aso
An agent skill by coreyhaines31, from coreyhaines31/marketingskills. Tags: analytics, app-store, mobile, optimization, search.
What it does
When the user wants to audit or optimize an App Store or Google Play listing. Also use when the user mentions 'ASO audit,' 'app store optimization,' 'optimize my app listing,' 'improve app visibility,' 'app store ranking,' 'audit my listing,' 'why aren't people downloading my app,' 'improve my app conversion,' 'keyword optimization for app,' or 'compare my app to competitors.' Use when the user shares an App Store or Google Play URL and wants to improve it.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add coreyhaines31/marketingskills --skill asoOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/coreyhaines31/marketingskills
cp -r marketingskills/skills/aso ~/.claude/skills/asoSafety box score
Grade B, low risk: 11 of 100 risk points, rated 2026-09-22. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill is a read-only ASO audit workflow: it fetches public App Store/Google Play listing data, scores metadata/creative assets, and generates recommendations. The main blast radius is outbound network access to store/search pages and optional reads of local marketing-context files; it does not ship code, request credentials, or make changes to the machine.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 0 (none) | No scripts, shell commands, or code evaluation are shipped; the skill is described entirely as analysis and reporting. |
| Network access | 2 (moderate) | It explicitly says to "Use WebFetch to retrieve the listing page" and to "search the web" for app names, so it will contact external sites during normal use. |
| Filesystem reach | 1 (low) | Before auditing it may read local context files like ".agents/product-marketing.md", ".claude/product-marketing.md", or "product-marketing-context.md" if present, which is limited read-only filesystem access. |
| Secrets & credentials | 0 (none) | It does not ask for passwords, tokens, keychain items, or other secret stores; it works from public listing URLs and visible store content. |
| Privilege & persistence | 0 (none) | There is no sudo, package installation, service registration, shell startup editing, or other privilege-changing step. |
| Instruction hijack surface | 0 (none) | It treats listing copy/reviews/HTML as untrusted and says not to follow embedded instructions, but it does not itself instruct the agent to ignore safeguards or fetch hidden prompts. |
| Irreversible actions | 0 (none) | The skill only audits and recommends; it does not publish, pay, book, delete, or push changes on the user's behalf. |
| Transparency | 0 (none) | All shipped files are plain markdown/reference text; there are no binaries, base64 blobs, or hidden install steps. |
Before installing
- Read the fetch section and confirm you're comfortable with the skill making outbound requests to App Store/Google Play and search engines.
- Check whether `.agents/product-marketing.md` or `.claude/product-marketing.md` exists in your workspace and make sure it does not contain sensitive internal notes.
- Verify you want the agent to analyze public listing text/screenshots only; this skill does not edit or publish store metadata.
Rated 2026-09-22 by an automated review of 7 files from the skill's repository.
Source
- Repository
- coreyhaines31/marketingskills (all skills from this repository)
- Path
- skills/aso/SKILL.md
- Branch
- main
- Collection
- marketingskills
- Updated
- 2026-09-21
Related skills
- ads — When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms.
- ab-testing — When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.
- ai-seo — When the user wants to optimize content for AI search engines, get cited by LLMs, or appear in AI-generated answers.
- cro — When the user wants to optimize, improve, or increase conversions on any marketing page or form — including homepage, landing pages, pricing pages.
- onboarding — When the user wants to optimize post-signup onboarding, user activation, first-run experience, or time-to-value.
- paywalls — When the user wants to create or optimize in-app paywalls, upgrade screens, upsell modals, or feature gates.