Skip to content

JasonColapietro/suede-creator-skills / skills/suede-aso

suede-aso

Verified

Suede App Store Optimization Skills. Use when asked to "improve our App Store listing" or prepare prelaunch keyword, title, subtitle, description and screenshot fields from app and console evidence. NOT FOR: app builds (android-app-factory or site-to-ios-app), release rollout (suede-play-release), paid assets (suede-ad-creative), or install instrumentation (suede-analytics).

FileKindSize
CARD.mdmarkdown4.2 KB
SKILL.mdskill md18.9 KB
agents/openai.yamlconfig580 B
evals/evals.jsonconfig7.6 KB
references/apple-specs.mdmarkdown7.4 KB
references/benchmarks.mdmarkdown3.2 KB
references/collector.mdmarkdown7.2 KB
references/google-play-specs.mdmarkdown6.4 KB
references/report-template.mdmarkdown5.0 KB
references/scoring-criteria.mdmarkdown13.8 KB
references/worked-contract.mdmarkdown1.8 KB
scripts/collect.mjsscript67.7 KB

evals/evals.json

View on GitHub
{
  "skill_name": "suede-aso",
  "evals": [
    {
      "id": 1,
      "prompt": "Here's our app on the App Store: https://apps.apple.com/us/app/example/id123456789. Can you audit our listing and tell me what to fix?",
      "expected_output": "Should check for product-marketing.md first. Should detect this is an Apple App Store URL and run the full ASO audit workflow. Should fetch the listing and extract Apple-specific fields (title 30 chars, subtitle 30 chars, description, promotional text 170 chars, category, screenshots, video, ratings). Should classify the app's brand maturity tier (Dominant/Established/Challenger) before scoring. Should score all 6 dimensions (Title & Subtitle 20%, Description 15%, Visual Assets 25%, Ratings & Reviews 20%, Metadata & Freshness 10%, Conversion Signals 10%) with weighted total out of 100 and a grade. Should output a scorecard, top 3 quick wins, detailed findings, keyword suggestions, visual recommendations, and prioritized action plan with specific 'change X from Y to Z' recommendations including character counts.",
      "assertions": [
        "Checks for product-marketing.md",
        "Identifies as Apple App Store URL",
        "Classifies brand maturity tier",
        "Scores all 6 dimensions with weights",
        "Provides scorecard with grade",
        "Lists top 3 quick wins",
        "Recommendations include character counts",
        "Recommendations are specific (X to Y format)"
      ],
      "files": []
    },
    {
      "id": 2,
      "prompt": "We're a small fintech startup with about 5,000 downloads. Our Play Store listing has a 2.8 rating and we haven't updated the description in 8 months. Help us figure out what to fix first.",
      "expected_output": "Should recognize this as a Challenger-tier Google Play app. Should immediately flag the always-flag issues: rating below 4.0 (critical), last update >3 months ago. Should apply strict Challenger scoring against textbook best practices. Should focus on Google Play-specific guidance: full description is indexed for search (core use-case terms in natural language, no keyword lists, which Play policy prohibits), no hidden keyword field, feature graphic required (1024x500), max 8 screenshots, Android Vitals affect ranking. Should prioritize fixing the rating issue (response strategy, in-app review prompts) and refreshing the description with keyword strategy. Should recommend updating the listing soon to break the >3 month stale signal.",
      "assertions": [
        "Identifies as Google Play app",
        "Classifies as Challenger tier",
        "Flags rating below 4.0",
        "Flags stale update (>3 months)",
        "Notes Google Play indexes full description",
        "Mentions feature graphic requirement",
        "Recommends natural use of core terms in the description without keyword stuffing",
        "Prioritizes rating improvement"
      ],
      "files": []
    },
    {
      "id": 3,
      "prompt": "Instagram's App Store listing has just 'Instagram' as the title and barely any keywords. Should they fix that?",
      "expected_output": "Should classify Instagram as a Dominant-tier app and apply tier-adjusted scoring. Should explain that brand-only titles are valid for Dominant apps (score 8+ if brand IS the keyword) because users search by brand name, not generic keywords. Should NOT flag this as a missed opportunity. Should explain the key principle: 'Is this a mistake or a deliberate choice by a team that has data I don't?' Should note that other dimensions (screenshots, description, what's new) are also evaluated against tier: lifestyle/brand photography and brief release notes are acceptable for Dominant apps. Should contrast with what would be a problem for a Challenger app.",
      "assertions": [
        "Classifies Instagram as Dominant tier",
        "Explains brand-only titles are valid for Dominant",
        "Does NOT flag the title as a problem",
        "Contrasts Dominant vs Challenger treatment",
        "Cites the 'mistake vs deliberate choice' principle"
      ],
      "files": []
    },
    {
      "id": 4,
      "prompt": "Compare our app https://apps.apple.com/us/app/ourapp/id111 against these two competitors: https://apps.apple.com/us/app/competitor1/id222 and https://apps.apple.com/us/app/competitor2/id333",
      "expected_output": "Should run Phase 3 competitor comparison. Should fetch and score all three apps with the same 6-dimension framework. Should build a side-by-side comparison table highlighting where the user's app is weaker or stronger across each dimension. Should identify keyword gaps: terms competitors target that the user's app doesn't. Should produce a prioritized list of competitor-informed changes. Should call out platform-specific considerations consistently across all three apps.",
      "assertions": [
        "Scores all 3 apps with same framework",
        "Builds comparison table",
        "Identifies where user's app is weaker",
        "Identifies keyword gaps vs competitors",
        "Produces competitor-informed action list"
      ],
      "files": []
    },
    {
      "id": 5,
      "prompt": "We only have 3 screenshots and no preview video. Does this really matter that much?",
      "expected_output": "Should explain that screenshot count and video presence are heavily weighted in the Visual Assets dimension (25% of total score). Should note Apple allows up to 10 screenshots per device and the first few carry the decision, since they show in search results. Should state that screenshot caption indexing is not confirmed by Apple, so captions are written for conversion and any ranking effect is a hypothesis. Should explain that iOS previews autoplay muted while Google Play video does not autoplay and is watched far less, without quoting vendor lift percentages as fact. Should recommend adding 5-8 screenshots with caption text and a 15-30s preview video, measured against the user's own App Store Connect or Play Console conversion data. Should flag fewer than 5 screenshots as an always-flag issue across all tiers.",
      "assertions": [
        "Notes Visual Assets is 25% of score",
        "Cites first few screenshots as most important",
        "States screenshot caption indexing is unconfirmed by Apple",
        "Contrasts iOS autoplay with Google Play video behavior without unsourced lift numbers",
        "Recommends specific screenshot count and video specs",
        "Uses console conversion data as the baseline",
        "Flags <5 screenshots as always-flag issue"
      ],
      "files": []
    },
    {
      "id": 6,
      "prompt": "Should I run a Custom Product Page experiment on iOS for our paid search campaigns?",
      "expected_output": "Should reference Apple-specific facts: Custom Product Pages (CPP), up to 70 per app, which can also be assigned keywords for organic search since July 2025. Should explain CPPs let you vary screenshots, video, and promotional text for specific traffic sources (e.g., Apple Ads keywords) and compare each against the default page in App Store Connect. Should recommend matching CPP variants to the keyword intent for the campaign, with no promised lift. Should cross-reference suede-ab-testing for proper experiment design and suede-ads for the campaign side. Should note this is an iOS-only feature (Google Play has Store Listing Experiments and Custom Store Listings as equivalents).",
      "assertions": [
        "Identifies Custom Product Pages as iOS-specific",
        "Does not promise a conversion lift; measures against the default page in console",
        "Explains CPP can match traffic source intent",
        "Cross-references suede-ab-testing or suede-ads",
        "Notes Google Play equivalents"
      ],
      "files": []
    }
  ]
}
deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall