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 ios-appstore-release-managergit 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/ios-appstore-release-manager)<a href="https://agentmods.dev/skills/flaqai/ios-application-development-skills/ios-appstore-release-manager"><img src="https://agentmods.dev/badge/skills/flaqai/ios-application-development-skills/ios-appstore-release-manager/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/ios-appstore-release-manager"><img src="https://agentmods.dev/badge/skills/flaqai/ios-application-development-skills/ios-appstore-release-manager.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 | $0.00082 | $0.02094 |
| Opus 5.5 | $0.00033 | $0.00838 |
| Sonnet 5.5 | $0.00016 | $0.00419 |
| Haiku 4.5 | $0.00008 | $0.00209 |
Grade A, and why
ios-appstore-release-manager 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 2mo 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS App Store Release Manager
Keep release-specific data in the project's docs/app-store-connect/releases/ directory. Keep this Skill limited to workflow, schema, and tooling.
Read references/release-form-schema.md before creating, validating, translating, or filling a release. Read references/aso-handoff-schema.md before importing ASO copy. Read references/release-version-table.md when comparing existing versions or adding a new version row.
Workflow
- Locate the repository root and determine whether it is Flutter or native Xcode. Prefer explicit
--versionplus--build, then Flutterpubspec.yaml, then Xcode build settings. Never guess among multiple workspaces, projects, or schemes; request--workspace,--project, or--scheme. - Choose the translation source locale with the user. Use any App Store Connect locale as the source; default to
zh-Hansonly when the user has no preference. Runpython3 <skill-dir>/scripts/release_form.py new --repo <repo> --source-locale <locale>when a form does not exist. It reads the current version/build, finds the latest previous form, and creates a schema 8 draft. - If
$app-store-asoproduced anaso-handoff.json, import it only after validation withpython3 <skill-dir>/scripts/release_form.py import-aso <handoff> <form>. Import only description, promotional text, keywords, and What's New. Keep App Name and Subtitle as App Information recommendations; never write them automatically. - Review Git changes and model configuration to draft four source-language fields:
描述,推广文本,关键词, and此版本的新增内容. - Show all four drafts in the selected source language to the user. Track their approval independently. Do not translate or fill any public copy until all four are explicitly approved.
- Open the App Store Connect language selector and inventory every language shown under both the localized and unlocalized groups. Record their union in
locale_inventoryand preserve each locale's current inventory state. - Before translating or filling any locale, perform both mandatory preflight confirmations:
- Inspect the current session's available Skills and tools for
computer-use:computer-use. Report whether it is available and recordcomputer_use_availabilityin the form. Never assume availability from an earlier run. - Show the localized and unlocalized locale counts, then explicitly ask whether the user wants to translate and create the currently unlocalized languages. Do not infer the choice from a prior release. Record
unlocalized_locale_policyand setlocalization_scopeto eitherapp_store_connect_localized_languagesorapp_store_connect_all_languages.
- Inspect the current session's available Skills and tools for
- Generate all four localized fields only for the confirmed scope, including a translated description in every included locale. Mark excluded unlocalized locales
not_requested_by_userwith page strategynot_in_scope; do not create, translate, or edit them. Use the active language model's own multilingual capability by default; translation must not depend on an external translation API, browser translation feature, network access, or third-party account. Only use an external translation service when the user explicitly requests that service. Keywords must be localized ASCII-comma-separated search terms, not sentence translations. - Before editing each in-scope field, read its current App Store Connect value and compare normalized text. If the page is empty, write the translation; if it matches, keep it; if it contains different content, pause and ask the user whether to inherit the existing value or replace it with this translation. Never make that conflict choice silently.
- Run
python3 <skill-dir>/scripts/release_form.py validate <form> --repo <repo>. Resolve errors before browser automation and report warnings requiring human judgment. - When Computer Use is available, use it with the user's existing Chrome login. If it is unavailable, state that clearly and use an available supported browser-control capability only after recording the fallback. Re-read the page before every edit. For each in-scope locale, inspect description, promotional text, keywords, and What's New before typing. Resolve every differing non-empty value with the user, then apply the recorded per-field strategy, save, and read all four displayed values back.
- Select only a build whose Apple processing is complete. Save the draft and verify the binding.
- Stop before Add for Review, Submit for Review, or any equivalent submission control. Report completed fields, excluded unlocalized languages, and remaining manual checks.
- Add or update the version row in
references/release-version-table.md, recording field status and inheritance without copying sensitive information.
What ships with it
6 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.
- 2mo ago First seen · 71 lines · 82 tokens per session scan A 7dd53d371e99
ios-appstore-release-manager is a skill published in the GitHub repository flaqai/ios-application-development-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 2,094 once invoked, about $0.0003 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 2026-08-31.
ios-appstore-release-manager compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ios-appstore-release-managerflaqai/ios-application-development-skills | Skill | 5 | 2mo ago | MIT | A | 82 | Codex |
| i18n-studioglebis/claude-skills | Skill | 409 | yesterday | MIT | A | 0 | Claude Code, Codex |
| init-xcode-appglebis/claude-skills | Skill | 409 | yesterday | MIT | A | 88 | Claude Code, Codex |
| typographyglebis/claude-skills | Skill | 409 | yesterday | MIT | A | 143 | Claude Code, Codex |
| library-syncglebis/claude-skills | Skill | 409 | yesterday | MIT | A | 42 | Claude Code, Codex |
| app-releaseglebis/claude-skills | Skill | 409 | yesterday | MIT | A | 166 | Claude Code, Codex |
| localization-l10nMindrally/skills | Skill | 297 | 29d ago | Apache-2.0 | A | 28 | Claude Code |