dojo.md: Skill for Claude Code

.claude/skills/ad-copy-google-ads/anthropic--claude-sonnet-4-6/SKILL.md

ad-copy-google-ads is a skill for Claude Code from edholofy/dojo.md. It costs 55 tokens per session (3,524 once invoked), scanned A, original, MIT.

A writing aid for Google Search ads, including headlines, descriptions, links, callouts, and keyword-based wording. It also checks the strict character limits used by each ad part.

In plain words
What is it for?
Use it to create or improve Google Search campaigns, organize keyword-based ad groups, write ad extensions, and investigate wording related to Quality Score, Google’s rating of how useful and relevant an ad is.
Why use it?
It removes the guesswork from fitting useful messages into small ad fields. It helps connect each ad to what people are searching for and avoid copy that does not meet Google’s limits.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

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/anthropic--claude-sonnet-4-6/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/anthropic-claude-sonnet-4-6/github.svg)](https://agentmods.dev/skills/edholofy/dojo.md/anthropic-claude-sonnet-4-6)
Your own site
<a href="https://agentmods.dev/skills/edholofy/dojo.md/anthropic-claude-sonnet-4-6"><img src="https://agentmods.dev/badge/skills/edholofy/dojo.md/anthropic-claude-sonnet-4-6/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/anthropic-claude-sonnet-4-6"><img src="https://agentmods.dev/badge/skills/edholofy/dojo.md/anthropic-claude-sonnet-4-6.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,524 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 $0.00055 $0.03524
Opus 5 $0.00028 $0.01762
Sonnet 5 $0.00011 $0.00705
Haiku 4.5 $0.00006 $0.00352

Measured 12d ago against content hash 8134de078128, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, 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 12d 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/anthropic--claude-sonnet-4-6/SKILL.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Domain Knowledge

Character Limits — The Numbers That Matter

  • Headlines: 30 characters. Not 35, not "about 30." Exactly 30. Count every character including spaces, hyphens, em dashes, ampersands.
  • Descriptions: 90 characters. Use at least 72+ (80%) to avoid wasting premium real estate.
  • Sitelink titles: 25 characters. Sitelink descriptions: 35 characters each (two lines).
  • Callouts: 25 characters. Each callout must be a distinct benefit not already in your headline/description.
  • Structured snippet values: 25 characters. Must use Google-approved headers (Amenities, Brands, Courses, Destinations, Featured hotels, Insurance coverage, Models, Neighborhoods, Service catalog, Shows, Styles, Types).

Character Counting Traps

  • Em dashes (—) = 1 character. Hyphens (-) = 1 character. Ampersands (&) = 1 character.
  • "Free" = 4 chars. "100%" = 4 chars. Common miscounts happen on words with double letters.
  • A headline reading "Transform Your Business Today" = 30 chars exactly. "Transform Your Business Today!" = 31 — VIOLATION.
  • LLMs cannot reliably count characters by estimation. You must count letter-by-letter, every time, no exceptions.

Quality Score — The Three Levers

  1. Expected CTR: Driven by headline specificity, strong CTAs, numbers, and emotional triggers. Generic headlines like "Best Service Available" kill CTR.
  2. Ad Relevance: The target keyword's core meaning must appear naturally in at least 1-2 headlines and 1 description. This is about semantic match, not keyword stuffing.
  3. Landing Page Experience: The ad's promise must be fulfilled on the landing page. If your ad says "Free Trial," the landing page must show a free trial — not a pricing page with a buried trial link.

Search Intent — The Four Types and What They Demand

Intent User Mindset Ad Strategy CTA Style
Informational "I want to learn" Educate, offer guides/resources "Learn More," "Get the Guide"
Commercial "I'm comparing options" Differentiate, use social proof "See Why 10K+ Choose Us," "Compare Plans"
Transactional "I'm ready to buy" Sell directly, urgency, price "Buy Now," "Start Free Trial"
Navigational "I want that specific brand" Redirect to correct page, reinforce brand "Visit Official Site," "Log In"

Read the full file on GitHub · 204 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. 12d ago First seen · 204 lines · 55 tokens per session scan A 8134de078128

Subscribe to this mod's changes

ad-copy-google-ads is a skill published in the GitHub repository edholofy/dojo.md (10 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 3,524 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