Keyword Optimizer logo

Keyword Optimizer

Community
rshankras
keyword-optimizer

Optimize app title, subtitle, and keywords for maximum App Store discoverability. Use when launching a new app, improving search rankings, entering new markets/languages, or safely optimizing ASO for an app with existing traffic.

Overview

Publisherrshankras
Repositoryclaude-code-apple-skills
Skill namekeyword-optimizer
Stars
744
Forks
70
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by rshankras on GitHub. Read the source before you install it.

Installation

Install the Keyword Optimizer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/rshankras/claude-code-apple-skills.git /tmp/claude-code-apple-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-apple-skills/skills/app-store/keyword-optimizer .claude/skills/keyword-optimizer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Keyword Optimizer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Keyword Optimizer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Keyword Optimizer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Keyword Optimizer

Optimize app title, subtitle, and keywords for maximum App Store discoverability.

When This Skill Activates

  • User is launching a new app
  • User wants to improve search rankings
  • User asks about ASO (App Store Optimization)
  • User is entering new markets/languages
  • User wants to analyze keyword opportunities
  • User needs safe optimization for existing apps

Reference Files

Before optimizing, load these reference materials:

FilePurpose
keyword-criteria.mdPopularity/Difficulty sweet spots, opportunity scoring
advanced-tactics.mdCross-localization, screenshot indexing, velocity boost
existing-app-strategy.mdSafe optimization for apps with existing traffic

Information Gathering

Before optimizing, ask about:

  1. App Identity

    • What does the app do in one sentence?
    • What category is it in?
    • What's the current app name (if exists)?
  2. Target Keywords

    • What would users search to find this app?
    • What problem words would they use?
    • Any branded terms to include?
  3. Competition

    • Main competitors?
    • What keywords do they target?
    • Where can you realistically compete?
  4. Goals

    • Brand awareness vs. category traffic?
    • Specific markets to prioritize?

Keyword Strategy

Where Keywords Count

FieldLimitWeightNotes
App Name30 charsHighestMost valuable real estate
Subtitle30 charsHighVisible in search, below name
Keywords100 charsMediumNot visible to users
Description4000 charsLow**Apple says indexed, debated

Keyword Types

  1. Branded - Your app name, company name
  2. Category - Generic terms (e.g., "todo app", "weather")
  3. Feature - Specific functionality (e.g., "offline maps")
  4. Problem - User pain points (e.g., "forget tasks")
  5. Long-tail - Specific phrases (e.g., "minimalist habit tracker")

Optimization Process

Step 1: Keyword Research

Generate Initial List:

1. Brainstorm 50+ keywords
2. What would YOU search for this app?
3. Check competitor names/subtitles
4. Use autocomplete suggestions
5. Consider misspellings users make

Research Tools:

  • App Store Search Autocomplete
  • AppFollow, Sensor Tower, AppTweak (paid)
  • Google Keyword Planner (related terms)
  • Competitor subtitle/keyword analysis

Step 2: Prioritize Keywords

Rate each keyword on:

FactorQuestion
RelevanceDoes it accurately describe your app?
VolumeDo people actually search this?
DifficultyCan you realistically rank?
IntentWill searchers want your app?

Priority Matrix:

High Volume + Low Difficulty = 🎯 Target First
High Volume + High Difficulty = 💪 Long-term Goal
Low Volume + Low Difficulty = ✅ Easy Wins
Low Volume + High Difficulty = ❌ Skip

Step 3: Allocate Keywords

App Name (30 characters):

[Brand Name] - [Top Keyword Phrase]
or
[Brand Name]: [Value Proposition]

Examples:
"Notion - Notes & Docs"
"Calm: Sleep & Meditation"
"Fantastical - Calendar & Tasks"

Subtitle (30 characters):

[Second Priority Keywords] / [Unique Value]

Examples:
"Focus Timer & Daily Planner"
"Simple Habit Building"
"Weather Radar & Forecasts"

Keywords Field (100 characters):

Rules:
- Comma-separated, NO spaces after commas
- No plurals (Apple handles it)
- No duplicates from name/subtitle
- No category name (already indexed)
- Single words perform better than phrases

Example:
"timer,pomodoro,focus,concentration,study,productivity,work,session,break,technique"

Character Optimization

Maximize 100 Characters

Bad (wastes characters):

task manager, todo list, productivity app, reminder app, checklist

Good (efficient):

task,todo,productivity,reminder,checklist,planner,organize,gtd,schedule,daily

Savings:

  • Remove spaces after commas
  • Don't repeat words in different forms
  • Skip obvious words (app, free, best)

Word Combinations

Apple combines words from all fields:

Name: "Focus Timer"
Subtitle: "Pomodoro Technique"
Keywords: "study,productivity,work,session"

Searchable combinations:
- "focus timer"
- "pomodoro timer"
- "focus productivity"
- "study timer"
- "work focus"
(and more...)

Cross-Field Deduplication

Apple indexes words from all three fields for the same locale — a word only needs to appear once. If a word appears in Title, don't repeat it in Subtitle or Keywords; if it appears in Subtitle, don't repeat it in Keywords.

Before & After Example

❌ BEFORE (duplicated words waste ~38 characters):
Title:    "Focus Timer - Stay Productive"
Subtitle: "Pomodoro Timer & Focus Sessions"
Keywords: "timer,focus,pomodoro,productive,study,work,session,break"

✅ AFTER (zero duplication, 5 new keywords gained):
Title:    "Focus Timer - Stay Productive"
Subtitle: "Pomodoro Technique & Deep Work"
Keywords: "study,concentration,interval,tomato,distraction,block,exam,revision,flowstate,desk"

Quick Dedup Check

CheckRule
Title word in Subtitle or Keywords?Remove from the lower field
Subtitle word in Keywords?Remove from Keywords
Plural/singular variant across fields?Keep only in highest field
Stop words (a, the, and, for)?Don't include anywhere — auto-indexed

Common Mistakes

Don't Do This:

  • Using spaces after commas in keywords
  • Duplicating words across fields
  • Including your category name
  • Using competitor brand names
  • Adding "app" or "application"
  • Including "free" (filterable separately)
  • Using special characters or emoji
  • Repeating singular/plural forms

Do This:

  • Research before guessing
  • Prioritize relevance over volume
  • Update keywords quarterly
  • Track ranking changes
  • Localize keywords per market

Keyword Template

APP NAME STRATEGY
━━━━━━━━━━━━━━━━━
Current: [existing name or blank]
Proposed: [Brand] - [Keywords]
Characters: [X/30]
Primary keywords: [list]

SUBTITLE STRATEGY
━━━━━━━━━━━━━━━━━
Current: [existing subtitle or blank]
Proposed: [keyword-rich subtitle]
Characters: [X/30]
Secondary keywords: [list]

KEYWORDS FIELD (100 chars)
━━━━━━━━━━━━━━━━━━━━━━━━━
Proposed: keyword1,keyword2,keyword3,...
Characters: [X/100]

EXPECTED COMBINATIONS
━━━━━━━━━━━━━━━━━━━━━
• [combination 1]
• [combination 2]
• [combination 3]
...

Localization Strategy

Priority Markets by Revenue

  1. 🇺🇸 United States (English)
  2. 🇨🇳 China (Simplified Chinese)
  3. 🇯🇵 Japan (Japanese)
  4. 🇬🇧 UK (British English - can differ!)
  5. 🇩🇪 Germany (German)
  6. 🇫🇷 France (French)
  7. 🇰🇷 South Korea (Korean)
  8. 🇪🇸 Spain (Spanish)
  9. 🇮🇹 Italy (Italian)
  10. 🇧🇷 Brazil (Portuguese)

Localization Tips

  • Don't just translate—research local search terms
  • Some markets search in English even for local apps
  • Character limits may be tighter in some languages
  • Hire native speakers to verify keywords make sense
  • Consider cultural differences in app usage

Tracking & Iteration

What to Track

  • Keyword rankings (use ASO tools)
  • Impressions (App Store Connect)
  • Conversion rate
  • Download sources

When to Update

  • Weekly: Check ranking changes
  • Monthly: Assess underperforming keywords
  • Quarterly: Major keyword refresh
  • Seasonally: Add seasonal keywords

A/B Testing

App Store Connect allows testing:

  • App icons
  • Screenshots
  • App previews

Use Product Page Optimization to test different approaches.

Quick Reference

Prohibited Terms

  • "Free" (use pricing filter instead)
  • "#1" or "best" without verification
  • Competitor names
  • "App" or "application"
  • Pricing information

Always Include

  • Core functionality words
  • Problem/solution words
  • Category-relevant terms
  • Action verbs users would search

Character Limits

App Name:      30 characters
Subtitle:      30 characters
Keywords:     100 characters
Description: 4000 characters (low SEO value)

Indie Developer Strategy

For building apps that generate $200-2,000/month:

The Sweet Spot Formula

Target keywords where:
- Popularity > 20 (enough traffic)
- Difficulty < 60 (beatable competition)

Ideal: Popularity 25-50, Difficulty < 45

Process

  1. Find underserved keywords using ASO tools (Astro, AppTweak)
  2. Build simple, single-feature apps around those keywords
  3. Double down on winners, abandon losers
  4. Portfolio effect compounds (30 apps × $500 = $15k/month)

See keyword-criteria.md for detailed scoring and evaluation.

Advanced Tactics Summary

Cross-Localization (Double Keywords)

Add Spanish (Mexico) locale with English keywords for US market. See advanced-tactics.md for all locales.

Screenshot Text Indexing (June 2025)

Apple OCR reads screenshot captions for keyword ranking. Put keywords in top/bottom of screenshots.

Existing App Optimization

Never change what's working. Use phased rollout. See existing-app-strategy.md for safe optimization.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Keyword Optimizer AI skill do?

Optimize app title, subtitle, and keywords for maximum App Store discoverability. Use when launching a new app, improving search rankings, entering new markets/languages, or safely optimizing ASO for an app with existing traffic.

Why use Keyword Optimizer on TypingMind?

Because you install it once and use it with any model. Keyword Optimizer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Keyword Optimizer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rshankras/claude-code-apple-skills/tree/main/skills/app-store/keyword-optimizer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Keyword Optimizer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Keyword Optimizer?

As many as you like. As long as a model supports skills, you can use Keyword Optimizer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Keyword Optimizer AI skill free?

Yes. It is published on GitHub by rshankras under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇