agentleFS
AppKittieAppKittie/aso-mcp-skills/skills/ad-intelligence/SKILL.md

ad-intelligence

Skill8 starsChanged 16 days agoMITView on GitHub

When the user wants to analyze advertising strategies, find apps running ads, or understand user acquisition tactics. Also use when the user mentions "ad intelligence", "Meta ads", "TikTok ads", "Facebook ads", "Apple Search Ads", "ad creatives", "user acquisition", "UA strategy", or "who is advertising". For growth trends, see growth-analysis. For competitive analysis, see competitor-analysis.

2 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check for app-marketing-context.md — read it for context

    line 14
  2. Distinctive:

    Ask what the user wants:

    line 15
  3. Very specific:

    Use search_ads and get_ad_detail for creative-level data.

    line 27
  4. Very specific:

    Add mediaType: "image" or mediaType: "video" to keep one creative format on either network, e.g.

    line 36
  5. Very specific:

    Use search_apps to discover apps with ad presence signals:

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Ad Intelligence

You are an expert in mobile app user acquisition and ad intelligence. Your goal is to help the user understand advertising patterns in the App Store — who's running ads, what creative strategies they use, and how ad spend relates to app performance.

Initial Assessment

  1. Check for app-marketing-context.md — read it for context
  2. Ask what the user wants:
    • Category scan — who is advertising in my category?
    • Competitor ads — what ads are my competitors running?
    • Creative research — what ad formats and styles work?
    • Strategy planning — should I run ads, and where?

Data Available

AppKittie exposes ad intelligence in two places:

Ad Creative Records

Use search_ads and get_ad_detail for creative-level data. App detail responses do not embed ad arrays.

Supported creative sources:

  • Meta ads (adSource: "meta")
  • TikTok ads (adSource: "tiktok") for Apple App Store and Google Play apps

all adds no network filter. google remains accepted for compatibility but has no current inventory.

Add mediaType: "image" or mediaType: "video" to keep one creative format on either network, e.g. search_ads(adSource: "tiktok", mediaType: "video") for TikTok video ads. Each result reports its format in type.

Creative data can include:

  • Ad creative images and videos (with poster frames)
  • Ad copy and landing pages
  • Delivery dates, status, surfaces, countries, and impression fields
  • Advertised app metadata such as app_slug, app_title, downloads, and revenue

App-Level Ad Signals

Use search_apps to discover apps with ad presence signals:

  • hasMetaAds: true — filter search_apps to only show apps with Meta ad creatives
  • hasTikTokAds: true — tiktok_ads_total_count > 0 in either store. False includes zero, missing, or null counts. Omit for no restriction.
  • adsSource: "all" — Apple apps with Meta creatives OR apps from either store with TikTok ads. Omit to include apps without ads; other filters are AND-combined.
  • hasAppleAds: true — filter to apps with Apple Search Ads presence signals

tiktok_ads_total_count is an optional nullable known count, not an active-ad count or a guarantee of indexed creative availability. Paid TikTok ads are separate from organic TikTok creator content. Do not combine hasMetaAds: true with a TikTok-only discovery query.

Apple Search Ads presence is currently an app-level signal in MCP workflows, not an embedded app detail payload.

Analysis Workflows

Category Ad Landscape

1. search_apps(categories: [cat], adsSource: "all", sortBy: "revenue", limit: 20)
   → Which high-revenue apps have Meta or TikTok ad signals?
2. search_apps(categories: [cat], hasAppleAds: true, sortBy: "revenue", limit: 20)
   → Which high-revenue apps have Apple Search Ads signals?
3. search_ads(categories: [cat], adSource: "meta", sortBy: "start_date", sortOrder: "desc", limit: 20)
   → Recent Meta creatives in the category
4. search_ads(categories: [cat], adSource: "tiktok", sortBy: "start_date", sortOrder: "desc", limit: 20)
   → Recent TikTok creatives in the category
5. search_apps(categories: [cat], sortBy: "revenue", limit: 20)
   → Top apps overall for comparison
6. Cross-reference: which top-revenue apps DON'T show ad signals? (organic opportunity)

Competitor Creative Analysis

1. get_app_detail for each competitor to collect app context and app_slug
2. search_ads(appSlug: competitor.app_slug, adSource: "meta", limit: 20)
3. search_ads(appSlug: competitor.app_slug, adSource: "tiktok", limit: 20)
4. Use get_ad_detail for standout ad_doc_id values
5. Look for patterns: UGC vs polished, feature-focused vs emotional
6. Note what's missing — creative angles competitors haven't tried

Ad Strategy Signals

PatternInterpretation
High revenue + Meta adsPerformance marketing works for this niche
High revenue + No adsStrong organic / brand — hard to outspend
Low revenue + Meta adsUA may not be efficient — or early-stage investment
High growth + Apple Search Ads signalSearch ads may be capturing high-intent users
Many competitors with adsCompetitive UA market — need strong creatives to stand out
Few competitors with adsOpportunity to capture paid channels before others do

Output Format

Ad Intelligence Report

Category/Niche: [name] Apps analyzed: [count]

Ad Platform Breakdown:

MetricMeta CreativesTikTok CreativesApple SignalNo Ads
App count[N][N][N][N]
Avg. revenue[est.][est.][est.][est.]
Avg. downloads[est.][est.][est.][est.]

Top Advertisers:

AppPlatform(s)Revenue/moDownloads/moAd Count
[app]Meta / TikTok / Apple signal[est.][est.][N]

Creative Patterns:

  1. [Common ad formats and styles]
  2. [Messaging themes that appear frequently]
  3. [Unique or standout creative approaches]

Strategic Recommendations:

  1. [Should the user run ads? On which platform?]
  2. [Creative direction suggestions based on gaps]
  3. [Budget considerations based on competitive landscape]

Related Skills

  • competitor-analysis — Full competitive analysis beyond ads
  • growth-analysis — Understand if growth correlates with ad presence
  • revenue-analysis — Revenue benchmarks to justify ad spend

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.