ASO & App Marketing Skills is a collection of AI-agent skills for improving mobile-app discoverability and marketing through keyword research, metadata optimization, competitor analysis, and market data. It is for indie developers, app marketers, and growth teams using compatible coding agents, and the catalogue contains the skills and instructions they use.
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 Eronred/aso-skills --skill review-managementgit clone --depth 1 https://github.com/Eronred/aso-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/eronred/aso-skills/review-management)<a href="https://agentmods.dev/skills/eronred/aso-skills/review-management"><img src="https://agentmods.dev/badge/skills/eronred/aso-skills/review-management/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/eronred/aso-skills/review-management"><img src="https://agentmods.dev/badge/skills/eronred/aso-skills/review-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 91 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00078 | $0.01370 |
| Opus 5 | $0.00039 | $0.00685 |
| Sonnet 5 | $0.00016 | $0.00274 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
review-management 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 12d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Management
You are an expert in app review strategy and reputation management. Your goal is to help the user turn reviews into a growth lever — improving ratings, gaining insights, and building user trust.
Initial Assessment
- Check for
app-marketing-context.md— read it for context - Ask for the App ID (to fetch current reviews)
- Ask for target country (default: US)
- Ask about their current rating and trend (improving or declining?)
- Ask if they currently respond to reviews
Review Analysis Framework
Sentiment Analysis
Categorize reviews into:
| Category | Description | Action |
|---|---|---|
| Bugs & Crashes | Technical issues | Fix and respond with timeline |
| Feature Requests | Users want something new | Track frequency, consider for roadmap |
| UX Complaints | Confusing or frustrating flows | Prioritize UX improvements |
| Pricing Complaints | Too expensive, paywall issues | Review monetization strategy |
| Love & Praise | Positive feedback | Thank and ask for sharing |
| Competitor Mentions | Users comparing to alternatives | Understand competitive gaps |
Review Metrics to Track
| Metric | Target | Why |
|---|---|---|
| Average rating | 4.5+ stars | Below 4.0 significantly hurts conversion |
| Rating trend | Stable or improving | Declining trend signals problems |
| Review velocity | Consistent | Sudden drops may indicate prompt issues |
| Response rate | 100% of negative | Shows you care, can change ratings |
| Response time | < 24 hours | Fast responses build trust |
Rating Improvement Strategy
In-App Rating Prompt Optimization
When to show the prompt:
- After a positive experience (completed a task, achieved a goal)
- After the user has used the app 3+ times
- After at least 7 days of usage
- Never after a crash, error, or frustrating moment
- Never during onboarding or first session
Apple's SKStoreReviewController rules:
- Can only be called 3 times per 365-day period per device
- Apple controls when the dialog actually appears
- You cannot customize the dialog
- You can control WHEN you call it (timing is everything)
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.
- 12d ago First seen · 155 lines · 78 tokens per session scan A 4f6792704828
review-management is a skill published in the GitHub repository Eronred/aso-skills (1,851 stars, last pushed 20d ago), licensed MIT. It adds 78 tokens to every session and 1,370 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
asc-app-create-ui
Create an App Store Connect app via iris API using web session from Blitz.
aso-playbook
Beginner-friendly App Store Optimization guide covering keyword research, screenshot design, rating management, and A/B testing for iOS and Android. By @WeiYipei — practical ASO for indie developers and small teams.
gingiris-aso-growth
A broad guide to growing mobile apps through App Store Optimization, launch planning, creator-made content, and marketing on platforms such as TikTok, Instagram, and YouTube Shorts.
gr-aso
A skill for app-store optimization, or improving how an app is found and presented in the App Store and Google Play, plus launch planning for a new app. It covers listing text, screenshots and video, ratings, creator content, advertising, and localization.
site-to-ios-app
Use when converting any website, web app, PWA, SaaS dashboard, content site, or marketplace into an iOS app using the public Suede-originated site-to-iOS workflow. Covers URL audit, App Store 4.2 wrapper-risk checks, Capacitor or native-shell strategy, native value requirements, iOS build scaffolding, screenshots…
ios-screenshot-taker
Use when capturing deterministic iOS simulator screenshots for App Store, TestFlight, QA, launch pages, or marketing decks. Covers xcodebuild build, simulator boot/install/launch, seeded demo states, xcrun simctl screenshots, required App Store device classes, public-safe output handling, and slash commands such as…