ad-copy-generation

ad-copy-generation is a skill for Claude Code from itallstartedwithaidea/agent-skills. It costs 33 tokens per session (2,045 once invoked), scanned A, original, MIT.

A tool for writing responsive search ads (RSAs), the text ads shown in search results. It creates multiple headlines and descriptions within Google Ads’ character limits.

In plain words
What is it for?
It helps create headlines, descriptions, keyword-insertion text, pinned ad elements, and A/B test variants for search campaigns. It can also compare competitor messaging and remove weaker variants based on performance.
Why use it?
It reduces the work of drafting many ad variations while following Google Ads editorial rules. The input also describes testing, scoring, and managing variants over time.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code; mentions Codex.

Part of the google-ads-skills plugin — 12 skills shipped together , and of all-skills

Good fit It helps create headlines, descriptions, keyword-insertion text, pinned ad elements, and A/B test variants for search campaigns. It can also compare competitor messaging and remove weaker variants based on performance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/itallstartedwithaidea/agent-skills/ad-copy-generation
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add itallstartedwithaidea/agent-skills --skill ad-copy-generation
Clone the repo
git clone --depth 1 https://github.com/itallstartedwithaidea/agent-skills

Made for: Claude Code.

Or install google-ads-skills, the plugin that ships this one along with the rest of its 12 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ad-copy-generation

README.md
[![agentmods](https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/ad-copy-generation/github.svg)](https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/ad-copy-generation)
Your own site
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/ad-copy-generation"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/ad-copy-generation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ad-copy-generation

Your own site · 80×15
<a href="https://agentmods.dev/skills/itallstartedwithaidea/agent-skills/ad-copy-generation"><img src="https://agentmods.dev/badge/skills/itallstartedwithaidea/agent-skills/ad-copy-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,045 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.02045
Opus 5 $0.00016 $0.01022
Sonnet 5 $0.00007 $0.00409
Haiku 4.5 $0.00003 $0.00204

Measured 9d ago against content hash 9ed478949fa2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ad-copy-generation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/google-ads/ad-copy-generation/SKILL.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ad Copy Generation

Part of Agent Skills™ by googleadsagent.ai™

Description

The Ad Copy Generation skill produces high-performance responsive search ad (RSA) copy using AI-driven generation pipelines calibrated against millions of ad performance data points. It generates headlines (up to 15, max 30 characters each) and descriptions (up to 4, max 90 characters each), optimizing for ad strength, click-through rate, and conversion relevance while adhering to Google Ads editorial policies.

The generation engine applies proven copywriting frameworks including AIDA (Attention, Interest, Desire, Action), PAS (Problem, Agitate, Solve), and benefit-driven messaging. It incorporates dynamic keyword insertion (DKI) syntax where appropriate, manages pin strategies for controlled ad assembly, and generates systematic A/B testing variants. Each ad variant is scored against Google's ad strength criteria before submission.

Beyond generation, the skill manages the full ad copy lifecycle: competitive ad analysis to identify messaging gaps, performance-based variant pruning, statistical significance testing for A/B experiments, and automated winner scaling. It integrates with the Buddy™ platform to learn from historical performance data, continuously improving generation quality for each specific account and industry vertical.

Use When

  • User asks to "write ad copy" or "generate ads"
  • User wants "new headlines" or "new descriptions" for RSAs
  • User mentions "ad strength" improvement
  • User asks for "A/B test variants" or "ad testing"
  • User wants to "improve click-through rate" on ads
  • User mentions "responsive search ads" or "RSA optimization"
  • User asks about "dynamic keyword insertion" or "DKI"
  • User wants "pin strategy" recommendations
  • User asks to "refresh stale ad copy" or "combat ad fatigue"

Architecture

flowchart TD
    A[Input: Keywords, Landing Page, USPs] --> B[Context Analysis]
    B --> C[Landing Page Scraper]
    B --> D[Keyword Intent Classifier]
    B --> E[Competitor Ad Analyzer]

    C --> F[Message Map Builder]
    D --> F
    E --> F

    F --> G[AI Generation Engine]
    G --> H[Headline Generator\nmax 30 chars x 15]
    G --> I[Description Generator\nmax 90 chars x 4]

    H --> J[Policy Compliance Check]
    I --> J

    J --> K[Ad Strength Scorer]
    K -->|Excellent| L[Final Ad Variants]
    K -->|Good| L
    K -->|Average| M[Regenerate with Feedback]
    K -->|Poor| M
    M --> G

    L --> N[Pin Strategy Optimizer]
    N --> O[A/B Test Plan]
    O --> P[Deploy to Google Ads]

Read the full file on GitHub · 212 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 212 lines · 33 tokens per session scan A 9ed478949fa2

Subscribe to this mod's changes

ad-copy-generation is a skill published in the GitHub repository itallstartedwithaidea/agent-skills (37 stars, last pushed 4mo ago), licensed MIT. It adds 33 tokens to every session and 2,045 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.