App Ads Context logo

App Ads Context

Organization
appeeky
app-ads-context

When the user wants to create or update their paid growth context document with app info, ad accounts, budgets, CPI/CPA targets, LTV, and connected channels. Use when starting any paid ads project or when the user mentions "ads context", "growth brief", "my ad budget", or "target CPA". All other paid growth skills check for this file first. For organic ASO context, see app-marketing-context.

Overview

Publisherappeeky
Repositoryua-skills
Skill nameapp-ads-context
Stars
73
Forks
5
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by appeeky on GitHub. Read the source before you install it.

Installation

Install the App Ads Context AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/appeeky/ua-skills/tree/main/skills/app-ads-context
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/appeeky/ua-skills.git /tmp/ua-skills
mkdir -p .claude/skills
cp -r /tmp/ua-skills/skills/app-ads-context .claude/skills/app-ads-context
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable App Ads Context in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads App Ads Context on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so App Ads Context is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

App Ads Context

You are a mobile app growth strategist. Create app-ads-context.md that all paid growth skills reference before pulling data or recommending spend.

Initial Assessment

  1. Check for app-marketing-context.md (aso-skills) — merge relevant sections if it exists
  2. Check for app-ads-context.md — update or create
  3. If Appeeky MCP available, probe connection status before asking the user to re-enter credentials

If context exists: Read it, confirm what's still accurate, update stale sections.

If context doesn't exist: Walk through each section below. Don't skip unit economics — every paid skill depends on CPA/LTV targets.

Document Structure

1. App Identity

markdown
## App
- **Name:**
- **Apple App ID:**
- **Google Play package:**
- **Category:**
- **Store URL:**
- **Price model:** Free / Freemium / Subscription / One-time
- **Primary conversion event:** Purchase / Subscribe / Trial start / Install (install-only only if ad-supported)
- **Platform priority:** iOS-first / Android-first / Both equal

Pull from app-marketing-context.md when available. Use Appeeky get_app to fill gaps (title, category, rating).

2. Unit Economics

Ask for or estimate. If Appeeky MCP available, pull rc_overview for MRR, active subscriptions, and trials.

markdown
## Economics
- **LTV (blended):** $___  (or "unknown — estimate from RC")
- **LTV by geo:** US $___ / EU $___ / ROW $___
- **Target CPA:** $___  (rule: CPA < 0.5× LTV to scale aggressively)
- **Target CPI:** $___  (install-only / ad-supported campaigns — not the scale target for subs apps)
- **Payback period target:** ___ days
- **Current MRR:** $___ (optional)
- **Store fee assumption:** 15% / 30%

LTV estimation when unknown:

MethodFormulaWhen to use
RC snapshotrevenue_28d / new_customersSubscription app with RC
Trial modeltrial_rate × paid_conversion × ARPU × avg_lifetime_monthsTrial-based apps
Conservative defaultAsk user for ARPU × expected retention monthsEarly stage

3. Budget & Channels

markdown
## Paid Growth
- **Monthly ad budget:** $___
- **Test budget (new channel):** $30–50/day ASA, $50/day social — run **7 days** (first kill window is 48h, not 2 days)
- **Active channels:** TikTok / Meta / ASA / Google UAC / none yet
- **Primary scale channel:** ___
- **Geo focus:** US / EU / global
- **MMP:** AppsFlyer / Adjust / Singular / none
- **MMP verified:** Yes / No / In progress

If no MMP verified, flag as blocker and route to mmp-setup before social spend.

4. Connected Accounts

markdown
## Integrations
| Platform | Connected | Account ID | Notes |
|----------|-----------|------------|-------|
| TikTok Ads | Yes/No | | Advertiser ID |
| Meta Ads | Yes/No | | Default ad account (act_xxx) |
| Apple Search Ads | Yes/No | | Org ID |
| RevenueCat | Yes/No | | Project ID |
| MMP | Yes/No | AppsFlyer/Adjust/Singular | |
| Google Ads | Yes/No | | UAC only |

Appeeky MCP credential checks:

PlatformMCP Tool
TikToktiktok_ads_credentials_status
Metameta_ads_credentials_status
ASAasa_credentials_status
RevenueCatrc_overview (requires rc_key + rc_project)

Record connection status in the document so skills don't re-ask.

5. Creative Assets

markdown
## Creatives
- **Winning formats:** (e.g. before/after, story transformation, UGC testimonial)
- **Creative refresh cadence:** every 3–7 days
- **Production method:** UGC / AI / in-house / agency
- **Spark Ads accounts:** list TikTok handles used for organic posts
- **Asset library size:** ___ videos, ___ images

6. Campaign History (if any)

markdown
## Historical Performance
| Channel | Best CPA | Best ROAS | Status | Last tested |
|---------|----------|-----------|--------|-------------|
| ASA | | | Active/Paused | |
| TikTok | | | | |
| Meta | | | | |

Pull from cross-channel-performance or Appeeky if channels are connected. Empty is fine for new apps.

7. Goals & Kill Criteria

markdown
## Goals (90 days)
- **Primary:** e.g. profitable installs at $18 CPA in US
- **Secondary:** e.g. build 20-ad creative library
- **Kill criteria:** spend > 2× target CPA with 0 conversions = pause channel
- **Scale criteria:** ROAS > 1.5× for 7 consecutive days = increase budget 20%

Questions to Ask (New to Paid Ads)

Set expectations honestly:

TopicWhat to tell the user
Learning spendFirst $300–500 per channel is testing — expect negative ROI
Sustainable margin30–50% net margin after store fees + ad spend is good for subscriptions
MMP requirementMMP must be live before scaling TikTok/Meta app install campaigns
ASA advantageiOS apps with search intent should start ASA before social
Creative fatigueSocial ads fatigue in 2–3 weeks — plan refresh cadence

Appeeky Data Bootstrap

When MCP is available and user has connected accounts, pre-fill economics:

rc_overview
  rc_key: "<sk_xxx>"
  rc_project: "<proj_xxx>"
  currency: USD

Use returned mrr, active_subscriptions, active_trials, revenue, new_customers to populate Economics section. Flag if active_trials >> active_subscriptions (conversion health issue).

Context Maintenance Rules

TriggerAction
New channel launchedAdd to Integrations + Historical Performance
CPA target changedUpdate Economics + Goals
Budget increasedUpdate Paid Growth section
MMP verifiedSet MMP verified = Yes
90 days elapsedRefresh Goals section with user

Output

  1. Save app-ads-context.md to project root or .cursor/
  2. Summarize what's filled vs. what still needs user input
  3. List blockers (no MMP, no RC, no ad accounts)
  4. Recommend first skill to run based on state
markdown
# App Ads Context — [App Name]

## Status
- Context file: created / updated
- Blockers: [list or "none"]
- Data sources used: [Appeeky MCP / user input / app-marketing-context]

## Recommended next steps
1. [skill-name] — [reason]
2. [skill-name] — [reason]

Cross-Skill Handoffs

User stateRoute to
No MMP, planning TikTok/Metammp-setup
MMP ready, no campaignscross-channel-budget
ASA connected, wants ROASasa-roas-analysis
Needs LTV baselinesubscription-snapshot
Organic positioning unclearapp-marketing-context

Related Skills

  • app-marketing-context — organic positioning (complementary, not duplicate)
  • mmp-setup — before any paid social spend
  • subscription-snapshot — RevenueCat health for LTV targets
  • cross-channel-budget — allocate monthly budget
  • cross-channel-performance — fill Historical Performance section

Frequently asked questions

What does the App Ads Context AI skill do?

When the user wants to create or update their paid growth context document with app info, ad accounts, budgets, CPI/CPA targets, LTV, and connected channels. Use when starting any paid ads project or when the user mentions "ads context", "growth brief", "my ad budget", or "target CPA". All other paid growth skills check for this file first. For organic ASO context, see app-marketing-context.

Why use App Ads Context on TypingMind?

Because you install it once and use it with any model. App Ads Context is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install App Ads Context in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/appeeky/ua-skills/tree/main/skills/app-ads-context. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use App Ads Context?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with App Ads Context?

As many as you like. As long as a model supports skills, you can use App Ads Context with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the App Ads Context AI skill free?

It is published on GitHub by appeeky. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇