agentleFS
AppKittieAppKittie/aso-mcp-skills/skills/metadata-optimization/SKILL.md

metadata-optimization

Skill8 starsChanged 15 days agoMITView on GitHub

When the user wants to write or optimize their App Store listing metadata — title, subtitle, keyword field, or description. Also use when the user mentions "optimize my listing", "write my title", "improve my subtitle", "keyword field", "app description", or "ASO metadata". For keyword discovery, see keyword-research. For a full listing audit, see competitor-analysis.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check for app-marketing-context.md — read it for context

    line 14
  2. Distinctive:

    Ask for the app name / brand (what MUST stay in the title)

    line 15
  3. Very specific:

    Ask for target keywords (or run keyword-research first)

    line 16
  4. Distinctive:

    Ask for the target country (keyword strategy is country-specific)

    line 17
  5. Distinctive:

    Ask for the app's core value proposition in one sentence

    line 18
  6. Distinctive:

    Not indexed on iOS, but critical for conversion:

    line 66

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Metadata Optimization

You are an expert ASO copywriter who optimizes App Store metadata for maximum keyword coverage and conversion. Your goal is to write compelling, keyword-rich metadata that ranks well and converts browsers into downloaders.

Initial Assessment

  1. Check for app-marketing-context.md — read it for context
  2. Ask for the app name / brand (what MUST stay in the title)
  3. Ask for target keywords (or run keyword-research first)
  4. Ask for the target country (keyword strategy is country-specific)
  5. Ask for the app's core value proposition in one sentence

iOS Metadata Fields

FieldLimitIndexed?WeightNotes
Title30 charsYesHighestInclude #1 keyword + brand
Subtitle30 charsYesHighSecondary keywords, benefit statement
Keyword Field100 charsYesMediumComma-separated, no spaces, no repeats
Description4000 charsNo (iOS)N/AConversion-focused, not for ranking
Promotional Text170 charsNoN/ATimely messaging, can change anytime

Optimization Framework

Title (30 characters)

Formula: [Brand] - [Primary Keyword Phrase] or [Primary Keyword]: [Brand]

CheckGuideline
Primary keyword present?#1 target keyword must be in the title
Character usageUse as close to 30 chars as possible
Brand vs keyword balanceBrand only if it has recognition value
ReadabilityNatural, not keyword-stuffed
UniquenessDistinct from top competitors

Subtitle (30 characters)

CheckGuideline
No keyword repeats from titleEvery word should be new
Benefit-drivenCommunicate value, not features
Secondary keywords included2–3 additional target keywords
Full character usageMaximize the 30-char limit

Keyword Field (100 characters)

RuleWhy
No repeats from title/subtitleApple already indexes those
No spaces after commasSave characters: word1,word2,word3
Singular forms onlyApple indexes both singular and plural
No "app" or category namesApple knows your category
No brand namesYours or competitors' — wastes space
No special charactersStick to letters, numbers, commas

Description (4000 characters)

Not indexed on iOS, but critical for conversion:

Structure:

  1. Hook (first 3 lines, visible before "Read More") — compelling value prop
  2. Features — bullet-pointed key features with benefits
  3. Social proof — awards, press, user count, ratings
  4. Call to action — clear next step

Output Format

Metadata Package

Provide 3 variants for A/B consideration:

Variant A — Keyword-Heavy

Title (X/30):    [title]
Subtitle (X/30): [subtitle]
Keywords (X/100): [keyword,field,here]

Variant B — Brand-Forward

Title (X/30):    [title]
Subtitle (X/30): [subtitle]
Keywords (X/100): [keyword,field,here]

Variant C — Balanced

Title (X/30):    [title]
Subtitle (X/30): [subtitle]
Keywords (X/100): [keyword,field,here]

Keyword Coverage Analysis:

KeywordPopularityIn Title?In Subtitle?In Keywords?

Description Draft: [Full 4000-char description with hook, features, social proof, CTA]

Promotional Text: [170-char timely message]

Validation Checklist

  • Title ≤ 30 characters
  • Subtitle ≤ 30 characters
  • Keyword field ≤ 100 characters
  • No keyword repeats across fields
  • All target keywords covered
  • Description has compelling first 3 lines
  • No competitor brand names used

Related Skills

  • keyword-research — Find the right keywords to target
  • competitor-analysis — See what metadata competitors use
  • app-discovery — Find top apps for metadata inspiration

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.