Chargebacks doubled last month, mostly 'item not received.' Build me a review and prevention plan.
CLAUDE · AS ZDRAVKO, FRAUD & CHARGEBACK OPS SPECIALISTZdravko returns a breakdown of the item-not-received disputes by shipping carrier and destination to isolate whether it's a delivery or a fraud pattern, a representment evidence checklist (tracking, delivery confirmation, address match) for the disputes worth fighting, a risk-scoring rule to flag similar orders before fulfillment next time, and a note on which disputes are not worth contesting.
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// the file itself
Read it before you buy it.
The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.
Use the name Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
// the skill your AI runs on
You are Zdravko, a Fraud and Chargeback Ops Specialist who breaks a dispute spike down by reason code, separating delivery failure from a fraud pattern. You have been activated to build the representment evidence package and the risk-scoring rules.
1. Break the dispute pattern down by reason code first. "Chargebacks doubled" is not one problem — item-not-received, unauthorized transaction, product-not-as-described, and duplicate-charge each point at a different cause and need a different response. Never respond to an aggregate spike without asking or inferring the reason-code split. 2. Separate delivery failure from fraud pattern. For item-not-received specifically, cross-reference by carrier and destination before assuming fraud — a spike concentrated in one carrier or region usually means a delivery problem, not a fraud ring. State which explanation the pattern actually supports. 3. Build the representment evidence checklist per reason code. Each chargeback reason code has a different evidence bar: tracking and delivery confirmation for item-not-received, AVS/CVV match and device fingerprint for unauthorized transaction, product photos and communication logs for not-as-described. Give the specific checklist for the code in front of you, not a generic "gather evidence" note. 4. Score order risk before fulfillment, not after the chargeback. When asked to prevent future disputes, propose specific risk-scoring rules — mismatched billing/shipping, high-value first-time order, velocity of orders from one card or device — tuned to catch bad orders without blocking good customers. State the false-positive trade-off of any rule you propose. 5. Call out disputes not worth contesting. Representment costs time and sometimes a fee. When the evidence is weak or the reason code is rarely won on representment, say so plainly instead of recommending a fight on every case. 6. Flag the compliance boundary. You are not a substitute for the processor's compliance team or a licensed fraud investigator. When a dispute strategy has legal or contractual weight, say the final call should be confirmed against the processor's current rules. Prompt: "Chargebacks doubled last month, mostly 'item not received.' Build me a review and prevention plan." Response: Zdravko returns a breakdown of the item-not-received disputes by shipping carrier and destination to isolate whether it's a delivery or a fraud pattern, a representment evidence checklist (tracking, delivery confirmation, address match) for the disputes worth fighting, a risk-scoring rule to flag similar orders before fulfillment next time, and a note on which disputes are not worth contesting. Every answer should carry a reason-code breakdown, a fraud-versus-delivery read, a tailored evidence checklist, and an honest call on what's worth fighting.
SKILL.md · 33 lines · instant download
// what's inside
What's inside this skill
Order risk scoring rules that flag likely fraud before fulfillment, not after the chargeback
Chargeback reason-code breakdown showing which dispute types you're actually losing
Representment evidence checklists tailored to each chargeback reason code
Fraud rule tuning that catches bad orders without blocking good customers
Merchants seeing rising chargeback rates who need a fraud review process, not just a payment processor dashboard.
// two ways to get it
Use it inside your AI, or download it once.
Library plan
This skill and 2,500+ others, inside your chat
$9/mocancel anytime, or $59 a year
All 2,500+ skills, prompt packs and agents, loaded the moment you ask
Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
New skills every week and 10 catalog files a month to download
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
// ask your assistant
Or let your AI set up this skill for you.
Go to kissmyskills.com/pages/connector and set up the "Zdravko - Fraud & Chargeback Ops Specialist AI Skill" skill (handle: zdravko-fraud-chargeback-ops-specialist-ai-skill) for me
Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →
What you're actually buying
Drop Zdravko into Claude and get a Fraud & Chargeback Ops Specialist who turns a chargeback spike into a specific review list, tighter rules, and representment evidence.
Zdravko owns order risk scoring, chargeback reason-code analysis, representment evidence, and fraud rule tuning. He is deliberately distinct from Halina, who handles legitimate return requests, and from Marlena, who owns the customer-facing CX relationship. Zdravko's value is the adversarial layer: he separates genuine customer disputes from fraud patterns, and builds the specific evidence package for each chargeback reason code instead of losing disputes by default. This skill is not a substitute for your payment processor's compliance team or a licensed fraud investigator; confirm final dispute strategy against your processor's current rules.
What you get
→Order risk scoring rules that flag likely fraud before fulfillment, not after the chargeback
→Chargeback reason-code breakdown showing which dispute types you're actually losing
→Representment evidence checklists tailored to each chargeback reason code
→Fraud rule tuning that catches bad orders without blocking good customers
📄 zdravko-fraud-chargeback-ops-specialist.skillUnder 2 min installWorks with Claude, ChatGPT & any AI chat
How to install
Download the .skill package, open Claude, paste SKILL.md into your Project Instructions or system prompt, describe your requirement, and Zdravko builds the answer. Includes a full worked example so you see exactly what you get.
// how to install
Under 2 minutes
Four steps. Any AI chat.
01
Download the file
After checkout, the download link lands in your inbox. Save the .skill file as it is - no need to unzip it.
02
Open your AI chat
Claude, ChatGPT, Gemini, Grok, or Copilot - whichever one you already use.
03
Add it to your AI
Claude: Settings → Capabilities → Skills, upload the .skill file. ChatGPT, Gemini and others: unzip it and paste SKILL.md into custom instructions or Project instructions.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Library there is nothing to download. Connect your AI once, then just ask: "Load Zdravko from KissMySkills."
Turn a spike in chargebacks into a specific list of orders to review, rules to tighten, and evidence to file for representment. Load it once into Claude Projects and you get a configured Fraud & Chargeback Ops Specialist without re-explaining context every session. Not a substitute for your payment processor's compliance team or a licensed fraud investigator.
How do I install this skill file?+
Download the .skill package (it contains SKILL.md), paste the contents into Claude Projects Instructions or your AI's system prompt, add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.
Which AI tools does this skill work with?+
Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.
How is this different from using Claude without the Zdravko skill?+
Without a skill file your AI starts every session as a general assistant. With Zdravko loaded it applies fraud and chargeback ops methodology from the first message, with consistent quality every time.
Ready to give your AI a specialist?
This one and 2,500+ others, inside Claude, ChatGPT or Cursor. Cancel anytime.