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.
curl -O https://raw.githubusercontent.com/edholofy/dojo.md/main/.claude/skills/ad-copy-google-ads/openai--gpt-4o/SKILL.mdgit clone --depth 1 https://github.com/edholofy/dojo.mdWrote 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.
[](https://agentmods.dev/skills/edholofy/dojo.md/openai-gpt-4o)<a href="https://agentmods.dev/skills/edholofy/dojo.md/openai-gpt-4o"><img src="https://agentmods.dev/badge/skills/edholofy/dojo.md/openai-gpt-4o/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.
<a href="https://agentmods.dev/skills/edholofy/dojo.md/openai-gpt-4o"><img src="https://agentmods.dev/badge/skills/edholofy/dojo.md/openai-gpt-4o.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.02170 |
| Opus 5 | $0.00034 | $0.01085 |
| Sonnet 5 | $0.00014 | $0.00434 |
| Haiku 4.5 | $0.00007 | $0.00217 |
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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ad-copy-google-ads
1. Quick Start
Most common task: Write a complete RSA with extensions.
Input: "Write search ads for a plumbing company targeting emergency plumbing services, $150 avg ticket."
Correct output pattern:
Headlines (30 chars max each — count every character including spaces):
- Emergency Plumber 24/7 (22) ✓
- Licensed & Insured Plumbers (28) ✓
- Same-Day Plumbing Service (25) ✓
- {KeyWord:Plumbing Service} (24 default) ✓
- Call Now — We're On Our Way (27) ✓
Descriptions (90 chars max each):
- Burst pipe? We arrive in 60 min. Licensed plumbers serving your area. Call now. (80) ✓
- Flat-rate pricing. No surprises. $150 avg repair. Book online or call 24/7. (76) ✓
Pinning recommendation: Pin headline 1 (emergency/availability) to Position 1. Do NOT pin all — Google needs flexibility to optimize.
Callout extensions (25 chars max each):
- 24/7 Emergency Service (22) ✓
- Licensed & Insured (18) ✓
- Same-Day Availability (21) ✓
- Upfront Flat Pricing (20) ✓
What agents get wrong: Skipping character counts, over-pinning headlines, writing generic callouts that duplicate headline text.
2. Core Rules
HIGH freedom rules (these cover all failure patterns):
Character limits are non-negotiable — always verify counts:
- Headline: 30 chars max (count it: "Save Money Today!" = 17 ✓, "Get The Best Deals Online Now!" = 30 ✓)
- Description: 90 chars max
- Callout extension: 25 chars max
- Sitelink headline: 25 chars max
- Sitelink description lines: 35 chars max each
Prefer specific data over vague claims when comparative analysis is needed:
- DON'T: "Better than competitors" (unverifiable, low CTR)
- DO: "Rated 4.9★ — 2,000+ Reviews" (specific, credible, 28 chars ✓)
Prefer real urgency triggers over filler urgency when writing CTAs:
- Real urgency: deadline ("Sale Ends Sunday"), scarcity ("3 Spots Left"), consequence ("Before Prices Rise")
- Fake urgency: "Act Now!", "Don't Wait!", "Limited Time!" — these underperform and Google may limit impression share
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.
- 11d ago First seen · 202 lines · 68 tokens per session scan A 5e2f62fd8bb0
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 68 tokens to every session and 2,170 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.
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.
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.
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.
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…
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.
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…