aso-audit

Trigger phrases

Phrases that activate this skill when typed to Claude Code:

• ASO audit
• audit my app listing
• app store optimization
• improve app visibility
• compare my app to competitors

What it does

aso-audit is a Claude Code skill from Corey Haines’s marketing-skills repo. It turns Claude into an ASO consultant who fetches your live App Store or Google Play listing, scores six dimensions against platform-specific specs, and produces a prioritized action plan. The skill activates when you mention “ASO audit”, “audit my app listing”, or “improve app visibility”, and applies brand-maturity tier adjustments (Dominant / Established / Challenger) so household-name apps don’t get penalized for deliberate brand choices.

The output of a session is a graded scorecard (Title & Subtitle 20%, Description 15%, Visual Assets 25%, Ratings 20%, Metadata 10%, Conversion Signals 10%), top-3 quick wins, per-dimension findings with specific fixes, keyword suggestions, and an impact-vs-effort priority list.

When to use it

Reach for it when:

• You have an App Store or Google Play URL and want a structured teardown
• You’re not getting downloads despite traffic and need to know if it’s the listing or upstream
• You want a side-by-side comparison against 2–3 competitor listings

When not to reach for it:

• The app isn’t live yet — there’s nothing to audit
• The bottleneck is paid acquisition spend, not listing conversion

Install

The skill is distributed via Corey Haines’s marketing-skills repo. Install via the repo’s recommended path — copy the aso-audit SKILL.md into your project’s .claude/skills/aso-audit/ directory, or use the repo’s plugin install if you’ve set it up.

Once installed, the skill activates on the trigger phrases above. The first time it runs, it will check for .agents/product-marketing-context.md (or .claude/product-marketing-context.md) — populating that file with your product context first dramatically improves output quality across all of Haines’s marketing skills.

What a session looks like

A typical session has three phases:

1. Fetch + tier classification. WebFetch pulls the listing; the skill classifies the app as Dominant, Established, or Challenger so scoring is calibrated to actual competition.
2. Six-dimension scoring. Apple-vs-Google indexing differences are applied — Apple keyword field rules, Google long-description indexing, screenshot caption indexing (Apple, since June 2025), Android Vitals thresholds.
3. Action plan. Top-3 quick wins (under one hour), specific text recommendations with character counts, screenshot/video improvements, keyword suggestions, and an impact-vs-effort ranked list.

The discipline that makes it work: the brand-tier classifier. A textbook ASO deviation by Instagram is not the same as one by an indie app — the skill applies different scoring rules instead of penalizing every household name for “missing keywords in title”.

Receipts

Honest reporting on what aso-audit produces and where it has limits:

Where it works well:

• The Apple-vs-Google indexing-rules table catches mistakes that single-platform audits miss
• Tier-aware scoring stops it from giving Spotify a low score for using its brand name as the title
• Action items are specific (“change subtitle from X to Y”) not vague

Where it backfires:

• Without paid ASO tools (Sensor Tower, AppTweak) it can’t see search-volume data — it suggests keywords without ranking demand
• WebFetch can miss client-rendered fields; you may need to paste in promotional text or screenshot captions manually

Pattern that works: run it once per quarter and after every release, then compare scores month-over-month. The dimension breakdown turns ASO from “vibes” into a tracked metric.

Source and attribution

Originally written by Corey Haines. The canonical SKILL.md and any supporting files live in the aso-audit folder of his marketing-skills repository.

License: MIT. You can install, adapt, and redistribute the skill, with attribution preserved.

This page documents the skill from a practitioner’s perspective. For the formal spec and any updates, defer to the source repo.