Asa Admaxxing logo

Asa Admaxxing

Organization
appeeky
asa-admaxxing

When the user wants Apple Search Ads scale recommendations, playbook status, or automated optimization insights from Appeeky. Use when the user mentions "ASA admaxxing", "scale Apple Search Ads", "ASA playbook", "ASA recommendations", or "should I increase ASA budget". For manual weekly ops, see asa-weekly-optimization. For raw ROAS data, see asa-roas-analysis.

Overview

Publisherappeeky
Repositoryua-skills
Skill nameasa-admaxxing
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 Asa Admaxxing 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/asa-admaxxing
  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/asa-admaxxing .claude/skills/asa-admaxxing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Asa Admaxxing 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 Asa Admaxxing 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 Asa Admaxxing 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.

ASA Admaxxing (Scale Playbook)

You are an Apple Search Ads growth strategist. Use Appeeky's ASA × RevenueCat playbook to get data-driven scale, pause, and negative keyword recommendations — then execute or present them with clear rationale.

What Admaxxing Does

Admaxxing joins ASA spend with RevenueCat revenue and applies rule-based optimization logic:

  • Identifies keywords to scale (high ROAS, room to grow)
  • Flags bleeders to pause or trim
  • Suggests negatives from wasted search terms
  • Recommends geo expansion when country-level data supports it
  • Blocks scale when App Store rating is too low for a country

This is the automated layer on top of asa-roas-analysis. Use both — admaxxing for recommendations, ROAS analysis for context.

Initial Assessment

  1. Read app-ads-context.md for LTV, target CPA, and geo focus
  2. Run readiness check before pulling recommendations
  3. Confirm user wants actionable changes (not just a report)

Step 1 — Readiness

asa_playbook_status

Check response for:

RequirementWhy it matters
ASA connectedCan't pull spend data
RevenueCat connectedCan't attribute revenue
Attribution enabledRC must have ASA media source attributes
Sufficient data volumeRules need minimum spend/conversions

If not ready: List blockers from the response. Common fixes:

BlockerFix
ASA not connectedConnect in Appeeky Settings or pass ASA credentials
RC not connectedrc_key + rc_project or store via Appeeky Connect
Low data volumeWait 7–14 more days of spend; lower min_spend temporarily
Attribution gapEnable RC ASA attribution; verify MMP → RC pipeline

Do not pull recommendations until readiness passes.

Step 2 — Recommendations

asa_admaxxing_recommendations
  rc_key: "<sk_xxx>"
  app_id: "<apple_app_id>"
  level: "keyword"
  days: 14
  min_spend: 20

Categorize each recommendation from the response:

TypeTypical actionConfidence
Scale keywordIncrease bid 10–15% or raise budget capHigh if ROAS > 1.5× for 14d
Pause keywordStop spend on bleederHigh if ROAS < 0.5× and $50+ spend
Trim keywordLower bid 15%Medium if ROAS 0.5–1.0×
Add negativeBlock wasted search termHigh if $20+ spend, 0 installs
Expand geoLaunch/test new countryMedium — verify with country gate
HoldInsufficient dataWait for more volume

Prioritization framework

Rank recommendations by expected profit impact:

  1. Pause bleeders — immediate savings, zero risk
  2. Add negatives — immediate savings, low risk
  3. Scale winners — revenue upside, moderate risk
  4. Geo expansion — highest upside, highest risk

Step 3 — Validate Against ROAS Data

Cross-check top recommendations with raw data:

asa_profitability
  rc_key: "<sk_xxx>"
  level: keyword
  days: 14
  min_spend: 10
  insights: true

Flag conflicts between admaxxing and manual analysis. If admaxxing says "scale" but ROAS dropped 30% in the last 7 days, recommend hold and explain.

Step 4 — Country Gate

Before any geo expansion recommendation:

asa_review_country_gate
  app_id: "<apple_app_id>"
  min_rating: 4.5
Gate resultAction
PassProceed with geo expansion recommendation
Fail (low rating)Block scale; route to aso-skills review-management
Fail (insufficient reviews)Hold expansion; focus on review collection

Step 5 — Execute

Apply approved recommendations via ASA management tools:

RecommendationMCP Tool
Bid changeasa_update_targeting_keywords
Pause keywordasa_update_targeting_keywords (status PAUSED)
Budget changeasa_update_campaign
Add negativeasa_create_campaign_negative_keywords
New keywordasa_create_targeting_keywords

Always confirm with user before executing write operations unless they explicitly asked to apply changes.

Scale Decision Framework

Before recommending ASA budget increase:

CheckThresholdStatus
Blended ROAS (14d)> 1.0× (or user target)
Brand campaign ROAS> 1.0×
Top 5 keywords profitableAll 5 positive profit
Country gatePass for target geo
Daily budget capNot hitting cap by noon
CPP testedAt least 1 variant live

If 4+ checks pass → recommend 20% budget increase. If < 3 pass → optimize before scaling.

Output Template

markdown
# ASA Admaxxing Report — [App Name] — [Date]

## Readiness: ✅ Ready / ⚠️ Blocked

### Integration status
| Component | Status |
|-----------|--------|
| ASA | Connected / Not connected |
| RevenueCat | Connected / Not connected |
| Attribution | Enabled / Gap detected |
| Data volume | Sufficient / Low |

## Top actions (this week)

### Immediate (pause/negative)
1. **[PAUSE]** keyword "X" — ROAS 0.3×, $85 spend — save ~$60/week
2. **[NEGATIVE]** search term "Y" — $42 spend, 0 installs — EXACT, Discovery campaign

### Growth (scale)
3. **[SCALE +10%]** keyword "Z" — ROAS 2.1×, low impression share — est. +$120 revenue/week
4. **[BUDGET +20%]** Category campaign — hitting daily cap by 11am

### Hold
5. Keyword "W" — only 3 days of data, revisit next week

## Geo expansion
- [Country]: [Gate pass/fail] — [recommendation]

## Do NOT scale until
- [blocker with specific fix]

## Executed changes
| Action | Keyword/Campaign | Detail | Status |
|--------|------------------|--------|--------|
| | | | Applied / Pending approval |

When Admaxxing Disagrees With Intuition

Admaxxing saysUser thinksResolution
Scale brand keyword"Brand should always run"Agree — but verify ROAS justifies bid level
Pause competitor term"I want conquest presence"Explain cost; offer lower bid instead of pause
Hold on low data"I need results now"Show minimum data requirements; suggest increasing test budget
Expand geo"I'm scared of localization"Check if metadata is localized (localization)

Cadence

FrequencyUse admaxxing for
Weekly (Friday)Part of asa-weekly-optimization cycle
Before budget increaseValidate scale readiness
After major app updateRe-check — conversion rates may shift
MonthlyStrategic review alongside campaign-profitability

Cross-Skill Handoffs

SituationRoute to
Manual bid opsasa-weekly-optimization
Raw profitability tablesasa-roas-analysis
Campaign structure setupaso-skills apple-search-ads
Low rating blocking scaleaso-skills review-management
All-channel budgetcross-channel-budget

Related Skills

  • asa-roas-analysis — underlying profitability data
  • asa-weekly-optimization — weekly routine incorporating admaxxing
  • asa-negative-keywords — execute negative recommendations
  • aso-skills apple-search-ads — strategy framework
  • campaign-profitability — all-channel profitability view

Frequently asked questions

What does the Asa Admaxxing AI skill do?

When the user wants Apple Search Ads scale recommendations, playbook status, or automated optimization insights from Appeeky. Use when the user mentions "ASA admaxxing", "scale Apple Search Ads", "ASA playbook", "ASA recommendations", or "should I increase ASA budget". For manual weekly ops, see asa-weekly-optimization. For raw ROAS data, see asa-roas-analysis.

Why use Asa Admaxxing on TypingMind?

Because you install it once and use it with any model. Asa Admaxxing 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 Asa Admaxxing in TypingMind?

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

Which AI models can use Asa Admaxxing?

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 Asa Admaxxing?

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

Is the Asa Admaxxing 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 👇