rorkai/app-store-connect-cli-skills is a community-maintained collection of Agent Skills for using the asc command-line tool with Apple App Store Connect and Apple Ads. It helps coding agents automate builds, TestFlight, metadata, submissions, signing, and advertising workflows.
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 rorkai/app-store-connect-cli-skills --skill asc-aso-auditgit clone --depth 1 https://github.com/rorkai/app-store-connect-cli-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/rorkai/app-store-connect-cli-skills/asc-aso-audit)<a href="https://agentmods.dev/skills/rorkai/app-store-connect-cli-skills/asc-aso-audit"><img src="https://agentmods.dev/badge/skills/rorkai/app-store-connect-cli-skills/asc-aso-audit/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/rorkai/app-store-connect-cli-skills/asc-aso-audit"><img src="https://agentmods.dev/badge/skills/rorkai/app-store-connect-cli-skills/asc-aso-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- 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 | $0.00040 | $0.02650 |
| Opus 5 | $0.00020 | $0.01325 |
| Sonnet 5 | $0.00008 | $0.00530 |
| Haiku 4.5 | $0.00004 | $0.00265 |
Grade A, and why
asc-aso-audit 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- asc-aso-audit — 100% identical, 4 lines differ
How it starts
The opening of the file, as written. The whole thing — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
asc ASO audit
Run a two-phase ASO audit: offline checks against local metadata files, then keyword gap analysis via Astro MCP. When available, include Apple-generated app tags as a discoverability signal.
Preconditions
- Metadata pulled locally into canonical files via
asc metadata pull --app "APP_ID" --version "1.2.3" --dir "./metadata". - If metadata came from
asc migrate exportorasc localizations download, normalize it into the canonical./metadatalayout before running this skill. - For Astro gap analysis: app tracked in Astro MCP (optional — offline checks run without it).
- For Apple-generated discoverability tags:
asc app-tags list --app "APP_ID" --output jsonworks when the API returns tags for the app.
Before You Start
- Read
references/aso_rules.mdto understand the rules each check enforces. - Identify the latest version directory under
metadata/version/(highest semantic version number). Use this for all version-level fields. - The primary locale is
en-USunless the user specifies otherwise.
Metadata File Paths
- App-info fields (
subtitle):metadata/app-info/{locale}.json - Version fields (
keywords,description,whatsNew):metadata/version/{latest-version}/{locale}.json - App name: May not be present in exported metadata. If
nameis missing from the app-info JSON, fetch it viaasc apps info listor ask the user. Do not flag it as a missing-field error.
Phase 1: Offline Checks
Run these 5 checks against the local metadata directory. No network calls required.
1. Keyword Waste
Tokenize the subtitle field (and name if available). Flag any token that also appears in the keywords field — it is already indexed and wastes keyword budget.
Severity: ⚠️ Warning
Example: "quran" appears in subtitle AND keywords — remove from keywords to free 6 characters
How to check:
- Read
metadata/app-info/{locale}.jsonforsubtitle(andnameif present) - Read
metadata/version/{latest-version}/{locale}.jsonforkeywords - Tokenize subtitle (+ name):
- Latin/Cyrillic scripts: split by whitespace, strip leading/trailing punctuation, lowercase
- Chinese/Japanese/Korean: split by
、，,or iterate characters — each character or character-group is a token. Whitespace tokenization does not work for CJK. - Arabic: split by whitespace, then also generate prefix-stripped variants (remove ال prefix) since Apple likely normalizes definite articles. For example, "القرآن" in subtitle should flag both "القرآن" and "قرآن" in keywords.
- Split keywords by comma, trim whitespace, lowercase
- Report intersection (including fuzzy matches from prefix stripping)
What ships with it
1 file 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.
- 5d ago Changed 7cabafa6277c
- 11d ago First seen · 248 lines · 40 tokens per session scan A a76e5f16db36
asc-aso-audit is a skill published in the GitHub repository rorkai/app-store-connect-cli-skills (1,024 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 2,650 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 2026-08-30.
Other skills, from other repositories
app-rejection-recovery
Diagnoses App Store rejections, drafts Resolution Center responses, and plans the fix for resubmission. Use when the user says "my app was rejected", "Apple rejected my app", "App Review rejection", "guideline violation", "Resolution Center response", "guideline 2.1", "guideline 4.3", "guideline 5.1.1", "binary…
asc-submission
Prepare an app for App Store submission or TestFlight distribution using the App Store Connect MCP server. Use when user says "prepare submission", "submit to app store", "prepare for review", "update metadata", "set what's new", "check submission readiness", "distribute to testflight", or wants to manage App Store…
asc-build-check
Check the latest CI build status and debug failures using the App Store Connect MCP server. Use when user says "check build", "what broke", "CI status", "build failing", or asks about recent build failures. Also use for signing issues, provisioning profiles, bundle ID capabilities, or Developer Portal queries.
review-management
Pull, cluster, triage, and respond to App Store reviews via the App Store Connect MCP. Use when you need to fetch recent reviews, analyze sentiment, draft developer responses, track recurring themes as product signals, or close the loop on a rating recovery campaign. Trigger phrases: "triage reviews", "respond to…
asc-audit
Read-only drift check between live App Store Connect state, the repo, and whatever launch/submission docs claim. Use before quoting any build/version/TestFlight number back to the user, before trusting a canonical "where we stand" doc block, and as the required first step of submission-preflight before any submit.…
submission-preflight
Pre-submission risk audit for App Store review — catch the rejection triggers (metadata, privacy, IAP, design, account, legal) BEFORE you submit, by app type. Use when the user says "preflight", "will this get rejected", "check before submitting", "review readiness", "submission checklist", "App Review guidelines"…