Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add finsilabs/awesome-ecommerce-skills --skill shopify-app-review-triagegit clone --depth 1 https://github.com/finsilabs/awesome-ecommerce-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/shopify-app-review-triage)<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/shopify-app-review-triage"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/shopify-app-review-triage/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/finsilabs/awesome-ecommerce-skills/shopify-app-review-triage"><img src="https://agentmods.dev/badge/skills/finsilabs/awesome-ecommerce-skills/shopify-app-review-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.03986 |
| Opus 5.5 | $0.00019 | $0.01594 |
| Sonnet 5.5 | $0.00010 | $0.00797 |
| Haiku 4.5 | $0.00005 | $0.00399 |
Grade A, and why
shopify-app-review-triage scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shopify App Review Triage
Overview
Shopify App Store reviews are the loudest public signal an app team gets, and the usual failure mode is treating every 1-star review as equally urgent. This skill turns rows of public review text for the apps you publish into one prioritized brief — P0 incident risk, P1 repeated friction, P2 pricing confusion, P3 feature request, plus an explicit needs-human-read bucket for anything the keyword pass cannot judge. Every item keeps a link back to the public listing it came from and is labeled either first pass — not human-checked or human-checked, so nobody mistakes a keyword match for a confirmed defect. It works for a single app or a portfolio with a few watched competitors, and it needs no API access, no scripts, and no private data.
When to Use This Skill
- When new 1-3-star reviews land on one of your app listings and you need to know which one to work on first
- When you publish several apps and low-star reviews arrive scattered across listings with no shared queue
- When an agency or support partner runs the inbox for an app team and owes them a weekly written brief
- When you want listing feedback clustered into incident risk vs friction vs pricing vs feature requests
- When you also watch competitor listings and need their reviews kept out of your own incident queue
Do not use this skill for storefront product reviews shown to shoppers — see @product-reviews-ratings for collecting and displaying those, and @review-generation-engine for requesting them.
Core Instructions
Ground rules
These are not style preferences. Breaking one makes the brief worse than no brief.
- Public review text only. Never accept, request, or copy support tickets, merchant emails, order data, personal contact details, or internal telemetry. If private data appears in the input, stop, name the affected rows, and ask for them to be removed before continuing.
- Never invent evidence. Do not write a review, rating, date, app name, or source URL that was not supplied. A row with no link gets
source: not captured— never a guessed one. - Keyword output is a sort, not a verdict. Anything produced by the rubric alone is labeled first pass — not human-checked. Only a person who read the review and checked it against their own systems may relabel it human-checked.
- Reviews are customer reports, not verified defects. Write "the reviewer reports the editor showed a blank screen", never "the editor is broken".
- No coverage claims. The brief covers exactly the rows supplied and says so. Never imply exhaustive coverage of a listing, a period, or an app.
- No promises. No revenue impact, no ranking effect, no legal or compliance advice. Suggest actions; do not predict results.
- Draft only — never contact anyone. Do not send email, post a developer reply, open a support ticket, message a reviewer, or publish anything. Hand the draft to the team and let a person decide what to send.
- Reviewers are people. Refer to "the reviewer". Do not name, profile, or speculate about them.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 228 lines · 48 tokens per session scan A 05571b95b591
shopify-app-review-triage is a skill published in the GitHub repository finsilabs/awesome-ecommerce-skills (60 stars, last pushed 5d ago), licensed MIT. It adds 48 tokens to every session and 3,986 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-24.
Other skills, from other repositories
review-management
Use when a public review needs an on-voice reply, when you need to earn more reviews legally, or when an aggregate rating is slipping across Google Business Profile, Trustpilot, the App Store or Google Play — including deciding reply versus flag, getting an unfair one-star removed rather than merely answered, and…
subscription-lifecycle
Generates StoreKit 2 subscription lifecycle management — grace periods, billing retry, offer codes, win-back offers, upgrade/downgrade paths, and subscription status monitoring. Use when user needs post-purchase subscription state handling beyond the initial paywall.
watermark-engine
Generates a watermark overlay system for images and video with configurable positioning, opacity, tiling, and paywall integration for automatic removal on subscription or purchase. Use when user wants to add branding, attribution, or free-tier watermarks to visual content.
offer-codes-setup
Generates offer code distribution strategies and configuration guides for subscription and IAP promotions — including partner campaigns, influencer programs, and email re-engagement. Use when setting up offer codes for distribution.
subscription-offers
Generates StoreKit 2 code for all subscription offer types — introductory, promotional, offer codes, and win-back. Includes eligibility checks, offer presentation, and the preferredSubscriptionOffer modifier. Use when adding subscription offers, free trials, or promotional pricing.
monetization
Monetization strategy for iOS/macOS apps. Covers readiness assessment, pricing model selection, tier structuring, free trial strategy, and implementation guidance. Use when deciding what to charge, how to price, or planning monetization end-to-end.