poly-glot-ai-workspace: Skill for Claude Code

.agents/skills/polyglot-asc-publish/SKILL.md

polyglot-asc-publish is a skill for Claude Code, Codex from hmoses/poly-glot-ai-workspace. It costs 57 tokens per session (1,179 once invoked), scanned A, original, MIT.

A release workflow for sending iOS and macOS builds and translated App Store information to App Store Connect, Apple's service for managing App Store submissions. It checks versions, build records, source changes, processing, and metadata before or after publishing.

In plain words
What is it for?
Use it to push builds, update translated store text such as What's New, and move an app toward review when the required access and tools are available.
Why use it?
It helps avoid uploading the wrong build, reusing a build number, changing unrelated code, or publishing incomplete store information.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is hmoses/poly-glot-ai-workspace's own configuration. It tells Claude Code and Codex how to work on poly-glot-ai-workspace itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything poly-glot-ai-workspace configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hmoses/poly-glot-ai-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/hmoses/poly-glot-ai-workspace/main/.agents/skills/polyglot-asc-publish/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/hmoses/poly-glot-ai-workspace

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for polyglot-asc-publish

README.md
[![agentmods](https://agentmods.dev/badge/skills/hmoses/poly-glot-ai-workspace/polyglot-asc-publish/github.svg)](https://agentmods.dev/skills/hmoses/poly-glot-ai-workspace/polyglot-asc-publish)
Your own site
<a href="https://agentmods.dev/skills/hmoses/poly-glot-ai-workspace/polyglot-asc-publish"><img src="https://agentmods.dev/badge/skills/hmoses/poly-glot-ai-workspace/polyglot-asc-publish/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.

agentmods 80×15 button for polyglot-asc-publish

Your own site · 80×15
<a href="https://agentmods.dev/skills/hmoses/poly-glot-ai-workspace/polyglot-asc-publish"><img src="https://agentmods.dev/badge/skills/hmoses/poly-glot-ai-workspace/polyglot-asc-publish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,179 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.01179
Opus 5.5 $0.00023 $0.00472
Sonnet 5.5 $0.00011 $0.00236
Haiku 4.5 $0.00006 $0.00118

Measured 2d ago against content hash 5e993f2e27f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

polyglot-asc-publish 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 2d 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.

.agents/skills/polyglot-asc-publish/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Poly-Glot AI Workspace ASC Publishing Skill

Updated 2026-10-15. Maintained in GitHub for cross-session retrieval. This repository skill is not automatically installed as a ChatGPT system-level skill.

First actions

  1. Read this skill and verify real-time GitHub, App Store Connect (ASC), and local build access. Do not claim access to ASC, signing, or a user computer without checking tools.
  2. Inspect BOTH platform's current ASC version records and newest valid processed builds. Determine platform from explicit platform attributes, checking minOsVersion/lsMinimumSystemVersion as corroborating hints, never just the numerical build sequence.
  3. Read the remote HEAD of the correct source repository on main. Check what the user actually requested; avoid unrelated code, subscriptions, paywall, telemetry, or site changes.
  4. For build/version changes, bump only the required version/build identifiers consistently in all three authoritative files, ensuring no reused build number, and validate Xcode project build settings.
  5. Push ONLY to the correct repo, validate CI, build/sign/upload if authorized tooling is genuinely available, confirm Apple processing, verify ASC metadata and linked binaries, then move to review only when requested.
  6. Report actual Git commit SHAs, build/version, upload/processing evidence, ASC state and localization coverage; distinguish completed, pending, failed and unverified tasks.

Authorized repositories

  • iOS/iPadOS: hmoses/polyglot-workspace-ios, main
  • macOS: hmoses/polyglot-workspace-mac, main
  • MCP/shared: hmoses/poly-glot-ai-workspace, main
  • Website: hmoses/poly-glot-site, main
  • Frozen legacy repos: hmoses/polyglot-workspace and hmoses/polyglot-prompt-studio: NEVER WRITE.

Required version files

  • iOS: ios/App/App/public/index.html; ios/App/App.xcodeproj/project.pbxproj; ios/App/App/Info.plist.
  • macOS: PolyGlotAI/PolyGlotAI/Resources/public/index.html; PolyGlotAI/PolyGlotAI.xcodeproj/project.pbxproj; active PolyGlotAI/PolyGlotAI/Resources/Info.plist (not the similarly named unused plist, unless source configuration proves otherwise).
  • Preserve _isMac=true on Mac and false/absent on iOS. Keep current deployment targets (IPHONEOS_DEPLOYMENT_TARGET=15.0 and MACOSX_DEPLOYMENT_TARGET=15.0) unless the user expressly authorizes a supported change.
  • Read remote changes before writing. Rebase/pull or use SHA-conditional updates; never overwrite concurrent commits.

Read the full file on GitHub · 49 lines

Changes

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.

  1. 2d ago First seen · 49 lines · 57 tokens per session scan A 5e993f2e27f1

Subscribe to this mod's changes

polyglot-asc-publish is a skill published in the GitHub repository hmoses/poly-glot-ai-workspace (0 stars, last pushed 4d ago), licensed MIT. It adds 57 tokens to every session and 1,179 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-17.

Related

Other skills, from other repositories

simple-english

Rewrite text to ASD-STE100 Simplified Technical English.

NousResearch/hermes-agent · 16 tokens

whisper

Transcribe and translate speech in 99 languages.

NousResearch/hermes-agent · 13 tokens

website-maintainer

Use this skill when working on the Repomix documentation website in website/ directory, including VitePress configuration, multi-language content, or translation workflows.

yamadashy/repomix · 37 tokens

maui-localization-theming

Implement MAUI localization and theming. USE FOR: RESX/AppResources, runtime culture switching, RTL/FlowDirection, platform language metadata, AppThemeBinding, DynamicResource, light/dark/system themes, UserAppTheme. DO NOT USE FOR: general layout, accessibility audits, icon/splash assets.

dotnet/maui-labs · 73 tokens

ios-marketing-capture

Use when the user wants to automate capture of marketing screenshots for a SwiftUI iOS app across multiple locales, devices, or appearances. Covers full-screen shots, isolated element renders (carousel cards, widgets), and reproducible output naming. Triggers on marketing screenshots, locale screenshots, widget…

ParthJadhav/ios-marketing-capture · 78 tokens

ios-localization

Production-grade iOS localization skill covering String Catalogs (.xcstrings), CLDR pluralization, SwiftUI/UIKit localization APIs, RTL layout, date/number/currency formatting, and enterprise patterns (modular apps, white-label, accessibility localization). This skill should be used when creating or editing localized…

rusel95/ios-agent-skills · 265 tokens