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/deepseek--deepseek-v3.2/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/deepseek-deepseek-v3.2)<a href="https://agentmods.dev/skills/edholofy/dojo.md/deepseek-deepseek-v3.2"><img src="https://agentmods.dev/badge/skills/edholofy/dojo.md/deepseek-deepseek-v3.2/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/deepseek-deepseek-v3.2"><img src="https://agentmods.dev/badge/skills/edholofy/dojo.md/deepseek-deepseek-v3.2.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 | $0.00051 | $0.03588 |
| Opus 5 | $0.00026 | $0.01794 |
| Sonnet 5 | $0.00010 | $0.00718 |
| Haiku 4.5 | $0.00005 | $0.00359 |
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.
How it starts
The opening of the file, as written. The whole thing — 182 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
- RSA Headlines: 30 characters (not words, not pixels — characters including spaces)
- RSA Descriptions: 90 characters (aim for 75-90; under 60 wastes opportunity)
- Sitelink titles: 25 characters
- Sitelink descriptions: 35 characters per line
- Callout extensions: 25 characters each
- Structured snippet values: 25 characters each
Count every character before outputting. The #1 recurring failure is exceeding limits by 1-5 characters. "Get Started With Your Free Trial Today" = 39 chars, busted headline. Always count, always verify, always show the count.
DKI Syntax — Exact Format
{KeyWord:Default Text}
KeyWord= Title Case insertion.Keyword= Sentence case.keyword= lowercase.KEYWORD= ALL CAPS.- The default text +
{KeyWord:}wrapper does NOT count toward the limit — only the longest possible inserted keyword does. - Critical: if your longest keyword is "affordable project management software" (41 chars), it blows a 30-char headline. You MUST check the longest keyword in the ad group against the 30-char ceiling.
- Always provide static fallback headlines alongside DKI headlines. DKI is never the only strategy.
DKI Risks Most People Miss
- Competitor names inserting into your ads (policy violation)
- Misspelled search queries appearing as headlines
- Negative/awkward terms: "cheap divorce lawyer" as a headline feels wrong
- Grammatical breakage: "Best {KeyWord:Shoes} Near You" + keyword "running shoe" = "Best running shoe Near You"
- Rule: if any keyword in the ad group would read awkwardly, don't use DKI for that group
Quality Score — The Three Levers
- Expected CTR: Driven by headline specificity, numbers, CTAs, and emotional triggers. Fix: make headlines irresistibly clickable for the exact query.
- Ad Relevance: The ad must echo the keyword's language and intent. Fix: mirror the keyword naturally in headline 1, reinforce in description 1.
- Landing Page Experience: The ad's promise must be fulfilled on the page. Fix: ensure the landing page headline matches the ad's primary claim; page load speed matters too.
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.
- 12d ago First seen · 182 lines · 51 tokens per session scan A 58a5f38e671c
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 51 tokens to every session and 3,588 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…