Agent skill

Shopify Admin Partial Refund Pattern Detector

by 40RTY-ai in 40RTY-ai/shopify-admin-skills

Read-only: surfaces orders with multiple partial refunds or unusually high partial-refund-to-total ratios that may indicate fraud, chronic complaints, or process gaps.

MITAuto-check passed

Install Shopify Admin Partial Refund Pattern Detector

skills CLI
$ npx skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-partial-refund-pattern-detector -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install 40RTY-ai/shopify-admin-skills shopify-admin-partial-refund-pattern-detector --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/40RTY-ai/shopify-admin-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/order-intelligence/shopify-admin-partial-refund-pattern-detector .claude/skills/shopify-admin-partial-refund-pattern-detector && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
shopify-admin-partial-refund-pattern-detector
GitHub stars
194
Token cost
~1.7k tokens
SKILL.md length
475 words
Files
1
Skills in repo
116
Repo updated
First seen
Licence
MIT

At a glance

Read-only: surfaces orders with multiple partial refunds or unusually high partial-refund-to-total ratios that may indicate fraud, chronic complaints, or process gaps.

  • Works in 4 steps: OPERATION: orders — query → For each order, count refunds and sum… → Flag orders meeting either condition:… → …
  • SKILL.md covers Purpose, Prerequisites, Parameters and Safety, plus 6 more sections
  • Calls shopify

What it does

Shopify Admin Partial Refund Pattern Detector is an agent skill from 40RTY-ai/shopify-admin-skills. Read-only: surfaces orders with multiple partial refunds or unusually high partial-refund-to-total ratios that may indicate fraud, chronic complaints, or process gaps.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Claude Code, Cursor, Codex, Gemini CLI

It works with Shopify. The repository describes itself as: Community-maintained AI agent skills for operating Shopify stores — workflows, optimization, reports and more. The licence is MIT.

Example prompts

  • “/shopify-admin-partial-refund-pattern-detector”

Requirements

  • Compatibility (from SKILL.md): Claude Code, Cursor, Codex, Gemini CLI

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. OPERATION: orders — query
  2. For each order, count refunds and sum totalRefundedSet.shopMoney.amount. Compute ratio = total_refunded / order_total.
  3. Flag orders meeting either condition: refund_count >= min_partials OR ratio >= ratio_threshold (and ratio < 1.0 so fully refunded orders…
  4. Group flagged orders by customer.id to surface repeat-offender customers (more than one flagged order in the window).

What it can do on your machine

Read from SKILL.md and the folder at commit 6765cb4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • shopify

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

  • Compatibility

    Claude Code, Cursor, Codex, Gemini CLI

    From compatibility in the SKILL.md frontmatter.

Context cost

Shopify Admin Partial Refund Pattern Detector loads about 1.7k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 475 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from 40RTY-ai/shopify-admin-skills at commit 6765cb4, republished under its MIT licence (© 40RTY-ai). 475 words, ~1,665 tokens.

Download SKILL.mdSave it as .claude/skills/shopify-admin-partial-refund-pattern-detector/SKILL.md (or your agent's skills folder).
name
shopify-admin-partial-refund-pattern-detector
description
Read-only: surfaces orders with multiple partial refunds or unusually high partial-refund-to-total ratios that may indicate fraud, chronic complaints, or process gaps.
compatibility
Claude Code, Cursor, Codex, Gemini CLI
role
order-intelligence
toolkit
shopify-admin, shopify-admin-execution
api_version
2025-01
graphql_operations
orders:query
status
stable

Purpose

Scans recent orders, extracts every refund, and flags orders that have either (a) two or more partial refunds, or (b) a partial-refund-to-order-total ratio above a configurable threshold. These patterns frequently indicate friendly fraud (incremental claims), an unhappy repeat customer pattern, or a staff workflow gap (refunding piecemeal instead of issuing one full credit). Read-only — no mutations.

Prerequisites

  • Authenticated Shopify CLI session: shopify store auth --store <domain> --scopes read_orders
  • API scopes: read_orders

Parameters

ParameterTypeRequiredDefaultDescription
storestringyes—Store domain (e.g., mystore.myshopify.com)
days_backintegerno90Lookback window for orders to analyze
min_partialsintegerno2Minimum number of partial refunds to flag an order
ratio_thresholdfloatno0.5Flag orders where total refunded / order total exceeds this ratio (still partial, i.e. below 1.0)
min_order_valuefloatno25Skip low-value orders below this amount
formatstringnohumanOutput format: human or json

Safety

ℹ️ Read-only skill — no mutations are executed. Safe to run at any time. Flagged orders are advisory — confirm with refund notes and customer history before taking action against a customer account.

Workflow Steps

  1. OPERATION: orders — query Inputs: query: "created_at:>='<NOW - days_back days>' financial_status:partially_refunded", first: 250, select refunds { id, createdAt, totalRefundedSet, note }, totalPriceSet, customer, pagination cursor Expected output: All partially refunded orders with full refund history; paginate until hasNextPage: false

  2. For each order, count refunds and sum totalRefundedSet.shopMoney.amount. Compute ratio = total_refunded / order_total.

  3. Flag orders meeting either condition: refund_count >= min_partials OR ratio >= ratio_threshold (and ratio < 1.0 so fully refunded orders are excluded).

  4. Group flagged orders by customer.id to surface repeat-offender customers (more than one flagged order in the window).

GraphQL Operations

graphql
# orders:query — validated against api_version 2025-01
query PartialRefundPatterns($query: String!, $after: String) {
  orders(first: 250, after: $after, query: $query) {
    edges {
      node {
        id
        name
        createdAt
        displayFinancialStatus
        totalPriceSet {
          shopMoney {
            amount
            currencyCode
          }
        }
        totalRefundedSet {
          shopMoney {
            amount
            currencyCode
          }
        }
        refunds {
          id
          createdAt
          note
          totalRefundedSet {
            shopMoney {
              amount
              currencyCode
            }
          }
          refundLineItems(first: 50) {
            edges {
              node {
                quantity
                lineItem {
                  id
                  title
                  sku
                }
              }
            }
          }
        }
        customer {
          id
          displayName
          defaultEmailAddress {
            emailAddress
          }
          numberOfOrders
        }
      }
    }
    pageInfo {
      hasNextPage
      endCursor
    }
  }
}
Show full SKILL.md (206 more words)Show less

Session Tracking

Claude MUST emit the following output at each stage. This is mandatory.

On start, emit:

╔══════════════════════════════════════════════╗
║  SKILL: Partial Refund Pattern Detector      ║
║  Store: <store domain>                       ║
║  Started: <YYYY-MM-DD HH:MM UTC>             ║
╚══════════════════════════════════════════════╝

After each step, emit:

[N/TOTAL] <QUERY|MUTATION>  <OperationName>
          → Params: <brief summary of key inputs>
          → Result: <count or outcome>

On completion, emit:

For format: human (default):

══════════════════════════════════════════════
PARTIAL REFUND PATTERN REPORT  (<days_back> days)
  Partially refunded orders:   <n>
  Flagged (multi-refund):      <n>
  Flagged (high ratio):        <n>
  Repeat-flagged customers:    <n>

  Top flagged customers by amount:
    <customer>  Orders: <n>  Refunded: $<n>  Ratio: <pct>%
  Output: partial_refund_patterns_<date>.csv
══════════════════════════════════════════════

For format: json, emit:

json
{
  "skill": "partial-refund-pattern-detector",
  "store": "<domain>",
  "period_days": 90,
  "partially_refunded_orders": 0,
  "flagged_multi_refund": 0,
  "flagged_high_ratio": 0,
  "repeat_flagged_customers": 0,
  "output_file": "partial_refund_patterns_<date>.csv"
}

Output Format

CSV file partial_refund_patterns_<YYYY-MM-DD>.csv with columns: order_name, order_id, customer_email, customer_lifetime_orders, order_total, total_refunded, refund_ratio, refund_count, flag_reason, first_refund_at, last_refund_at

Error Handling

ErrorCauseRecovery
THROTTLEDAPI rate limit exceededWait 2 seconds, retry up to 3 times
Order has refund but totalRefundedSet is zeroRefund recorded as $0 (note only, no money moved)Skip from ratio calc, count refund
Customer is null (guest order)No customer attachedGroup by email instead of customer ID
No partially refunded ordersClean windowExit with summary: 0 flagged

Best Practices

  • Combine min_partials: 2 and ratio_threshold: 0.5 for the most useful signal — single small partial refunds are usually legitimate.
  • Sort by refund_ratio descending: high ratios on high-value orders are the strongest fraud signal.
  • A repeat-flagged customer with numberOfOrders > 5 is often a chronic complainer, not a fraudster — review the refund notes before action.
  • Use this skill quarterly alongside order-risk-report to detect post-purchase fraud that fraud filters miss at checkout.
  • Refund note content frequently reveals the pattern (e.g., "item missing" repeated three times) — read the notes before flagging a customer.

© 40RTY-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/order-intelligence/shopify-admin-partial-refund-pattern-detector of 40RTY-ai/shopify-admin-skills.

Open the folder on GitHubat commit 6765cb4

Compare with similar skills

Shopify Admin Partial Refund Pattern Detector next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Shopify Admin Partial Refund Pattern Detector compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Shopify Admin Partial Refund Pattern Detector this skill40RTY-ai/shopify-admin-skills194—~1.7kAutomated safety check: PassMIT
ShopifyShopify/Shopify-AI-Toolkit589—~4.2kAutomated safety check: PassMIT
E-commerce Visual Copywritingfeichanggege/ecommerce-visual-copywriting-skill853—~1.3kAutomated safety check: PassMIT
Reviewing Pull RequestsShopify/shopify-app-js543—~1.9kAutomated safety check: PassMIT
Better Designmarvkr/better-design254—~1.2kAutomated safety check: PassMIT
Tracking Discoverjtrackingai/analytics-tracking-automation1421 repos~614Automated safety check: PassApache-2.0

Similar skills

  • Shopify

    Shopify/Shopify-AI-Toolkit

    Official

    Build anything on Shopify. An agent skill from Shopify/Shopify-AI-Toolkit.

    589 GitHub stars~4.2k tokensUpdated today
    Backend & APIsAuto-check passed
  • E-commerce Visual Copywriting

    feichanggege/ecommerce-visual-copywriting-skill

    Turns product details, packaging, target platform and audience into an executable e-commerce image plan with copy, storyboards, image prompts and a compliance review.

    853 GitHub stars~1.3k tokensUpdated 21 days ago
    Writing & ContentAuto-check passed
  • Reviewing Pull Requests

    Shopify/shopify-app-js

    Official

    Reviews pull requests for Shopify/shopify-app-js with comprehensive analysis including semver compliance (MAJOR/MINOR/PATCH classification), single responsibility validation, pattern consistency…

    543 GitHub stars~1.9k tokensUpdated today
    DevelopmentAuto-check passed
  • Better Design

    marvkr/better-design

    Build, improve, and review production interfaces with the Better Design MCP.

    254 GitHub stars~1.2k tokensUpdated 15 days ago
    Frontend & DesignAuto-check passed
  • Tracking Discover

    jtrackingai/analytics-tracking-automation

    A skill your agent uses when the user wants crawl coverage, platform detection, dataLayer discovery, or a fresh artifact directory before grouping and schema work.

    142 GitHub starsUsed in 1 repo~614 tokens
    Marketing & SEOAuto-check passed
  • Liquid Theme A11y

    benjaminsehl/liquid-skills

    Implement WCAG 2.2 accessibility patterns in Shopify Liquid themes.

    120 GitHub stars~3.2k tokensUpdated 2 mo ago
    Frontend & DesignAuto-check passed

More from 40RTY-ai/shopify-admin-skills

All 116 skills in this repo
  • Shopify Admin Delivery Time Analysis

    40RTY-ai/shopify-admin-skills

    Read-only: calculates average time from fulfillment creation to delivery by carrier using fulfillment and order data.

    194 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Shopify Admin Shipping Cost Analysis

    40RTY-ai/shopify-admin-skills

    Read-only: aggregates shipping revenue charged to customers vs.

    194 GitHub starsUsed in 1 repo~1.4k tokens
    Auto-check passed
  • Shopify Admin Abandoned Cart Recovery

    40RTY-ai/shopify-admin-skills

    Query checkouts abandoned in the last N days, generate unique discount codes per customer, and tag them for re-engagement.

    194 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Shopify Admin Address Correction

    40RTY-ai/shopify-admin-skills

    Update the shipping address on an unfulfilled order before it ships.

    194 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Shopify Admin Agentic Crawler Access

    40RTY-ai/shopify-admin-skills

    Edit the theme's robots.txt.liquid to explicitly allow AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, OAI-SearchBot, Amazonbot) so AI assistants are permitted to read the catalog.

    194 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Rewrite thin product descriptions into structured, fact-rich copy (materials, fit, use-cases, the words shoppers actually type) so AI agents have something concrete to quote and match.

    194 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Shopify Admin Partial Refund Pattern Detector

What does Shopify Admin Partial Refund Pattern Detector do?

Read-only: surfaces orders with multiple partial refunds or unusually high partial-refund-to-total ratios that may indicate fraud, chronic complaints, or process gaps. Shopify Admin Partial Refund Pattern Detector is an agent skill from 40RTY-ai/shopify-admin-skills. Read-only: surfaces orders with multiple partial refunds or unusually high partial-refund-to-total ratios that may indicate fraud, chronic complaints, or process gaps.

How do I install Shopify Admin Partial Refund Pattern Detector in Claude Code?

Run `npx skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-partial-refund-pattern-detector -a claude-code`. Or copy the skill folder (skills/order-intelligence/shopify-admin-partial-refund-pattern-detector in 40RTY-ai/shopify-admin-skills) into .claude/skills/shopify-admin-partial-refund-pattern-detector in your project. Claude Code loads it when a task matches its description.

How do I install Shopify Admin Partial Refund Pattern Detector in Codex?

Run `npx skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-partial-refund-pattern-detector -a codex`. Or copy the skill folder (skills/order-intelligence/shopify-admin-partial-refund-pattern-detector in 40RTY-ai/shopify-admin-skills) into .agents/skills/shopify-admin-partial-refund-pattern-detector in your project. Codex loads it when a task matches its description.

Can I use Shopify Admin Partial Refund Pattern Detector in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-partial-refund-pattern-detector -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/shopify-admin-partial-refund-pattern-detector, .gemini/skills/shopify-admin-partial-refund-pattern-detector, .github/skills/shopify-admin-partial-refund-pattern-detector and .opencode/skills/shopify-admin-partial-refund-pattern-detector in your project.

What does Shopify Admin Partial Refund Pattern Detector need to run?

Going by SKILL.md and its folder, Shopify Admin Partial Refund Pattern Detector needs the command-line tools its instructions call (shopify). Compatibility (from SKILL.md): Claude Code, Cursor, Codex, Gemini CLI.

Does Shopify Admin Partial Refund Pattern Detector access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Shopify Admin Partial Refund Pattern Detector safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Shopify Admin Partial Refund Pattern Detector use?

Shopify Admin Partial Refund Pattern Detector is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Shopify Admin Partial Refund Pattern Detector use?

About 1.7k tokens (SKILL.md is roughly 6.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Shopify Admin Partial Refund Pattern Detector?

Skills that share tags, products or a category with Shopify Admin Partial Refund Pattern Detector: Shopify (Shopify/Shopify-AI-Toolkit, 589 stars), E-commerce Visual Copywriting (feichanggege/ecommerce-visual-copywriting-skill, 853 stars), Reviewing Pull Requests (Shopify/shopify-app-js, 543 stars) and Better Design (marvkr/better-design, 254 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Shopify Admin Partial Refund Pattern Detector?

40RTY-ai (a GitHub organization) maintains it in 40RTY-ai/shopify-admin-skills, which has 194 GitHub stars. The repository holds 116 skills in this directory. The repository was last updated on August 14, 2026.

Source: 40RTY-ai/shopify-admin-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.