← Back to Skills Marketplace
kostja94

app-ads

by Kostja Zhang · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ Security Clean
189
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install app-ads-paid-ads
Description
When the user wants to run app install ads, user acquisition (UA), or promote mobile apps. Also use when the user mentions "app ads," "app install ads," "UA,...
README (SKILL.md)

Paid Ads: App Ads

Guides app advertising: app install campaigns, user acquisition (UA), and in-app promotion. Use when promoting mobile apps (iOS, Android); conversion = install or in-app action, not landing page.

When invoking: On first use, if helpful, open with 1–2 sentences on what this skill covers and why it matters, then provide the main output. On subsequent use or when the user asks to skip, go directly to the main output.

Key Platforms

Platform Best for Conversion
Google App Campaigns Android + iOS; automated across Search, YouTube, Display, Play, Discover Install, in-app event
Apple Search Ads (ASA) iOS only; high-intent App Store search Install
Meta App Install Facebook/Instagram; demand gen for apps Install, in-app event
TikTok App Install Younger users; viral creative Install

Google App Campaigns

  • Reach: Search, YouTube, Display, Google Play, Discover
  • Bidding: Maximize Conversions (automated) or Target CPI/CPA (30+ conversions/week)
  • Creative: Provide diverse assets (videos, images, text); algorithm tests combinations
  • iOS: SKAdNetwork; conversion value mapping; Firebase for in-app events
  • Bid–budget ratio: ≥10× for CPI, ≥15× for CPA

Apple Search Ads

  • Placements: App Store search results, Today tab, Search tab, product pages
  • Modes: Basic (automated) or Advanced (keywords, audiences, bids)
  • Audience: High-intent users actively searching in App Store
  • ASO benefit: Can improve keyword rankings as secondary effect

Metrics

Metric Use
CPI Cost per install
CPA Cost per acquisition (in-app action)
LTV Lifetime value; iOS often higher than Android
Retention D1, D7, D30; quality signal

iOS vs Android: iOS typically higher LTV, higher CPI; Android greater scale, lower CPI.

Tracking

  • Firebase: In-app events, audiences, value-based optimization (Google)
  • SKAdNetwork: iOS attribution; configure conversion value mapping
  • UTM: Use utm_medium=app or cpc with utm_source for app campaigns in GA4

Pre-Launch Checklist

  • App Store / Play Store listing optimized (ASO)
  • Firebase or equivalent connected; in-app events defined
  • Creative assets (video, images, text) prepared
  • Conversion events (install, signup, purchase) configured
  • Bid–budget ratio meets minimum (10× CPI, 15× CPA)

Related Skills

  • paid-ads-strategy: Ad formats by medium; when to use app vs web
  • analytics-tracking: In-app events; conversion setup
  • traffic-analysis: UTM for app campaigns; attribution
Usage Guidance
This skill is a text-only guide for running app install ads and appears internally consistent. Before installing, consider: (1) you will need to supply any real ad-account credentials or SDK setup yourself — the skill does not request them; (2) verify any campaign or tracking recommendations against official platform docs (Google, Apple, Meta) and your legal/privacy requirements; and (3) review outputs for correctness before applying changes to live ad accounts. No sensitive system access is requested by the skill itself.
Capability Analysis
Type: OpenClaw Skill Name: app-ads-paid-ads Version: 1.0.1 The skill bundle contains purely informational content and behavioral instructions for an AI agent regarding mobile app advertising (UA, CPI, CPA). There is no executable code, no network activity, and no evidence of malicious prompt injection or data exfiltration in SKILL.md or _meta.json.
Capability Assessment
Purpose & Capability
Name, description, and SKILL.md all describe app-install ad guidance (Google App Campaigns, ASA, Meta, etc.). The skill requests no binaries, credentials, or config paths, which is proportionate for an advice/guide skill.
Instruction Scope
SKILL.md contains only guidance on campaign strategy, tracking, metrics, and a pre-launch checklist. It does not instruct the agent to read files, access environment variables, or call external endpoints beyond describing common platforms and tools.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes on-disk execution and installation risk.
Credentials
The skill declares no environment variables, credentials, or config paths. That is appropriate for a purely advisory skill that references third-party ad platforms but does not integrate with them directly.
Persistence & Privilege
always is false and default autonomous invocation is allowed (normal). The skill does not request persistent system presence or modify other skills or system settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install app-ads-paid-ads
  3. After installation, invoke the skill by name or use /app-ads-paid-ads
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Batch: disclosure through tiktok-ads
v1.0.0
Automated batch sync
Metadata
Slug app-ads-paid-ads
Version 1.0.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 2
Frequently Asked Questions

What is app-ads?

When the user wants to run app install ads, user acquisition (UA), or promote mobile apps. Also use when the user mentions "app ads," "app install ads," "UA,... It is an AI Agent Skill for Claude Code / OpenClaw, with 189 downloads so far.

How do I install app-ads?

Run "/install app-ads-paid-ads" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is app-ads free?

Yes, app-ads is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does app-ads support?

app-ads is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created app-ads?

It is built and maintained by Kostja Zhang (@kostja94); the current version is v1.0.1.

💬 Comments