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 rshankras/claude-code-apple-skills --skill localization-strategygit clone --depth 1 https://github.com/rshankras/claude-code-apple-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/rshankras/claude-code-apple-skills/localization-strategy)<a href="https://agentmods.dev/skills/rshankras/claude-code-apple-skills/localization-strategy"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/localization-strategy/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/rshankras/claude-code-apple-skills/localization-strategy"><img src="https://agentmods.dev/badge/skills/rshankras/claude-code-apple-skills/localization-strategy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00065 | $0.05451 |
| Opus 5 | $0.00032 | $0.02726 |
| Sonnet 5 | $0.00013 | $0.01090 |
| Haiku 4.5 | $0.00006 | $0.00545 |
Grade A, and why
localization-strategy 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 5d 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 — 595 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Localization Strategy
End-to-end localization planning for Apple platform apps — from market prioritization through translation workflow to localized App Store optimization.
When This Skill Activates
Use this skill when the user:
- Wants to localize their app for new markets
- Asks "which languages should I support?"
- Needs help deciding market expansion priorities
- Wants to plan a translation workflow
- Asks about internationalization (i18n) best practices
- Mentions "localization", "translation", "multi-language", or "global markets"
- Wants to understand localization ROI by language
- Needs cost estimates for translation
- Asks about right-to-left (RTL) layout support
- Wants to localize App Store metadata (title, description, keywords, screenshots)
Process
Phase 1: Market Prioritization Framework
Not all languages are equal. Prioritize by revenue potential, not just speaker count.
Revenue Potential by Language
Based on App Store revenue data and per-user spending patterns:
| Language | Relative Revenue Potential | Why |
|---|---|---|
| English | Baseline (1.0x) | Largest single market, highest per-user spend |
| Japanese | 0.8-1.2x | Extremely high willingness to pay, especially for subscriptions |
| Chinese (Simplified) | 0.6-0.9x | Massive volume, growing per-user spend, competitive market |
| German | 0.4-0.6x | High per-user spend, values quality and privacy |
| French | 0.3-0.5x | Large market across France, Canada, Africa |
| Korean | 0.3-0.5x | Tech-savvy users, high app spending per capita |
| Spanish | 0.3-0.4x | Huge population, lower per-user spend, growing market |
| Portuguese (Brazilian) | 0.2-0.4x | Large market, mobile-first users, growing economy |
Key insight: Japanese and German users often pay 2-3x more per user than Spanish or Portuguese users. Volume vs. value is the fundamental tradeoff.
Category-Specific Priorities
App category changes which languages to prioritize first:
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.
- 5d ago First seen · 595 lines · 65 tokens per session scan A 9ac7fc8e5712
localization-strategy is a skill published in the GitHub repository rshankras/claude-code-apple-skills (710 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 5,451 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
i18n-localization
Internationalization and localization for global applications. Use when adding multi-language support, handling regional formats, or preparing apps for global markets.
i18n-localization
Internationalization and localization for web applications. Handles next-intl, react-intl, ICU MessageFormat, RTL layouts, and dynamic locale loading.
aso-listing
Research and improve app-store keywords, metadata, localization, and seasonal listing changes for Apple App Store and Google Play.
korean-autopilot
A Korean-language helper for Claude Code, the command-line coding assistant. It detects Korean requests about Claude Code and runs or explains suitable commands.
thinking-theory-of-constraints
When throughput or latency is pipeline-limited, identify the single binding constraint and exploit, subordinate, elevate, then recheck—ignore non-constraints.
electron-desktop
Desktop application development with Electron for Windows, macOS, and Linux. Use when building cross-platform desktop apps, implementing native OS features, or packaging web apps for desktop.