Playbooks: App Store and Google Play agent skills | AppGoat

Free agent skills that know which AppGoat calls to make, what each costs, and how to turn the data into a decision. Install once, ask in plain words, or put them on a schedule.
Runs a quick App Store / Google Play audit of one app with live AppGoat data – listing quality, ratings trend, recent complaints, keyword rankings, competitors and their recent changes – and ends with a prioritized fix list.
Finds underserved App Store / Google Play niches with live AppGoat data – search demand (keyword popularity) against weak supply (low ratings, abandoned incumbents, few strong apps) – and returns a ranked shortlist of app ideas with evidence and user pain points.
Researches App Store / Google Play keywords for one app with live AppGoat data (current ranks, competitor keyword gaps, popularity, difficulty, relevance) and rewrites the title, subtitle, keyword field and description within the store character limits.
Writes a weekly competitor digest for one App Store / Google Play app from an AppGoat competitor watch – what each competitor changed (title, subtitle, description, screenshots, icon), price and in-app purchase changes, new versions with release-note summaries, rating and chart moves, keyword gains and losses against the user's app, keyword gaps and review themes – and ends with 3 recommended actions linked to other playbooks. Sets up or reuses the competitor_set watch.
Turns recent negative App Store / Google Play reviews into deduplicated GitHub issues – one issue per problem topic, with linked and quoted reviews, new reviews added as comments to the existing issue instead of duplicates. Uses AppGoat review data and the gh CLI (or the GitHub MCP server).
Drafts a reply to every unanswered App Store and Google Play review of the user's own app, in the app's voice, through their connected App Store Connect / Play Console account – each reply is a dry run with a before/after diff and AppGoat guardrail scores (policy, tone, claims), and only the replies the user approves are posted.
Optimizes the user's Apple Ads (Search Ads) campaigns through their connected Apple Ads account – reads the last 14 days of keyword and search term reports, raises bids on keywords that convert under the target CPA (capped +30% per run), lowers or pauses keywords that spend without installs, adds converting search terms as exact keywords and wasteful ones as negatives – every change a dry run with a diff the user approves.
Sets up Apple Ads (Search Ads) search results campaigns for an app from scratch through the user's connected Apple Ads account – researches keywords (Apple's own suggestions and search popularity plus AppGoat keyword data), builds the standard Brand / Category / Competitor / Discovery structure with exact and Search Match ad groups, adds cross negatives so the campaigns don't bid against each other, and creates everything PAUSED for the user to review and enable. Every change is a dry run with a diff the user approves.
Localizes the user's own App Store / Google Play listing into new languages through their connected App Store Connect or Play Console account – picks target locales from markets with demand, researches the keywords people actually search in each country with AppGoat, writes a localized name, subtitle, keyword field and promotional text (Play title, short and full description) within the store limits, and pushes each locale as a dry run with a before/after diff the user approves.
Add AppGoat to Claude or Cursor in one click (or run one command in Claude Code) and every playbook comes with it as a prompt. Each playbook page has the steps for your client.
Coming soon: the Claude Code plugin. Today every client gets the playbooks as prompts of the hosted AppGoat MCP server.
The Free plan's 250 monthly credits cover a run of App audit (lite), Find app ideas, ASO keywords → metadata rewrite, Competitor digest, Reviews → GitHub issues, Reply to every review, Apple Ads optimizer, Apple Ads launch, Localization push. Every tool result shows what the call cost and what is left.
App store intelligence for your AI agent. Built in Berlin. Ships fast, actually answers emails.