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-5.2/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/openai-gpt-5.2)<a href="https://agentmods.dev/skills/edholofy/dojo.md/openai-gpt-5.2"><img src="https://agentmods.dev/badge/skills/edholofy/dojo.md/openai-gpt-5.2/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/openai-gpt-5.2"><img src="https://agentmods.dev/badge/skills/edholofy/dojo.md/openai-gpt-5.2.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 | $0.00050 | $0.03623 |
| Opus 5 | $0.00025 | $0.01811 |
| Sonnet 5 | $0.00010 | $0.00725 |
| Haiku 4.5 | $0.00005 | $0.00362 |
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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Knowledge
Character Limits (Memorize These — Violations Are the #1 Failure)
- Headlines: 30 characters (not words). Count every letter, space, and punctuation mark.
- Descriptions: 90 characters. Use 80+ to avoid wasting space; never exceed 90.
- Sitelink text: 25 characters. Sitelink descriptions: 35 characters each (2 lines).
- Callouts: 25 characters. No punctuation needed — they display as a list.
- Structured snippet values: 25 characters per value.
- DKI headline with
{KeyWord:Default}: The default text AND the longest keyword must each fit in 30 characters including the DKI syntax wrapper.
DKI Syntax — The Exact Rules
- Format:
{KeyWord:Default Text}— the curly braces, colon, and capitalization pattern are all meaningful. - Capitalization variants:
{keyword:default}= lowercase,{Keyword:default}= title case first word,{KeyWord:Default}= title case all words,{KEYWORD:DEFAULT}= ALL CAPS. - The entire
{KeyWord:Default Text}token counts as the length of the longest triggering keyword OR the default text, whichever is longer, for character limit purposes. - Critical trap: If your longest keyword is 28 characters, you have only 2 characters left in a 30-char headline. Most people forget to check this.
DKI Risks Most People Miss
- Competitor brand names in keyword lists → your ad says "Buy [Competitor Name]" which violates trademark policy.
- Misspelled keywords (broad match) inserting into headlines → "Cheep Sofware" in your ad.
- Grammatically awkward insertions: "Get {KeyWord:Solutions} Today" + keyword "data analytics consulting services" → broken grammar.
- Sensitive/negative terms: keywords like "mold removal" or "debt relief" can create alarming ad copy in wrong context.
- Always provide 2-3 static (non-DKI) headline alternatives as safety nets.
Quality Score — The Three Levers
- Expected CTR: Driven by headline specificity, emotional triggers, numbers, and strong CTAs. Generic headlines ("Best Service Available") kill CTR.
- Ad Relevance: The target keyword's core concept must appear naturally in at least 1 headline and 1 description. Not keyword stuffing — semantic alignment.
- Landing Page Experience: The ad's promise must be fulfilled on the landing page. If the ad says "Free Trial," the landing page must show a free trial — not a pricing page. Recommend specific landing page content changes, not just "improve your landing page."
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 · 190 lines · 50 tokens per session scan A 6b4f7cf5ac29
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 50 tokens to every session and 3,623 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…