Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add flaqai/ios-application-development-skills --skill app-store-asogit clone --depth 1 https://github.com/flaqai/ios-application-development-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/flaqai/ios-application-development-skills/app-store-aso)<a href="https://agentmods.dev/skills/flaqai/ios-application-development-skills/app-store-aso"><img src="https://agentmods.dev/badge/skills/flaqai/ios-application-development-skills/app-store-aso/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/flaqai/ios-application-development-skills/app-store-aso"><img src="https://agentmods.dev/badge/skills/flaqai/ios-application-development-skills/app-store-aso.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.00972 |
| Opus 5 | $0.00037 | $0.00486 |
| Sonnet 5 | $0.00015 | $0.00194 |
| Haiku 4.5 | $0.00007 | $0.00097 |
Grade A, and why
app-store-aso scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Store ASO
Optimize Apple App Store listings without presenting industry folklore as Apple-confirmed ranking behavior. Read references/apple-app-store-specs.md for current Apple constraints, references/audit-framework.md for analysis structure, and references/aso-handoff-schema.md before creating a handoff.
Workflow
- Establish the app, storefront, source locale, audience, business goal, release context, and provided evidence. Ask for a public App Store URL when available.
- Use current Codex web or browser capabilities to inspect public Apple product pages, Apple documentation, and explicitly named competitor pages. Record direct URLs and the retrieval date. Never use legacy
WebFetchinstructions. - Separate evidence into observed facts, Apple-documented requirements, and recommendations or hypotheses that require testing.
- If a page, field, screenshot set, performance metric, or competitor cannot be inspected, add it to an Evidence gaps section. Do not silently fabricate missing data.
- Audit positioning, relevance, differentiation, metadata clarity, screenshot narrative, previews, localization, ratings/reviews context, and conversion experiments. Use the scorecard in
audit-framework.mdonly as a planning aid, not an Apple ranking formula. - Draft source-locale recommendations for App Name, Subtitle, Description, Promotional Text, Keywords, and What's New. Enforce Apple limits. Each keyword must be longer than two characters, use ASCII commas, and keep the complete value at most 100 UTF-8 bytes.
- Review screenshots and previews against Apple's current specifications. Recommend a message sequence and testable hypotheses; do not invent device dimensions from memory when the current Apple table can be checked.
- Compare competitors only from pages actually inspected. Present a compact matrix of positioning, metadata, proof, visual story, and gaps. Label any inference.
- Present recommendations in priority order with expected mechanism, effort, evidence, and a measurable validation plan. Do not describe a speculative ranking factor as Apple-confirmed.
- Ask the user to approve Description, Promotional Text, Keywords, and What's New separately. App Name and Subtitle are recommendations under App Information and are never part of the automatic release import.
- A pending
aso-handoff.jsontemplate may be created at any time withscripts/aso_handoff.py new. Finalize it asapproval_status: approvedonly after all four release fields are complete and independently approved. Then hand off to$ios-appstore-release-manager.
What ships with it
8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 57 lines · 74 tokens per session scan A c93eb72b24d3
app-store-aso is a skill published in the GitHub repository flaqai/ios-application-development-skills (4 stars, last pushed 27d ago), licensed MIT. It adds 74 tokens to every session and 972 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
compose-ui-builder
Author and edit a Compose UI design over MCP against a compose-preview serve deployment — create a screen or a Wear widget, insert and edit nodes, and export the Kotlin, PNG or SVG. Use when asked to build, change, or review a UI Builder design (a URL like /ui-builder/ / ), to turn a design into Compose code, or to…
useragent-get-useragent
Parses a user agent string and returns structured information about the browser, OS, device, and bot status.
imagegen-frontend-mobile
Generate premium app-native mobile screen images and coherent multi-screen flows for iOS, Android, or cross-platform products. Use when the deliverable is mobile UI imagery, screen concepts, or phone-mockup presentations. Produce images only; do not write app code, website sections, or brand-guideline boards.
compose-preview
Render Compose @Preview functions to PNG outside Android Studio. Use this to verify UI changes, iterate on designs, and compare before/after states across Android (Jetpack Compose) and Compose Multiplatform Desktop projects.
kotlin-specialist
Provides idiomatic Kotlin implementation patterns including coroutine concurrency, Flow stream handling, multiplatform architecture, Compose UI construction, Ktor server setup, and type-safe DSL design. Use when building Kotlin applications requiring coroutines, multiplatform development, or Android with Compose.…
tastemaker
Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…