← 返回 Skills 市场
alirezarezvani

App Store Optimization

作者 Alireza Rezvani · GitHub ↗ · v2.1.1 · MIT-0
cross-platform ⚠ suspicious
2539
总下载
4
收藏
14
当前安装
3
版本数
在 OpenClaw 中安装
/install app-store-optimization
功能描述
App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility o...
使用说明 (SKILL.md)

App Store Optimization (ASO)


Keyword Research Workflow

Discover and evaluate keywords that drive app store visibility.

Workflow: Conduct Keyword Research

  1. Define target audience and core app functions:
    • Primary use case (what problem does the app solve)
    • Target user demographics
    • Competitive category
  2. Generate seed keywords from:
    • App features and benefits
    • User language (not developer terminology)
    • App store autocomplete suggestions
  3. Expand keyword list using:
    • Modifiers (free, best, simple)
    • Actions (create, track, organize)
    • Audiences (for students, for teams, for business)
  4. Evaluate each keyword:
    • Search volume (estimated monthly searches)
    • Competition (number and quality of ranking apps)
    • Relevance (alignment with app function)
  5. Score and prioritize keywords:
    • Primary: Title and keyword field (iOS)
    • Secondary: Subtitle and short description
    • Tertiary: Full description only
  6. Map keywords to metadata locations
  7. Document keyword strategy for tracking
  8. Validation: Keywords scored; placement mapped; no competitor brand names included; no plurals in iOS keyword field

Keyword Evaluation Criteria

Factor Weight High Score Indicators
Relevance 35% Describes core app function
Volume 25% 10,000+ monthly searches
Competition 25% Top 10 apps have \x3C4.5 avg rating
Conversion 15% Transactional intent ("best X app")

Keyword Placement Priority

Location Search Weight
App Title Highest
Subtitle (iOS) High
Keyword Field (iOS) High
Short Description (Android) High
Full Description Medium

See: references/keyword-research-guide.md


Metadata Optimization Workflow

Optimize app store listing elements for search ranking and conversion.

Workflow: Optimize App Metadata

  1. Audit current metadata against platform limits:
    • Title character count and keyword presence
    • Subtitle/short description usage
    • Keyword field efficiency (iOS)
    • Description keyword density
  2. Optimize title following formula:
    [Brand Name] - [Primary Keyword] [Secondary Keyword]
    
  3. Write subtitle (iOS) or short description (Android):
    • Focus on primary benefit
    • Include secondary keyword
    • Use action verbs
  4. Optimize keyword field (iOS only):
    • Remove duplicates from title
    • Remove plurals (Apple indexes both forms)
    • No spaces after commas
    • Prioritize by score
  5. Rewrite full description:
    • Hook paragraph with value proposition
    • Feature bullets with keywords
    • Social proof section
    • Call to action
  6. Validate character counts for each field
  7. Calculate keyword density (target 2-3% primary)
  8. Validation: All fields within character limits; primary keyword in title; no keyword stuffing (>5%); natural language preserved

Platform Character Limits

Field Apple App Store Google Play Store
Title 30 characters 50 characters
Subtitle 30 characters N/A
Short Description N/A 80 characters
Keywords 100 characters N/A
Promotional Text 170 characters N/A
Full Description 4,000 characters 4,000 characters
What's New 4,000 characters 500 characters

Description Structure

PARAGRAPH 1: Hook (50-100 words)
├── Address user pain point
├── State main value proposition
└── Include primary keyword

PARAGRAPH 2-3: Features (100-150 words)
├── Top 5 features with benefits
├── Bullet points for scanability
└── Secondary keywords naturally integrated

PARAGRAPH 4: Social Proof (50-75 words)
├── Download count or rating
├── Press mentions or awards
└── Summary of user testimonials

PARAGRAPH 5: Call to Action (25-50 words)
├── Clear next step
└── Reassurance (free trial, no signup)

See: references/platform-requirements.md


Competitor Analysis Workflow

Analyze top competitors to identify keyword gaps and positioning opportunities.

Workflow: Analyze Competitor ASO Strategy

  1. Identify top 10 competitors:
    • Direct competitors (same core function)
    • Indirect competitors (overlapping audience)
    • Category leaders (top downloads)
  2. Extract competitor keywords from:
    • App titles and subtitles
    • First 100 words of descriptions
    • Visible metadata patterns
  3. Build competitor keyword matrix:
    • Map which keywords each competitor targets
    • Calculate coverage percentage per keyword
  4. Identify keyword gaps:
    • Keywords with \x3C40% competitor coverage
    • High volume terms competitors miss
    • Long-tail opportunities
  5. Analyze competitor visual assets:
    • Icon design patterns
    • Screenshot messaging and style
    • Video presence and quality
  6. Compare ratings and review patterns:
    • Average rating by competitor
    • Common praise themes
    • Common complaint themes
  7. Document positioning opportunities
  8. Validation: 10+ competitors analyzed; keyword matrix complete; gaps identified with volume estimates; visual audit documented

Competitor Analysis Matrix

Analysis Area Data Points
Keywords Title keywords, description frequency
Metadata Character utilization, keyword density
Visuals Icon style, screenshot count/style
Ratings Average rating, total count, velocity
Reviews Top praise, top complaints

Gap Analysis Template

Opportunity Type Example Action
Keyword gap "habit tracker" (40% coverage) Add to keyword field
Feature gap Competitor lacks widget Highlight in screenshots
Visual gap No videos in top 5 Create app preview
Messaging gap None mention "free" Test free positioning

App Launch Workflow

Execute a structured launch for maximum initial visibility.

Workflow: Launch App to Stores

  1. Complete pre-launch preparation (4 weeks before):
    • Finalize keywords and metadata
    • Prepare all visual assets
    • Set up analytics (Firebase, Mixpanel)
    • Build press kit and media list
  2. Submit for review (2 weeks before):
    • Complete all store requirements
    • Verify compliance with guidelines
    • Prepare launch communications
  3. Configure post-launch systems:
    • Set up review monitoring
    • Prepare response templates
    • Configure rating prompt timing
  4. Execute launch day:
    • Verify app is live in both stores
    • Announce across all channels
    • Begin review response cycle
  5. Monitor initial performance (days 1-7):
    • Track download velocity hourly
    • Monitor reviews and respond within 24 hours
    • Document any issues for quick fixes
  6. Conduct 7-day retrospective:
    • Compare performance to projections
    • Identify quick optimization wins
    • Plan first metadata update
  7. Schedule first update (2 weeks post-launch)
  8. Validation: App live in stores; analytics tracking; review responses within 24h; download velocity documented; first update scheduled

Pre-Launch Checklist

Category Items
Metadata Title, subtitle, description, keywords
Visual Assets Icon, screenshots (all sizes), video
Compliance Age rating, privacy policy, content rights
Technical App binary, signing certificates
Analytics SDK integration, event tracking
Marketing Press kit, social content, email ready

Launch Timing Considerations

Factor Recommendation
Day of week Tuesday-Wednesday (avoid weekends)
Time of day Morning in target market timezone
Seasonal Align with relevant category seasons
Competition Avoid major competitor launch dates

See: references/aso-best-practices.md


A/B Testing Workflow

Test metadata and visual elements to improve conversion rates.

Workflow: Run A/B Test

  1. Select test element (prioritize by impact):
    • Icon (highest impact)
    • Screenshot 1 (high impact)
    • Title (high impact)
    • Short description (medium impact)
  2. Form hypothesis:
    If we [change], then [metric] will [improve/increase] by [amount]
    because [rationale].
    
  3. Create variants:
    • Control: Current version
    • Treatment: Single variable change
  4. Calculate required sample size:
    • Baseline conversion rate
    • Minimum detectable effect (usually 5%)
    • Statistical significance (95%)
  5. Launch test:
    • Apple: Use Product Page Optimization
    • Android: Use Store Listing Experiments
  6. Run test for minimum duration:
    • At least 7 days
    • Until statistical significance reached
  7. Analyze results:
    • Compare conversion rates
    • Check statistical significance
    • Document learnings
  8. Validation: Single variable tested; sample size sufficient; significance reached (95%); results documented; winner implemented

A/B Test Prioritization

Element Conversion Impact Test Complexity
App Icon 10-25% lift possible Medium (design needed)
Screenshot 1 15-35% lift possible Medium
Title 5-15% lift possible Low
Short Description 5-10% lift possible Low
Video 10-20% lift possible High

Sample Size Quick Reference

Baseline CVR Impressions Needed (per variant)
1% 31,000
2% 15,500
5% 6,200
10% 3,100

Test Documentation Template

TEST ID: ASO-2025-001
ELEMENT: App Icon
HYPOTHESIS: A bolder color icon will increase conversion by 10%
START DATE: [Date]
END DATE: [Date]

RESULTS:
├── Control CVR: 4.2%
├── Treatment CVR: 4.8%
├── Lift: +14.3%
├── Significance: 97%
└── Decision: Implement treatment

LEARNINGS:
- Bold colors outperform muted tones in this category
- Apply to screenshot backgrounds for next test

Before/After Examples

Title Optimization

Productivity App:

Version Title Analysis
Before "MyTasks" No keywords, brand only (8 chars)
After "MyTasks - Todo List & Planner" Primary + secondary keywords (29 chars)

Fitness App:

Version Title Analysis
Before "FitTrack Pro" Generic modifier (12 chars)
After "FitTrack: Workout Log & Gym" Category keywords (27 chars)

Subtitle Optimization (iOS)

Version Subtitle Analysis
Before "Get Things Done" Vague, no keywords
After "Daily Task Manager & Planner" Two keywords, benefit clear

Keyword Field Optimization (iOS)

Before (Inefficient - 89 chars, 8 keywords):

task manager, todo list, productivity app, daily planner, reminder app

After (Optimized - 97 chars, 14 keywords):

task,todo,checklist,reminder,organize,daily,planner,schedule,deadline,goals,habit,widget,sync,team

Improvements:

  • Removed spaces after commas (+8 chars)
  • Removed duplicates (task manager → task)
  • Removed plurals (reminders → reminder)
  • Removed words in title
  • Added more relevant keywords

Description Opening

Before:

MyTasks is a comprehensive task management solution designed
to help busy professionals organize their daily activities
and boost productivity.

After:

Forget missed deadlines. MyTasks keeps every task, reminder,
and project in one place—so you focus on doing, not remembering.
Trusted by 500,000+ professionals.

Improvements:

  • Leads with user pain point
  • Specific benefit (not generic "boost productivity")
  • Social proof included
  • Keywords natural, not stuffed

Screenshot Caption Evolution

Version Caption Issue
Before "Task List Feature" Feature-focused, passive
Better "Create Task Lists" Action verb, but still feature
Best "Never Miss a Deadline" Benefit-focused, emotional

Tools and References

Scripts

Script Purpose Usage
keyword_analyzer.py Analyze keywords for volume and competition python keyword_analyzer.py --keywords "todo,task,planner"
metadata_optimizer.py Validate metadata character limits and density python metadata_optimizer.py --platform ios --title "App Title"
competitor_analyzer.py Extract and compare competitor keywords python competitor_analyzer.py --competitors "App1,App2,App3"
aso_scorer.py Calculate overall ASO health score python aso_scorer.py --app-id com.example.app
ab_test_planner.py Plan tests and calculate sample sizes python ab_test_planner.py --cvr 0.05 --lift 0.10
review_analyzer.py Analyze review sentiment and themes python review_analyzer.py --app-id com.example.app
launch_checklist.py Generate platform-specific launch checklists python launch_checklist.py --platform ios
localization_helper.py Manage multi-language metadata python localization_helper.py --locales "en,es,de,ja"

References

Document Content
platform-requirements.md iOS and Android metadata specs, visual asset requirements
aso-best-practices.md Optimization strategies, rating management, launch tactics
keyword-research-guide.md Research methodology, evaluation framework, tracking

Assets

Template Purpose
aso-audit-template.md Structured audit checklist for app store listings

Platform Notes

Platform / Constraint Behavior / Impact
iOS keyword changes Require app submission
iOS promotional text Editable without an app update
Android metadata changes Index in 1-2 hours
Android keyword field None — use description instead
Keyword volume data Estimates only; no official source
Competitor data Public listings only

When not to use this skill: web apps (use web SEO), enterprise/internal apps, TestFlight-only betas, or paid advertising strategy.


Related Skills

Skill Integration Point
content-creator App description copywriting
marketing-demand-acquisition Launch promotion campaigns
marketing-strategy-pmm Go-to-market planning

Proactive Triggers

  • No keyword optimization in title → App title is the #1 ranking factor. Include top keyword.
  • Screenshots don't show value → Screenshots should tell a story, not show UI.
  • No ratings strategy → Below 4.0 stars kills conversion. Implement in-app rating prompts.
  • Description keyword-stuffed → Natural language with keywords beats keyword stuffing.

Output Artifacts

When you ask for... You get...
"ASO audit" Full app store listing audit with prioritized fixes
"Keyword research" Keyword list with search volume and difficulty scores
"Optimize my listing" Rewritten title, subtitle, description, keyword field

Communication

All output passes quality verification:

  • Self-verify: source attribution, assumption audit, confidence scoring
  • Output format: Bottom Line → What (with confidence) → Why → How to Act
  • Results only. Every finding tagged: 🟢 verified, 🟡 medium, 🔴 assumed.
安全使用建议
This skill appears to actually implement an ASO toolkit (the Python scripts line up with the advertised features), but there are important unknowns you should resolve before installing or executing anything: 1) Ask the author how the scripts obtain live App Store / Google Play data and search-volume estimates. If they require API access, request explicit instructions and which credentials are needed. 2) Request a requirements.txt or dependency list and run the code only in a controlled environment (container or VM). 3) Review the Python scripts for network calls (search for requests, urllib, selenium, google-play-scraper, playwright, or other scraping libraries) and any hard-coded endpoints before running. 4) If you will run the scripts, do so offline / sandboxed first and with non-sensitive test data; do not paste production credentials unless you understand and trust the code. 5) If you need fully automated live scraping or API access, prefer a skill that documents required credentials/third-party services clearly. If you want, I can scan the included Python files for network calls, credential reads, or suspicious patterns and summarize what they do.
功能分析
Type: OpenClaw Skill Name: app-store-optimization Version: 2.1.1 The app-store-optimization skill bundle is a legitimate and well-structured toolkit for mobile app marketing analysis. All included Python scripts (such as keyword_analyzer.py, aso_scorer.py, and review_analyzer.py) contain only mathematical, statistical, and string-processing logic necessary for SEO tasks. There is no evidence of data exfiltration, unauthorized network activity, or malicious prompt injection; the instructions in SKILL.md are strictly aligned with the stated purpose of optimizing app store presence.
能力评估
Purpose & Capability
The name, description, SKILL.md workflows, and included Python modules (keyword_analyzer, competitor_analyzer, metadata_optimizer, aso_scorer, ab_test_planner, localization_helper, review_analyzer, launch_checklist) are coherent with an ASO toolkit. However, the skill claims capabilities that normally require external data (app store metadata, rankings, search volume) yet does not declare any required API keys, credentials, or explain the data source. That omission is unexpected and reduces clarity about how the tool obtains live store data.
Instruction Scope
SKILL.md and HOW_TO_USE explicitly instruct usage of the included Python scripts for research/analysis. The instructions request user-provided data in many cases (reviews, metrics, competitor app names), which is appropriate, but they do not explain how the scripts fetch live store metadata/rankings or search volumes. The runtime instructions assume the agent or user will run the Python modules but do not list required Python, libraries, or run commands. Running unreviewed scripts that may perform network access or scraping is a meaningful scope risk.
Install Mechanism
There is no install spec (instruction-only from the registry perspective) but the package ship includes eight sizable Python modules and multiple docs. No requirements.txt, no dependency list, and no platform install steps for Python packages are provided. That makes runtime behavior unclear (dependencies may be missing) and increases the chance someone will execute code without understanding its external dependencies or side effects. There is no download-from-URL risk in the registry metadata itself.
Credentials
The skill requests no environment variables or credentials, which is good from a secrets-exfiltration standpoint. At the same time, many of the advertised features (live rankings, search volume estimates, automated competitor extraction) typically require network access and/or API credentials; the SKILL.md instead leans on the user supplying data or the scripts performing their own fetches, but it does not state which approach is used. This mismatch (complex capability but no declared data-source credentials) is an unexplained gap.
Persistence & Privilege
The skill is not marked always:true and does not request system-wide config changes. It is user-invocable and allows normal autonomous invocation. There is no evidence in the metadata that it modifies other skills or system settings.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install app-store-optimization
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /app-store-optimization 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v2.1.1
v2.1.1: optimization, reference splits
v1.0.0
- Initial release of the App Store Optimization (ASO) toolkit. - Provides workflows for keyword research, metadata optimization, competitor analysis, and app launch. - Includes best practices, validation steps, evaluation criteria, and platform requirements for Apple App Store and Google Play Store. - Supports triggers for app ranking, visibility, marketing, and conversion rate improvement.
v0.1.0
Initial release of the App Store Optimization (ASO) toolkit. - Provides step-by-step workflows for keyword research, metadata optimization, competitor analysis, and app launch. - Includes keyword evaluation criteria and metadata placement strategies for both Apple App Store and Google Play Store. - Features detailed competitor analysis templates and gap identification methods. - Covers best practices for app store listing elements, visual assets, and rating/review management. - Offers validation checklists, platform character limits, and description structure templates.
元数据
Slug app-store-optimization
版本 2.1.1
许可证 MIT-0
累计安装 14
当前安装数 14
历史版本数 3
常见问题

App Store Optimization 是什么?

App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility o... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 2539 次。

如何安装 App Store Optimization?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install app-store-optimization」即可一键安装,无需额外配置。

App Store Optimization 是免费的吗?

是的,App Store Optimization 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

App Store Optimization 支持哪些平台?

App Store Optimization 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 App Store Optimization?

由 Alireza Rezvani(@alirezarezvani)开发并维护,当前版本 v2.1.1。

💬 留言讨论