Individual skill

refund-deescalation

Handles angry customers and refund requests with a validate-own-act de-escalation sequence and a refund decision matrix that weighs refund cost against customer LTV and chargeback risk. Use when someone asks "this customer is furious, what do I say", "should I approve this refund", "how do I deny a refund without losing the customer", or a conversation is emotionally charged. Do NOT use for routine, non-charged ticket responses - use support-ticket-reply instead; for diagnosing systemic patterns behind falling satisfaction scores, use csat-root-cause.

skills/refund-deescalation/SKILL.md

Read pinned source

Source commit 97a13607d669157a4a16d5ba79b77f208319f7b9

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Not checked yet
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
24
Repository last updated
Oct 13, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Refund and De-escalation

An angry customer is not attacking the agent - they are in pain and looking for someone to fix it. De-escalation is not about calming the customer down; it is about giving them a reason to trust the company again. The costly mistake this prevents is the two-sided failure: refunding reflexively (training customers to escalate for money) or denying rigidly (converting a $49 refund request into a chargeback, a public review, and a lost account worth far more).

## Operating procedure

### Step 1: Gather inputs

Before responding, establish:

1. The exact thing that went wrong, in the customer's words.
2. The refund amount requested versus the customer's LTV (tenure × monthly value, or total historical spend). Label an LTV estimate a guess if the data is thin.
3. Whether the failure was the company's fault, ambiguous, or the customer's misunderstanding.
4. Contact history on this issue - how many touches so far.
Back to top