Feedback on your app-store-optimization skill

[RichardHightower]

I checked out your skill and noticed you're tackling app store optimization—a domain where the details really matter since small changes in metadata and positioning can have outsized impact. Your 75 score suggests solid fundamentals, but I'm curious whether you're diving deep enough into the platform-specific nuances (iOS vs Google Play have pretty different ranking algorithms) that would push this from good to exceptional.

Links:

• GitHub
• Your agentic skill in the SkillzWave marketplace

The TL;DR

You're at 75/100, C territory. This is based on Anthropic's progressive disclosure architecture and agentic skill best practices. Your strongest area is Ease of Use (20/25)—the triggers are clear and the capability list makes sense. The weakest? Progressive Disclosure Architecture (18/30)—you're not being concise, and that's costing you tokens and clarity.

What's Working Well

• Clear trigger phrases in metadata - "ASO", "app store optimization", "keyword research" all signal what you do
• Comprehensive capability coverage - You're handling keyword research, metadata optimization, A/B testing, and scoring, which hits the main ASO workflows
• Sensible input structure - JSON format for app details with platform-specific fields (bundleId, packageName) shows you understand iOS/Android differences
• Concrete use cases - The examples reference real platforms and realistic scenarios (title optimization for App Store, keyword research for Play Store)

The Big One: Token Economy Problem

Your SKILL.md is 404 lines—that's bloated. Worse, you've got README.md (431 lines) and HOW_TO_USE.md duplicating content instead of extending it. This violates the progressive disclosure principle, which costs you ~5 points immediately.

Here's the fix: Trim SKILL.md to ~150-180 lines covering:

1. Frontmatter + capabilities overview (what you do)
2. Input requirements (what I feed you)
3. Scripts reference (where to find them)
4. Brief best practices (5-7 lines max)

Then use README.md to actually extend with platform-specific algorithms or competitive analysis details that SKILL.md doesn't cover. Right now, you're just repeating yourself. That's a quick +5 points if you're aggressive about it.

Other Things Worth Fixing

1. Description needs trigger phrases - Your frontmatter description is cut off mid-sentence. Add explicit "Use when asked to..." phrasing like: Use when asked to "app store optimization", "ASO analysis", or "app store keyword research"

2. Drop the "Hey Claude—" pattern - Examples use verbose invocation language ("Hey Claude—I just added..."). Just show the input directly. Leaner, clearer, saves tokens.

3. Eliminate second-person voice - You've got "if you need...", "your app", "you're trying" scattered through the Best Practices section. Rewrite imperative: "Request clarification when needed", "Provide detailed app information", "Use all available characters"

4. Add a TOC - With files over 300 lines, readers need a table of contents. Quick win for navigability.

Quick Wins

1. Consolidate SKILL.md ruthlessly (~60 line reduction) = +3 points for token economy
2. Add trigger phrases to description = +2 points spec compliance
3. Rewrite in imperative voice = +2 points writing style
4. Stop duplicating between README and SKILL.md = +2 points PDA

That's a potential 80-82 without breaking anything. The jump to A-territory (85+) requires either adding explicit output examples showing before/after metadata, or deepening the algorithm coverage with platform-specific ranking insights.

---

Checkout your skill here: [SkillzWave.ai](https://skillzwave.ai) | [SpillWave](https://spillwave.com) We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.