Google Ads logo

Google Ads

Community
ivangfalco
google-ads

Google Ads management skill with API integration. Covers campaign creation, optimization, keyword management, performance analysis, and search term auditing via Python scripts that connect to the Google Ads API. MANDATORY TRIGGERS: Google Ads, Google campaign, Google search ads, Google PMax, Performance Max, Google Display, Google Shopping, Google ad performance, Google keyword, search terms, Google RSA, Google bidding, Google Ads API

Overview

Publisherivangfalco
Repositoryads-skills
Skill namegoogle-ads
Stars
284
Forks
84
Bundled files
24
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.

  • 24 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Google Ads 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/ivangfalco/ads-skills/tree/main/.claude/skills/google-ads
  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/ivangfalco/ads-skills.git /tmp/ads-skills
mkdir -p .claude/skills
cp -r /tmp/ads-skills/.claude/skills/google-ads .claude/skills/google-ads
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Ads 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 Google Ads 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 Google Ads 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.

Google Ads Management

Orchestrator for all Google Ads tasks. Combines strategic knowledge with programmatic API access for full campaign management.

Methodology

This skill implements the Ivan Falco B2B demand generation methodology for Google Ads - an intent-first approach that captures existing demand through systematic keyword targeting, proving unit economics before expanding outward.

Core Philosophy

Intent is everything. Capture demand before you create it.

Google Ads is the #1 channel for capturing existing demand. People are actively searching for solutions - your job is to be there at the right moment with the right message. Start with high-intent keywords (brand + solution-aware), prove unit economics, then expand outward to medium/low-intent and awareness.

Architecture

This skill has two layers:

  1. Knowledge Base - Strategic frameworks and campaign planning (knowledge-base/)
  2. API Scripts - Programmatic Google Ads management (scripts/)

API Scripts - What You Can Do

All scripts live in scripts/. Run from that directory.

Prerequisites: Credentials configured in scripts/.env. See api-reference.md for setup.

Quick Reference

TaskCommand
Account snapshotpython account_overview.py --date-range last_30d --compare
Campaign performancepython get_campaign_performance.py --date-range last_7d --by-day
List campaignspython list_campaigns.py --status ENABLED
Search terms auditpython search_terms_report.py --no-conversions --min-clicks 3
Keyword performancepython get_keyword_performance.py --top 30
Create campaignpython create_campaign.py --name "Brand - Search" --type SEARCH --budget 50
Update campaignpython update_campaign.py --campaign-id <id> --status ENABLED --budget 75
Create ad grouppython create_ad_group.py --campaign-id <id> --name "High Intent KWs"
Create RSApython create_ad.py --ad-group-id <id> --headlines "H1" "H2" "H3" --descriptions "D1" "D2" --final-url "https://..."
List adspython list_ads.py --campaign-id <id>
Add keywordspython add_keywords.py --ad-group-id <id> --keywords "kw1" "kw2" --match-type PHRASE
Add negative KWspython add_keywords.py --ad-group-id <id> --keywords "free" "cheap" --negative

Workflow: Analyze an Account

  1. Run python account_overview.py --compare - get the big picture
  2. Identify top-spending campaigns, check ROAS
  3. Run python get_campaign_performance.py --campaign-id <id> --by-day - daily trends
  4. Run python search_terms_report.py --no-conversions - find wasted spend
  5. Run python get_keyword_performance.py --campaign-id <id> - keyword-level analysis
  6. Make recommendations: pause underperformers, add negatives, adjust budgets

Workflow: Build a New Campaign

  1. python create_campaign.py --name "..." --type SEARCH --budget 50 --bidding MAXIMIZE_CONVERSIONS
  2. python create_ad_group.py --campaign-id <id> --name "..." --cpc-bid 3.00
  3. python add_keywords.py --ad-group-id <id> --keywords "..." --match-type PHRASE
  4. python create_ad.py --ad-group-id <id> --headlines "..." --descriptions "..." --final-url "..."
  5. python update_campaign.py --campaign-id <id> --status ENABLED

Safety: All new campaigns start PAUSED. Enable only after reviewing setup.

Routing Logic

User IntentRouteWhen to Use
Account analysis, performance reviewRun account_overview.py then drill down"How are my Google Ads doing?"
Search term wasteRun search_terms_report.py --no-conversions"Where am I wasting money?"
Keyword optimizationRun get_keyword_performance.py"Which keywords are working?"
Create new campaignUse the build workflow above"Set up a search campaign for..."
Pause/enable/budget changesRun update_campaign.py"Pause this campaign" / "Increase budget"
Strategic campaign planningLoad the knowledge base files belowNew account, media plan, scaling decision

Knowledge Base

Ground all strategy in these files. Read the relevant one before advising.

FileContainsRead When
intent-first-strategy.mdIntent ladder (brand -> high-intent -> competitor -> problem-aware -> demand-gen), capture-before-create, B2B realitiesAny strategy/planning question, prioritizing spend
account-structure.mdSplitting by intent, themed ad groups (not SKAGs), naming, network/geo defaults, when to consolidateSetting up or restructuring an account
keyword-and-match-types.mdMatch type progression, B2B keyword research, negatives, avoiding self-competitionBuilding keyword lists, choosing match types
bidding-strategy.mdBidding by conversion volume, tCPA/tROAS, setting/moving targets, the optimize-to-quality trapChoosing or changing a bid strategy
search-terms-and-negatives.mdWeekly search terms ritual, what to negative, negative match types, shared listsWeekly optimization, cutting waste
benchmarks-and-measurement.mdB2B SaaS benchmark ranges, metrics that matter, offline conversion import, weekly scorecardPerformance review, expectations, measurement setup
performance-max-b2b.mdWhen/when-not to run PMax, guardrails (brand exclusions, signals, negatives), reading PMaxPMax questions, scaling beyond Search
rsa-and-landing-pages.mdRSA assets, pinning, writing to intent, landing page message match, Quality ScoreWriting ads, improving CVR or Quality Score
cheatsheet-overview.mdCampaign types cheatsheet (Search, Shopping, Display, PMax, Video)Quick campaign-type selection

Core Rules

  1. Always start PAUSED. Never create campaigns in ENABLED state. Review everything before turning on spend.

  2. Check search terms weekly. The search terms report is the #1 optimization lever. Find irrelevant terms, add negatives, discover new keyword opportunities.

  3. Build bottom-up by intent. Start with brand + high-intent keywords. Prove they convert. Then expand to medium-intent, then low-intent/awareness.

  4. Match type strategy matters. Start with Phrase match for control, expand to Broad match only with Smart Bidding and sufficient conversion data (30+ conversions/month).

  5. Quality Score drives costs. Monitor QS on keywords - low QS means ad relevance or landing page issues. Fix those before increasing bids.

  6. RSA best practices. 8-10 unique headlines, 3-4 descriptions. Pin critical brand/CTA to position 1. Let Google optimize the rest.

  7. Speak from this methodology directly and with conviction - it's built from managing real B2B spend. Don't pad with generic "best practices."

Campaign Types - When to Use What

TypeUse CaseWhen
SearchHigh-intent keyword captureAlways - this is your foundation
Performance MaxBroad AI-driven across all networksAfter Search proves unit economics
DisplayRemarketing and awarenessRemarketing first, prospecting second
ShoppingE-commerce product adsProduct catalog campaigns
Video (YouTube)Brand awareness and remarketingAfter core campaigns are profitable

Key Metrics to Watch

MetricWhat It Tells You
Search Impression ShareHow much demand you're capturing
Quality ScoreAd + landing page relevance
Cost per ConversionUnit economics
ROASRevenue efficiency
Search Terms (no conv)Budget waste
Top Impression %Ad position competitiveness

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Google Ads AI skill do?

Google Ads management skill with API integration. Covers campaign creation, optimization, keyword management, performance analysis, and search term auditing via Python scripts that connect to the Google Ads API. MANDATORY TRIGGERS: Google Ads, Google campaign, Google search ads, Google PMax, Performance Max, Google Display, Google Shopping, Google ad performance, Google keyword, search terms, Google RSA, Google bidding, Google Ads API

Why use Google Ads on TypingMind?

Because you install it once and use it with any model. Google Ads 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 Google Ads in TypingMind?

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

Which AI models can use Google Ads?

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 Google Ads?

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

Is the Google Ads AI skill free?

It is published on GitHub by ivangfalco. 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 👇