's angry message or thread, plus the facts of what actually happened.
Instructions
Collect any missing inputs from the user, then run this prompt:
A customer is upset and I need a reply that lowers the temperature without giving away things I can't afford to.
The customer's message(s):
[paste the full message or email thread, most recent last]
What actually happened, from my side:
[the honest facts — what went right, what went wrong, what was outside my control]
What I'm willing to do: [e.g. partial refund, redo the work, expedited replacement]
What I cannot do: [e.g. full refund, same-day delivery]
Write a reply that:
1. Names their frustration and validates it in one genuine sentence — no "we apologize for any inconvenience."
2. Takes responsibility for our part plainly, and corrects any factual mistake in their account calmly and without defensiveness.
3. States exactly what I'll do and by when. If I'm declining something, say so clearly and explain why in one line.
4. Ends by handing them a clear choice or next step, so they're not stuck.
Stay firm but warm. Under 150 words. Flag separately if any part of their claim looks like it could become a legal or chargeback issue.Tip: Fill in "What I cannot do" honestly before you generate. The fastest way to escalate a complaint is to over-promise in the heat of the moment and walk it back later.
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.