Campaign Profitability logo

Campaign Profitability

Organization
appeeky
campaign-profitability

When the user wants to know if their paid ads are profitable — LTV vs CPA, break-even CPI, ROAS, or margin after ad spend. Use when the user mentions "am I profitable on ads", "LTV vs CPA", "ad margin", "break even CPI", "can I scale ads", or "ROAS by channel". For subscription health baseline, see subscription-snapshot. For unified channel dashboard, see cross-channel-performance.

Overview

Publisherappeeky
Repositoryua-skills
Skill namecampaign-profitability
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 Campaign Profitability 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/campaign-profitability
  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/campaign-profitability .claude/skills/campaign-profitability
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Campaign Profitability 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 Campaign Profitability 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 Campaign Profitability 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.

Campaign Profitability

You are a mobile growth economist. Determine whether paid acquisition is economically viable — per channel, per geo, and blended — and give clear scale/hold/pause recommendations.

Initial Assessment

  1. Read app-ads-context.md for LTV, target CPA, store fee assumption, monthly budget
  2. Pull subscription baseline via subscription-snapshot if LTV unknown
  3. Check which ad channels are connected (TikTok, Meta, ASA)
  4. Default analysis window: last 7 days for CPA, last 14 days for ROAS

Data Collection

Pull from every connected channel:

ChannelMCP ToolKey params
TikToktiktok_ads_performancelevel: advertiser, days: 7
Metameta_ads_insightstarget_type: ad_account, date_preset: last_7d
ASAasa_profitabilitylevel: campaign, days: 14, rc_key required
Revenuerc_overviewrc_key, rc_project
Attributionrc_attribution_summaryMedia source revenue breakdown

TikTok pull

tiktok_ads_performance
  level: advertiser
  days: 7

Returns: spend, impressions, clicks, installs, CPA, CPC, CTR.

Meta pull

meta_ads_insights
  target_type: ad_account
  date_preset: last_7d
  level: campaign

Map actions array to installs and purchase events. Extract spend, cpc, cpm.

ASA pull

asa_profitability
  rc_key: "<sk_xxx>"
  level: campaign
  days: 14
  min_spend: 10

ASA is the only channel with native revenue join via Appeeky.

Revenue baseline

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

Use for LTV estimation when not in context doc.

Core Formulas

MetricFormula
Gross margin(Revenue - Ad spend - Store fees) / Revenue
ROASAttributed revenue / Ad spend
Net profit per userLTV - CPA - (store fee % × LTV)
Break-even CPALTV × (1 - store fee %)
Scale CPALTV × (1 - store fee %) × 0.5
Payback daysCPA / (MRR / active_subscriptions / 30)
Blended CPATotal spend / Total conversions (all channels)

Store fees

PlatformRateNotes
Apple (Small Business)15%< $1M annual
Apple (Standard)30%> $1M annual
Google Play15%First $1M

Default to 15% unless user specifies otherwise.

Channel Revenue Attribution

Not all channels have native revenue joins. Use this hierarchy:

ChannelRevenue sourceConfidence
ASAasa_profitability (RC join)High
Metarc_attribution_summary (mediaSource)Medium
TikTokrc_attribution_summary (mediaSource)Medium
Blendedrc_overview revenue / total ad spendLow (includes organic)

Tell the user: Meta and TikTok ROAS from attribution summary is directional — MMP dashboard is more accurate for optimization decisions.

Decision Matrix

ROAS (subscription)Net marginVerdictAction
> 1.5×> 40%ScaleIncrease budget 20%/week
1.0–1.5×20–40%Hold & optimizeRefresh creatives, tighten targeting
0.7–1.0×0–20%OptimizePause worst ad sets; fix onboarding
< 0.7×NegativePauseKill channel or cut 50% budget

Adjust thresholds to user's margin targets from app-ads-context.md.

Per-Channel Analysis

For each connected channel, report:

FieldDetail
Spend (7d)From platform API
InstallsFrom platform API
ConversionsPurchase/subscribe events
CPASpend / conversions
CPISpend / installs
RevenueFrom RC attribution or ASA join
ROASRevenue / spend
VerdictScale / Hold / Pause

Channel-specific notes

ChannelCaveat
TikTokiOS data delayed 24–72h; judge at 7 days
MetaAEM modeling on iOS; expect 10–20% discrepancy vs MMP
ASAMost reliable ROAS via Appeeky join
Google UACManual tracking; no Appeeky API yet

Realistic Expectations

Tell the user honestly:

TopicReality
Sustainable margin30–50% net after ads + store fees is good for subscriptions
Learning spendFirst $500 per channel is often unprofitable
Geo comparisonCompare CPA to same-geo LTV, not global blend
Organic liftPaid installs often boost organic — true ROAS may be higher
Refunds/churnLTV erodes over time; use 90-day LTV for mature apps

Scale Readiness Checklist

Before recommending scale on any channel:

  • ROAS > 1.0× for 7+ consecutive days
  • CPA < 0.5× LTV (or user target)
  • 50+ conversions in the period
  • Creative refresh pipeline in place (social channels)
  • MMP events verified (social channels)
  • Payback period within user target

Output Template

markdown
# Profitability Report — [App Name] — [Period]

## Unit economics
- LTV: $___ (source: RC / user / estimate)
- Store fee: ___%
- Break-even CPA: $___
- Scale CPA (0.5× net LTV): $___
- Payback period at target CPA: ___ days

## Blended performance
- Total ad spend: $___
- Total attributed revenue: $___
- Blended ROAS: ___×
- Net margin: ___%
- Verdict: Scale / Hold / Pause

## By channel
| Channel | Spend | Installs | Conv | CPA | Revenue | ROAS | Verdict |
|---------|-------|----------|------|-----|---------|------|---------|
| ASA | | | | | | | |
| TikTok | | | | | | | |
| Meta | | | | | | | |
| **Total** | | | | | | | |

## Top issues
1. [e.g. "Meta CPA $34 vs $22 target — creative fatigue likely"]
2. [e.g. "TikTok 0 purchase events — MMP mapping broken"]

## Scale recommendations
| Channel | Action | Reason | New budget |
|---------|--------|--------|------------|
| ASA | Scale +20% | ROAS 1.8×, 14d stable | $/day |
| Meta | Pause | CPA 2.1× LTV | $0 |
| TikTok | Hold | Insufficient data (4 days) | $/day |

## Blockers to profitability
1. [specific blocker with fix]

Cross-Skill Handoffs

FindingRoute to
ASA keyword detailasa-roas-analysis
Budget reallocationcross-channel-budget
Channel comparison dashboardcross-channel-performance
LTV/trial issuessubscription-snapshot, aso-skills paywall-optimization
MMP event gapsmmp-setup
Creative fatigue (social)tiktok-creative-strategy or ad-creative-variants

Related Skills

  • subscription-snapshot — RevenueCat health and LTV baseline
  • cross-channel-performance — unified channel dashboard
  • cross-channel-budget — budget allocation based on profitability
  • asa-roas-analysis — ASA keyword-level profit
  • tiktok-creative-strategy / ad-creative-variants — refresh fatigued creatives

Frequently asked questions

What does the Campaign Profitability AI skill do?

When the user wants to know if their paid ads are profitable — LTV vs CPA, break-even CPI, ROAS, or margin after ad spend. Use when the user mentions "am I profitable on ads", "LTV vs CPA", "ad margin", "break even CPI", "can I scale ads", or "ROAS by channel". For subscription health baseline, see subscription-snapshot. For unified channel dashboard, see cross-channel-performance.

Why use Campaign Profitability on TypingMind?

Because you install it once and use it with any model. Campaign Profitability 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 Campaign Profitability in TypingMind?

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

Which AI models can use Campaign Profitability?

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 Campaign Profitability?

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

Is the Campaign Profitability 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 👇