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

references/scoring-criteria.md

View on GitHub
# ASO Scoring Criteria

Score each dimension 0-10 using the rubrics below.
**Apply brand maturity tier adjustments** from Phase 1.5 of the main skill.

---

## Brand Maturity Adjustments (apply to all dimensions)

Before scoring, determine the app's tier: **Dominant**, **Established**, or **Challenger**.

**Dominant apps (Instagram, Uber, Spotify, WhatsApp, Netflix):**

- Brand-only titles score 8+ (the brand IS the keyword)
- Lifestyle/brand screenshots score same as captioned UI screenshots
- Generic What's New at weekly+ cadence scores 8+
- Missing in-app events for utility apps is not a penalty
- Description scored on conversion quality only, not keyword presence
- Localization scored relative to actual market footprint
- Missing preview video is acceptable if brand awareness is near-universal

**Established apps (Duolingo, Strava, Notion, Calm, Cash App):**

- Brand-first titles with 1-2 keywords score normally
- Strategic description/visual choices get benefit of the doubt
- All other dimensions scored normally

**Challenger apps (most apps):**

- Scored strictly against textbook ASO: every character and feature matters

**Key principle:** Before docking points, ask: "Is this a mistake or a data-informed
choice by a team with more information than I have?"

---

## 1. Title & Subtitle (Weight: 20%)

**Challenger rubric:**

| Score | Criteria                                                                                                                                                                |
| ----- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 9-10  | Brand + high-value keyword in title, complementary keywords in subtitle, no word repetition across fields, near max character usage, instantly communicates app purpose |
| 7-8   | Good keyword presence, minor character waste (5+ unused chars), clear purpose                                                                                           |
| 5-6   | Has keywords but poor placement, some repetition between fields, purpose somewhat clear                                                                                 |
| 3-4   | Title is brand-only or generic, subtitle missing or weak, poor character usage                                                                                          |
| 1-2   | No keyword strategy, title doesn't communicate purpose, major character waste                                                                                           |
| 0     | Cannot assess (data unavailable)                                                                                                                                        |

**Dominant/Established adjustment:** Brand-only titles (e.g., "Instagram") are
valid if the brand has high search volume. Score 8+ for Dominant apps where
brand recognition eliminates the need for generic keywords. Evaluate whether
unused characters represent waste or intentional simplicity.

**Check for:**

- Characters used vs limit (title: 30, subtitle/short desc: 30/80). "Near max" = within 3 chars of the limit (27+/30, 77+/80)
- Primary keyword in title
- Keyword duplication between title and subtitle
- Whether app purpose is immediately clear
- Unnecessary words (articles, prepositions) consuming space
- Special characters or claims ("#1", "best") that risk rejection (Apple)

---

## 2. Description (Weight: 15%)

### Apple App Store

| Score | Criteria                                                                                                                                               |
| ----- | ------------------------------------------------------------------------------------------------------------------------------------------------------ |
| 9-10  | First 3 lines hook with clear value prop, structured with features/benefits/social proof/CTA, promotional text actively used, compelling and scannable |
| 7-8   | Good opening, decent structure, could improve scannability or CTA                                                                                      |
| 5-6   | Generic opening ("Welcome to..."), some structure, missing CTA or social proof                                                                         |
| 3-4   | Wall of text, no clear value prop above fold, no promotional text                                                                                      |
| 1-2   | Minimal or boilerplate description, no effort                                                                                                          |
| 0     | Cannot assess                                                                                                                                          |

### Google Play

| Score | Criteria                                                                                                                                     |
| ----- | -------------------------------------------------------------------------------------------------------------------------------------------- |
| 9-10  | Core use-case terms appear naturally in the first 3 sentences and in feature sections, scannable structure, specific benefits, strong CTA, no term lists |
| 7-8   | Core terms present and natural, some structure, one or two important use cases unnamed                                                                   |
| 5-6   | Core terms sparse, or repeated until the copy reads unnaturally, weak structure                                                                          |
| 3-4   | No discernible terms a searcher would use, poor formatting, wall of text                                                                                |
| 1-2   | Minimal description, or keyword lists that breach Play metadata policy                                                                                   |
| 0     | Cannot assess                                                                                                                                            |

Google Play's policy asks for everyday language and prohibits keyword lists.
Density percentages are folklore; judge whether a searcher's words appear where
a reader would expect them.

**Check for:**

- First 3 lines quality (visible before "Read More")
- Feature-benefit framing (not just feature lists)
- Social proof (downloads, awards, press mentions)
- Call to action
- Natural use of the core use-case terms (Google Play), with no keyword lists
- HTML formatting usage (Google Play)
- Promotional text presence and quality (Apple)

---

## 3. Visual Assets (Weight: 25%)

| Score | Criteria                                                                                                                                                                      |
| ----- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 9-10  | First three screenshots carry the core value story with captions, 5+ total each communicating one benefit, preview video present, icon is distinctive and memorable           |
| 7-8   | 5+ captioned screenshots but the first three don't lead with the core value, good icon, no video OR good video but some screenshot messaging unclear                          |
| 5-6   | 5+ screenshots but weak/no captions, basic icon, no video, screenshots are UI dumps                                                                                           |
| 3-4   | 3-4 screenshots, no captions, generic icon, no storytelling                                                                                                                   |
| 1-2   | Fewer than 3 screenshots, or screenshots are raw unedited UI, poor icon                                                                                                       |
| 0     | Cannot assess                                                                                                                                                                 |

**Check for:**

- Screenshot count (at least 5; past the first few, order matters more than count, and most visitors decide from the first two or three, per `benchmarks.md`, so judge the first three most heavily)
- Caption/overlay text on screenshots (one message per screen, 5-7 words max)
- First 3 screenshots (highest conversion impact on Apple)
- Preview video presence and quality
- Icon distinctiveness (no text in icon, bold shapes, stands out)
- Feature graphic presence (Google Play - mandatory for featured placements)
- Screenshot storytelling flow (do they tell a coherent story?)
- Localized visual assets (for non-English markets)
- Caption keywords (Apple has not confirmed caption indexing; treat as unverified, see apple-specs.md)

---

## 4. Ratings & Reviews (Weight: 20%)

| Score | Criteria                                                                                               |
| ----- | ------------------------------------------------------------------------------------------------------ |
| 9-10  | 4.5+ stars, 10K+ ratings, recent reviews positive, developer responds to negatives, steady review flow |
| 7-8   | 4.0-4.4 stars, 1K+ ratings, mostly positive recent reviews, some developer responses                   |
| 5-6   | 3.5-3.9 stars, 500+ ratings, mixed recent reviews, no developer responses                              |
| 3-4   | 3.0-3.4 stars, <500 ratings, negative themes in recent reviews                                         |
| 1-2   | Below 3.0 stars, few ratings, no developer engagement, visible complaints                              |
| 0     | No ratings yet or cannot assess                                                                        |

**Check for:**

- Average rating (target: 4.0+ minimum, 4.5+ ideal)
- Total rating count
- Recent review sentiment (last 5-10 visible reviews)
- Common complaint themes (bugs, crashes, pricing, UX)
- Developer response presence and quality
- Rating trend (improving or declining, if visible)
- Review recency (fresh reviews signal active user base)

---

## 5. Metadata & Freshness (Weight: 10%)

| Score | Criteria                                                                                                                  |
| ----- | ------------------------------------------------------------------------------------------------------------------------- |
| 9-10  | Updated within last month, 10+ localizations, optimal category choice, in-app events/LiveOps active, data safety complete |
| 7-8   | Updated within 2 months, 5+ localizations, good category, data safety present                                             |
| 5-6   | Updated within 3 months, 2-4 localizations, acceptable category                                                           |
| 3-4   | Updated 3-6 months ago, 1-2 localizations, possibly wrong category                                                        |
| 1-2   | Not updated in 6+ months, single language, poor category choice                                                           |
| 0     | Cannot assess                                                                                                             |

**Check for:**

- Last update date and recency
- Number of supported languages/localizations
- Category selection (is it the best fit? less competitive alternative?)
- In-app events (Apple) or promotional content (Google) presence
- Data safety / privacy nutrition label completeness
- Age rating appropriateness
- Version history quality (do release notes communicate value?)
- What's New text quality

---

## 6. Conversion Signals (Weight: 10%)

| Score | Criteria                                                                                                                                                          |
| ----- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 9-10  | Clear value before download, transparent pricing/IAP, social proof visible (press, awards), download range suggests strong traction, developer credibility strong |
| 7-8   | Good value communication, pricing clear, some social proof                                                                                                        |
| 5-6   | Value prop exists but weak, pricing unclear or IAP heavy, limited social proof                                                                                    |
| 3-4   | Unclear what user gets, confusing pricing, no social proof, low downloads visible                                                                                 |
| 1-2   | No value communication, suspicious pricing, app looks abandoned                                                                                                   |
| 0     | Cannot assess                                                                                                                                                     |

**Check for:**

- Price transparency (free, freemium, paid - is it clear?)
- In-app purchase list quality (do IAP names communicate value?)
- Download range (Google Play - 10K+, 100K+, 1M+ signals trust)
- Developer name/brand recognition
- "Editors' Choice" or featured badges
- Press mentions or awards in description
- Related apps from same developer (portfolio trust signal)
- Privacy practices transparency

---

## Calculating Final Score

```
Final Score = (Title * 0.20) + (Description * 0.15) + (Visuals * 0.25)
            + (Ratings * 0.20) + (Metadata * 0.10) + (Conversion * 0.10)

Scale to 100: Final Score * 10
```

**Example:** Title: 7, Description: 6, Visuals: 8, Ratings: 9, Metadata: 5, Conversion: 7

```
(7 * 0.20) + (6 * 0.15) + (8 * 0.25) + (9 * 0.20) + (5 * 0.10) + (7 * 0.10)
= 1.4 + 0.9 + 2.0 + 1.8 + 0.5 + 0.7
= 7.3 → 73/100 → Grade: B
```
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