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 rshankras/claude-code-apple-skills --skill product-page-optimizationgit clone --depth 1 https://github.com/rshankras/claude-code-apple-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/rshankras/claude-code-apple-skills/product-page-optimization)<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/product-page-optimization"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/product-page-optimization/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/rshankras/claude-code-apple-skills/product-page-optimization"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/product-page-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.02336 |
| Opus 5 | $0.00021 | $0.01168 |
| Sonnet 5 | $0.00008 | $0.00467 |
| Haiku 4.5 | $0.00004 | $0.00234 |
Grade A, and why
product-page-optimization 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 6d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Page Optimization Generator
Create structured A/B test plans for App Store Product Page Optimization (PPO), including test hypotheses, variant designs, success metrics, and iteration strategy.
When This Skill Activates
Use this skill when the user:
- Asks to "optimize product page" or "A/B test App Store page"
- Mentions "product page optimization" or "PPO"
- Wants to improve "App Store conversion rate"
- Asks about "screenshot testing" or "icon testing"
- Mentions improving download rate or tap-through rate
How PPO Works
- Test up to 3 treatments against your original (control); a single test can include up to 3 app preview videos per treatment
- Testable elements: app icon, screenshots, app previews
- Traffic proportion: you choose 1–50% of page traffic, split evenly across treatments (30% over 3 treatments = 10% each) — no treatment may exceed the original page's share
- Duration: run at least 1 week and extend in 7-day increments to capture weekday/weekend cycles; hard cap 90 days
- Statistical confidence: no confidence shown for the first 7 days; 90% confidence is the decision bar — per Apple, "9 of 10 reruns would repeat the result"
- Localization: tests can target specific localizations only — confirm those locales have enough traffic to conclude within 90 days
- Icon treatments: can only use icons that already ship in the app binary's asset catalog as alternate icons — plan icon tests one release ahead
- Prerequisites: app must be Ready for Sale; role must be Account Holder, Admin, App Manager, or Marketing
Important Limitations
- Cannot test: app name, subtitle, description, keyword field, or price
- One test at a time per localization
- Only one test submission can be in App Review at a time
- Results apply to organic App Store traffic only
- Minimum traffic required for statistical significance
Minimum Traffic Thresholds
PPO requires sufficient impression volume to produce meaningful results. If the app doesn't meet these thresholds, skip A/B testing and make direct qualitative improvements instead.
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.
- 6d ago First seen · 233 lines · 42 tokens per session scan A 80df262a9d4f
product-page-optimization is a skill published in the GitHub repository rshankras/claude-code-apple-skills (713 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 2,336 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
android-development
Android development with Kotlin, Jetpack Compose, and modern Android architecture. Use when building Android apps, implementing Material Design, or following Android best practices.
flutter-development
Cross-platform development with Flutter and Dart for iOS, Android, Web, Desktop, and embedded. Use when building Flutter apps, implementing Material/Cupertino design, or optimizing Dart code.
ios-development
Comprehensive guide for building native Apple platform applications.
kotlin-multiplatform
KMP/CMP shared business logic, Compose Multiplatform, expect/actual, Ktor, SQLDelight, and platform-specific implementations. Use when building cross-platform Kotlin applications for Android, iOS, desktop, or web.
flame-harness-admob
Phase 7 — analyze the game, decide a rewarded-ad strategy, guide manual AdMob ad-unit creation, and inject googlemobileads + ATT/UMP consent code.
flame-harness-submit
Phase 10 — upload store text metadata + categories via fastlane, then pause with exact manual steps for the final iOS review submission and Android production promotion.