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 jihongboo/appstoreconnect-mcp --skill appstoreconnect-translationgit clone --depth 1 https://github.com/jihongboo/appstoreconnect-mcpWrote 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/jihongboo/appstoreconnect-mcp/appstoreconnect-translation)<a href="https://agentmods.dev/skills/jihongboo/appstoreconnect-mcp/appstoreconnect-translation"><img src="https://agentmods.dev/badge/skills/jihongboo/appstoreconnect-mcp/appstoreconnect-translation/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/jihongboo/appstoreconnect-mcp/appstoreconnect-translation"><img src="https://agentmods.dev/badge/skills/jihongboo/appstoreconnect-mcp/appstoreconnect-translation.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 | $0.00039 | $0.02699 |
| Opus 5 | $0.00019 | $0.01350 |
| Sonnet 5 | $0.00008 | $0.00540 |
| Haiku 4.5 | $0.00004 | $0.00270 |
Grade A, and why
appstoreconnect-translation 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 11d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
App Store Connect Translation & Localization Best Practices
Metadata localization is one of the most critical steps for driving international user acquisition, boosting App Store Optimization (ASO) rankings, and improving conversion rates (CVR). When configuring localized metadata in App Store Connect, you must adhere to Apple's rigid constraints and specific business logic.
🌐 Golden Rule: Primary Locale Parity
Every field populated in the primary locale MUST also be populated in every other configured locale.
This rule applies universally across all localization layers:
| Localization Layer | Scope |
|---|---|
| App Store Version Localization | description, keywords, whatsNew (non-v1.0), supportUrl, marketingUrl |
| App Info Localization | name, subtitle, privacyPolicyUrl, privacyChoicesUrl |
| In-App Purchase / Subscription Localization | name, description |
| Beta Build Localization | whatsNew (TestFlight notes) |
Why this matters:
- Leaving a field blank in a secondary locale causes Apple to fall back to the primary locale value, which may be in the wrong language for that market — harming user trust and store conversion.
- For mandatory fields like
supportUrl, an empty value in any locale can trigger an App Review rejection. - Incomplete localizations are a leading cause of inconsistent App Store pages across regions.
Operational Rule for MCP Tool Execution: Before completing any localization task, always verify that every field set in the primary locale has a corresponding value in all target locales. If the user has not provided locale-specific content for a given field, default to carrying over the primary locale value verbatim rather than leaving the field empty. Prompt the user only when a field genuinely requires locale-specific adaptation (e.g., translated descriptions, region-specific URLs).
1. Core Metadata Localization Guide
A. App Store Version Metadata (App Store Version Localization)
- App Description (Description)
- Length Limit: Maximum 4,000 characters.
- Formatting Principle: Keep the first 2-3 lines highly engaging and clear, as this is the "above the fold" content shown before the "More" toggle. Use lists or emojis to partition key features and value propositions.
- Search Keywords (Keywords)
- Length Limit: Maximum 100 characters (including separators).
- Separator Rule: Use half-width commas (
,) without spaces. Spaces consume characters and cause indexing issues. - ASO Optimization: Consolidate functional keywords, synonyms, and category terms. Combine them to fill 90–99 characters to maximize your indexing potential.
- ⚠️ Translation Keyword Rule: After translating keywords to a target language, always count the resulting character length. Translated keywords are almost always shorter than the primary locale due to CJK character density differences. You MUST expand the keyword list with additional synonyms, use-case terms, and long-tail phrases to reach 90–99 characters. Never submit translated keywords below 80 characters — this wastes indexing slots and directly harms ASO rankings in that market.
- First-Version Constraint (v1.0 / Prepare For Submission)
- ⚠️ Crucial Trap: If the App Store version is the very first release (v1.0), the
whatsNew(What's New in This Version) parameter MUST be set tonil(empty) during creation or update. - Reason: Since a first version has no previous version to compare to, Apple's API does not allow release notes. Passing text to this field will result in a
409 STATE_ERROR - Attribute 'whatsNew' cannot be edited at this timeAPI rejection. This field is only allowed for subsequent app updates (v1.1, v2.0, etc.).
- ⚠️ Crucial Trap: If the App Store version is the very first release (v1.0), the
- Support URL (supportUrl)
- Required: Mandatory for all App Store versions; omitting it will cause submission rejection. Must be a fully qualified
https://orhttp://URL.
- Required: Mandatory for all App Store versions; omitting it will cause submission rejection. Must be a fully qualified
- Marketing URL (marketingUrl)
- Optional: Fully qualified
https://orhttp://URL. Leave empty if not applicable.
- Optional: Fully qualified
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.
- 11d ago First seen · 204 lines · 39 tokens per session scan A c963452c294f
appstoreconnect-translation is a skill published in the GitHub repository jihongboo/appstoreconnect-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 2,699 once invoked, about $0.0002 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
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — Diagnostics issues first, then errors, failed tool calls, latency, regressions, and low online-eval scores. With the Opik MCP connected it lists the project's agentinsightsissue entities, offers to turn Diagnostics on when the project has it…
cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find gaps', 'what topics are weak', or when you…
quick-capture
Use this skill to drop a new task into GSD Task Manager from any AI assistant that has the gsd-mcp-server connected.
edt-mcp-project-translation
Inspect and run EDT translation workflows through EDT-MCP while preserving declared languages, dictionaries, storage, and programmatic metadata names.
event-staffing-ordering
Order W-2 event staff for US/CA events through TempGuru.
delegacion-local
Regla y catálogo para delegar pasos mecánicos (resumir, clasificar, extraer, boilerplate, mensaje de commit desde un diff, traducir texto o archivo, resumir salida de lint/tests/CI, explicar código, describir una imagen, verificar si el backend local está disponible) a modelos locales vía las tools local del MCP…