dojo.md: Skill for Claude Code

.claude/skills/ad-copy-google-ads/google--gemini-3-flash-preview/SKILL.md

ad-copy-google-ads is a skill for Claude Code from edholofy/dojo.md. It costs 51 tokens per session (3,487 once invoked), scanned A, original, MIT.

A writing guide for Google Search ads, including headlines, descriptions, links, calls to action, and keyword insertion. It also explains how ad wording relates to Google’s Quality Score, which compares expected clicks, relevance, and landing-page experience with competing ads.

In plain words
What is it for?
Use it to create, audit, or improve search campaigns from keyword research through final ad copy and extensions.
Why use it?
It helps prevent rejected or truncated ads and addresses the problem of generic wording that does not match what people searched for.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is edholofy/dojo.md's own configuration. It tells Claude Code how to work on dojo.md itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything dojo.md configures →

Reuse

Borrowing it

Nothing to install: this file belongs to edholofy/dojo.md. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/edholofy/dojo.md/main/.claude/skills/ad-copy-google-ads/google--gemini-3-flash-preview/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/edholofy/dojo.md

Made for: Claude Code.

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-google-ads

README.md
[![agentmods](https://agentmods.dev/badge/skills/edholofy/dojo.md/google-gemini-3-flash-preview/github.svg)](https://agentmods.dev/skills/edholofy/dojo.md/google-gemini-3-flash-preview)
Your own site
<a href="https://agentmods.dev/skills/edholofy/dojo.md/google-gemini-3-flash-preview"><img src="https://agentmods.dev/badge/skills/edholofy/dojo.md/google-gemini-3-flash-preview/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-google-ads

Your own site · 80×15
<a href="https://agentmods.dev/skills/edholofy/dojo.md/google-gemini-3-flash-preview"><img src="https://agentmods.dev/badge/skills/edholofy/dojo.md/google-gemini-3-flash-preview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,487 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 $0.00051 $0.03487
Opus 5 $0.00026 $0.01743
Sonnet 5 $0.00010 $0.00697
Haiku 4.5 $0.00005 $0.00349

Measured 10d ago against content hash b26d69287a59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ad-copy-google-ads 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 10d 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.

.claude/skills/ad-copy-google-ads/google--gemini-3-flash-preview/SKILL.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domain Knowledge

Character Limits — The Non-Negotiable Numbers

  • Headlines: 30 characters (aim for 25-30; under 20 wastes space)
  • Descriptions: 90 characters (aim for 75-90; under 60 is underutilized)
  • Sitelink text: 25 characters
  • Sitelink descriptions: 35 characters each (2 lines)
  • Callouts: 25 characters
  • Structured snippet values: 25 characters
  • DKI default text + syntax overhead: the longest keyword in the ad group + {KeyWord:} wrapper must fit within the 30-char headline limit. Count the literal longest keyword, not the default.

Quality Score — The Three Levers

Quality Score = Expected CTR + Ad Relevance + Landing Page Experience. Each is rated Above Average / Average / Below Average. The critical insight: these are relative to other advertisers bidding on the same keyword, not absolute metrics.

  • Expected CTR: Driven by headline specificity, numbers, and strong CTAs. Generic headlines ("Best Service Available") kill CTR.
  • Ad Relevance: The target keyword's core intent must appear semantically in the ad copy — not just keyword-stuffed, but meaningfully addressed. If the keyword is "emergency plumber near me," the ad must signal immediacy and locality, not just contain those words.
  • Landing Page Experience: The ad's promise must be fulfilled on the landing page. If the ad says "Free Quote in 60 Seconds," the landing page must have a visible, fast quote form — not a generic homepage.

DKI — The Traps Nobody Warns About

{KeyWord:Default Text} capitalization variants: {keyword:} = lowercase, {Keyword:} = title case first word, {KeyWord:} = title case all words, {KEYWORD:} = ALL CAPS. The default text must itself be compelling ad copy, not placeholder garbage like "Our Product." Always calculate: longest keyword in the ad group + any static text in that headline ≤ 30 chars. Risky keywords for DKI: competitor brand names (trademark violations), misspellings, long-tail queries that read awkwardly as headlines, anything with "cheap" or "free" that could misrepresent the offer.

Read the full file on GitHub · 161 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. 10d ago First seen · 161 lines · 51 tokens per session scan A b26d69287a59

Subscribe to this mod's changes

ad-copy-google-ads is a skill published in the GitHub repository edholofy/dojo.md (9 stars, last pushed 4mo ago), licensed MIT. It adds 51 tokens to every session and 3,487 once invoked, about $0.0003 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 2026-08-31.

Related

Other skills, from other repositories

hugging-face-evaluation

Add and manage evaluation results in Hugging Face model cards. Supports extracting eval tables from README content, importing scores from Artificial Analysis API, and running custom model evaluations with vLLM/lighteval. Works with the model-index metadata format.

synthetic-sciences/openscience · 55 tokens

llm-evaluator

Evaluate LLM outputs systematically using LLM-as-judge, human evaluation frameworks, and regression testing. Use when assessing model quality, comparing models, or preventing quality regression.

chandrudp29/skillhub · 39 tokens

rag-evaluator

Evaluate RAG pipeline quality across faithfulness, relevance, and hallucination metrics. Use when user asks to test, benchmark, or improve a RAG system, or when RAG outputs look wrong.

chandrudp29/skillhub · 44 tokens

mcplab-assistant

Operator guide for MCPLab config authoring, Test Case Assistant workflows, execution, and result analysis. Use when users need to create or refine test cases from runs/traces, suggest deterministic checks or value capture, write or debug MCPLab eval YAML, run or queue evaluations, troubleshoot failures, or compare…

inspectr-hq/mcplab · 71 tokens

ai-engineering-toolkit

6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.

sickn33/agentic-awesome-skills · 47 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens