Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SupercmoHQ/superCMO-skills --skill writing-ad-copygit clone --depth 1 https://github.com/SupercmoHQ/superCMO-skillsWrote 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/supercmohq/supercmo-skills/writing-ad-copy)<a href="https://agentmods.dev/skills/supercmohq/supercmo-skills/writing-ad-copy"><img src="https://agentmods.dev/badge/skills/supercmohq/supercmo-skills/writing-ad-copy/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/supercmohq/supercmo-skills/writing-ad-copy"><img src="https://agentmods.dev/badge/skills/supercmohq/supercmo-skills/writing-ad-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00089 | $0.02176 |
| Opus 5 | $0.00044 | $0.01088 |
| Sonnet 5 | $0.00018 | $0.00435 |
| Haiku 4.5 | $0.00009 | $0.00218 |
Grade A, and why
writing-ad-copy 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ad copy
Write the words that ride beside the creative in the ad platform — the headline, the primary text, the description, the call to action. Text only — nothing is generated here. Not the text drawn on the image, and not a spoken voiceover.
Ad copy may run on one channel or several. The same product, written for each channel it runs on — because the fields and the limits differ, and the register does too. Write each channel's set, then hand them all back.
Workflow
Step 1: Read what's fixed
Ask only for what would change the copy and can't be defaulted.
- The product and the offer — what it is, what it does for the buyer, and any promotion (a price, a discount, a launch).
- Who it's for, and how aware they are — a buyer who already knows the category reads differently from one meeting the problem for the first time.
- Which channel(s) the copy runs on — this decides the fields, the limits and the register.
- The grounding — the claims the user will stand behind, and any raw material: reviews, a winning ad, ad comments, the words real customers use. This is what the copy is built from.
Feature claims vs proof claims. What the product is and does — its features, how it works, the offer — the user can simply assert, and you write from that. A proof claim — a number, a rating, a testimonial, a "better than X" result — needs real backing; where there is none the claim doesn't get made, and you ask rather than invent one. Where the proof is only a paraphrase ("reviewers keep saying it's less bitter"), attribute it — reviewers say… — rather than stating it as fact; a supplied review's own words are stronger still.
What to default, and what to ask. Audience and awareness can be defaulted to the broad buyer where unstated. The channel and the grounding cannot: no channel named → ask which; no grounding at all → ask for it and don't write yet. A partial gap — a missing offer, a single thin claim — is different: write the angles the material supports and name the gap.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 117 lines · 89 tokens per session scan A 936697507e49
writing-ad-copy is a skill published in the GitHub repository SupercmoHQ/superCMO-skills (38 stars, last pushed 14d ago), licensed Apache-2.0. It adds 89 tokens to every session and 2,176 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…