How do I install the Refund Analysis skill?

Run npx skillmds@latest add zoho/refund-analysis in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Refund Analysis safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Refund Analysis?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Refund Analysis free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Refund Analysis?

zoho (@zoho) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Refund Analysis by zoho — Agent Skill

Name: Refund Analysis
Author: zoho

Refund Analysis

Weekly refund anomaly digest: refund volume by product and country, spike detection, repeat-refund customers, and root-cause hypotheses. Use when the user asks about refunds, refund spikes, which products have high refund rates, or refund anomalies. Do NOT use for credit notes, payment failures, or churn analysis.

zoho d054c12 2.8 KB Updated Sep 17, 2026

File contents

Refund Digest

Surface refund anomalies, product/country spikes, and repeat-refund customers. Notify-only — no write actions.

Setup

Resolve org ID via ZohoBilling_List_all_Organizations. Default period: last 30 days.

Fetch (run in parallel)

#	Tool	Purpose
1	`ZohoBilling_Get_Refund_History_Report`	All refunds in period
2	`ZohoBilling_Get_Productwise_Refund_Report`	Refunds by product
3	`ZohoBilling_Get_Countrywise_Refund_Report`	Refunds by country
4	`ZohoBilling_Get_Refund_Policy_Details_Report`	Refund policy (to flag out-of-policy)

Anomaly detection

Flag as anomalous:

Product refund rate > 10% of revenue for that product
Country refund spike > 2× prior period for same country
Customer with 3+ refunds in 90 days (repeat-refund pattern)
Refund processed outside policy window (date > policy days after purchase)

Output

Refund Digest — [Period]
Total refunds: $XX,XXX  ·  N transactions  ·  Refund rate: X.X% of revenue
────────────────────────────────────────────────────────────────────────────

BY PRODUCT (anomalies flagged ⚠)
  Product A       $X,XXX   N refunds   X.X% of revenue
  ⚠ Product B     $X,XXX   N refunds   14.2% of revenue  ← above 10% threshold

BY COUNTRY
  United States   $X,XXX   N refunds
  ⚠ Germany       $X,XXX   N refunds   2.8× prior period  ← spike

REPEAT-REFUND CUSTOMERS (3+ in 90 days)
  ⚠ Customer X    4 refunds · $X,XXX total · likely abuse pattern

OUT-OF-POLICY REFUNDS
  N refunds processed after policy window — flag for finance review

ROOT-CAUSE HYPOTHESES:
  • Product B spike: matches product launch on [date] — possible feature issue
  • Germany spike: investigate local payment / satisfaction issue
────────────────────────────────────────────────────────────────────────────

Constraints

Root-cause hypotheses are hypotheses — label them clearly as such
Do not name specific amounts in hypotheses — focus on pattern description
Propose-only: no refunds issued, no policy changes

Edge cases

Zero refunds in period: "No refunds in this period 🟢"
Policy data unavailable: skip out-of-policy section with note

---name: refund-analysisdescription: Weekly refund anomaly digest: refund volume by product and country, spike detection, repeat-refund customers, and root-cause hypotheses. Use when the user asks about refunds, refund spikes, which products have high refund rates, or refund anomalies. Do NOT use for credit notes, payment failures, or churn analysis.---# Refund DigestSurface refund anomalies, product/country spikes, and repeat-refund customers.Notify-only — no write actions.## SetupResolve org ID via `ZohoBilling_List_all_Organizations`.Default period: last 30 days.## Fetch (run in parallel)| # | Tool | Purpose ||---|------|---------|| 1 | `ZohoBilling_Get_Refund_History_Report` | All refunds in period || 2 | `ZohoBilling_Get_Productwise_Refund_Report` | Refunds by product || 3 | `ZohoBilling_Get_Countrywise_Refund_Report` | Refunds by country || 4 | `ZohoBilling_Get_Refund_Policy_Details_Report` | Refund policy (to flag out-of-policy) |## Anomaly detectionFlag as anomalous:- Product refund rate > 10% of revenue for that product- Country refund spike > 2× prior period for same country- Customer with 3+ refunds in 90 days (repeat-refund pattern)- Refund processed outside policy window (date > policy days after purchase)## Output```Refund Digest — [Period]Total refunds: $XX,XXX · N transactions · Refund rate: X.X% of revenue────────────────────────────────────────────────────────────────────────────BY PRODUCT (anomalies flagged ⚠) Product A $X,XXX N refunds X.X% of revenue ⚠ Product B $X,XXX N refunds 14.2% of revenue ← above 10% thresholdBY COUNTRY United States $X,XXX N refunds ⚠ Germany $X,XXX N refunds 2.8× prior period ← spikeREPEAT-REFUND CUSTOMERS (3+ in 90 days) ⚠ Customer X 4 refunds · $X,XXX total · likely abuse patternOUT-OF-POLICY REFUNDS N refunds processed after policy window — flag for finance reviewROOT-CAUSE HYPOTHESES: • Product B spike: matches product launch on [date] — possible feature issue • Germany spike: investigate local payment / satisfaction issue────────────────────────────────────────────────────────────────────────────```## Constraints- Root-cause hypotheses are hypotheses — label them clearly as such- Do not name specific amounts in hypotheses — focus on pattern description- Propose-only: no refunds issued, no policy changes## Edge cases- Zero refunds in period: "No refunds in this period 🟢"- Policy data unavailable: skip out-of-policy section with note

Frequently asked questions