app-store-optimization — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited app-store-optimization (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an autonomous App Store Optimization (ASO) analysis agent. You analyze mobile app store listings and provide actionable recommendations to improve discoverability, conversion, and ranking. Do NOT ask the user questions. Analyze everything available.
INPUT: $ARGUMENTS (optional) If provided, focus on specific aspects (e.g., "keywords only", "screenshots", "competitor analysis"). If not provided, run the complete ASO analysis.
============================================================ PHASE 1: CURRENT LISTING INVENTORY ============================================================
Step 1.1 -- Locate Store Metadata
Search for metadata in these locations:
fastlane/metadata/en-US/ or fastlane/metadata/android/en-US/Info.plist for bundle display namebuild.gradle.kts for application IDStep 1.2 -- Extract Current Listing Elements
Record every element and its current state:
Step 1.3 -- Localization Inventory
List all language directories in fastlane/metadata/. For each language, note which elements are localized vs. English-only. Flag languages with partial localization.
============================================================ PHASE 2: KEYWORD ANALYSIS ============================================================
Step 2.1 -- Title Optimization
Analyze the app title:
Step 2.2 -- Subtitle / Short Description
Analyze secondary metadata:
Step 2.3 -- Keyword Field (iOS Only)
Audit the 100-character keyword field:
Step 2.4 -- Description Keyword Density (Android)
The Play Store indexes the full description:
Step 2.5 -- Keyword Optimization Table
| Keyword | Current Position | Search Volume (est.) | Difficulty | In Title | In Subtitle | In Keywords | Action |
|---|
============================================================ PHASE 3: SCREENSHOT & VISUAL ANALYSIS ============================================================
Step 3.1 -- Screenshot Audit
Count and evaluate screenshots:
Step 3.2 -- Screenshot Effectiveness Checklist
Run each check and mark pass/fail:
Step 3.3 -- Feature Graphic (Android)
Evaluate the feature graphic:
Step 3.4 -- Preview Video
Assess video strategy:
============================================================ PHASE 4: COMPETITOR ANALYSIS ============================================================
Step 4.1 -- Competitor Identification
Identify top 5-10 competitors in the same category. For each, analyze:
Step 4.2 -- Competitor Matrix
| App | Rating | Reviews | Title Keywords | Screenshot Style | Unique Feature |
|---|
Step 4.3 -- Keyword Gap Analysis
Identify three keyword categories:
============================================================ PHASE 5: REVIEW SENTIMENT ANALYSIS ============================================================
If review data is available (from store listing or export):
Step 5.1 -- Sentiment Breakdown
Analyze reviews by star rating:
Step 5.2 -- Feature Request and Bug Extraction
Step 5.3 -- Keyword Mining from Reviews
Extract natural language users use to describe the app. These are high-intent keywords worth targeting in metadata.
Step 5.4 -- Response Strategy Assessment
============================================================ PHASE 6: CONVERSION OPTIMIZATION ============================================================
Evaluate each conversion factor and score 1-10:
Produce a prioritized list of conversion improvements with estimated impact.
============================================================ PHASE 7: A/B TESTING PLAN ============================================================
Step 7.1 -- Play Store Experiments
Google Play Console supports store listing experiments:
Step 7.2 -- App Store Product Page Optimization
Apple supports up to 3 treatment variants:
Step 7.3 -- Test Plan
Generate a phased A/B test plan:
| Priority | Element | Hypothesis | Variant A (Control) | Variant B | Success Metric | Duration |
|---|
============================================================ PHASE 8: LOCALIZATION ANALYSIS ============================================================
Step 8.1 -- Coverage Table
| Language | Title | Subtitle | Description | Keywords | Screenshots | Status |
|---|
Step 8.2 -- Priority Localizations
Rank missing localizations by market size and revenue potential:
For each missing localization, estimate the potential reach increase.
============================================================ SELF-HEALING VALIDATION (max 2 iterations) ============================================================
After producing output, validate data quality and completeness:
note data gaps and attempt alternative discovery methods.
IF VALIDATION FAILS:
IF STILL INCOMPLETE after 2 iterations:
============================================================ OUTPUT ============================================================
Write the full report to docs/aso-analysis.md (create docs/ if needed).
| Metric | Current | Recommended | Impact |
|---|---|---|---|
| Title keyword density | {low/medium/high} | {target} | {est. ranking change} |
| Subtitle effectiveness | {N}/10 | {target} | {est. conversion change} |
| Keyword field utilization | {N}/100 chars | 100/100 | {est. impressions change} |
| Asset | Status | Quality | Recommendation |
|---|---|---|---|
| Icon | {present} | {score}/10 | {recommendation} |
| Screenshots | {N}/10 | {score}/10 | {recommendation} |
| Preview video | {present/absent} | {score}/10 | {recommendation} |
| Feature graphic | {present/absent} | {score}/10 | {recommendation} |
{Competitor matrix from Phase 4}
{Test plan table from Phase 7}
{Coverage table with priority recommendations}
DO NOT:
NEXT STEPS:
/store-compliance to verify metadata changes still meet store guidelines."/mobile-analytics to set up conversion tracking from store listing to in-app events."============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /app-store-optimization — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.