Skip to content
SkillModel-led3,405 tokens in use

aso

Audits an App Store or Google Play listing: fetches it, scores each dimension, compares competitors and writes an optimization report.

61,709 stars on the repository MIT Licensecoreyhaines31/marketingskills · skills/aso
npx skills add coreyhaines31/marketingskills --skill aso
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing aso costs

47tokens idle
3,405tokens in use
11,612tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure19/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

aso works through a listing audit in phases. It detects the store from the URL, fetches the listing, assesses brand maturity, scores each dimension, optionally compares competitors and generates a report.

It knows the field limits and rules of Apple and Google Play, including title, subtitle, short description, promotional text and screenshots, and ends with a checklist of common issues.

What You Get

  • A fetched summary of listing fields such as title, subtitle, screenshots, ratings and recent reviews
  • A score for each dimension against written scoring criteria
  • An optional side-by-side comparison with competitor listings
  • A report built from a report template
  • A common issues checklist and store-specific rules

Common Use Cases

  • Auditing a new app’s listing before launch
  • Choosing between title and keyword options
  • Finding why downloads are low despite traffic
  • Comparing a listing with two competitors

What Makes It Unique

It adjusts scoring to brand maturity, so an established brand and a new app are judged differently. References hold the character limits and specs for Apple and Google Play, scoring criteria and benchmarks.

Under The Hood

The SKILL.md and five references (Apple specs, Google Play specs, benchmarks, scoring criteria and a report template) are loaded as context. The skill ships no scripts. It tells the agent to use WebFetch to read the public store listing page and to search the web for the listing when only a name is given.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers