ad-copy

ad-copy is a skill for Claude Code from Gekkos-tech/agency-os. It costs 162 tokens per session (1,964 once invoked), scanned A, original, MIT.

A writing tool for finished advertising and landing-page text in German, English, or both. It covers headlines, calls to action, and copy for common online advertising channels.

In plain words
What is it for?
Use it to write or vary Meta, Google, and LinkedIn ads, landing pages, banners, headlines, calls to action, and A/B test versions.
Why use it?
It turns a campaign brief into usable text while accounting for the audience stage, language, tone, channel, and placement.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ad-creative plugin — 8 skills, 2 commands shipped together

Good fit Use it to write or vary Meta, Google, and LinkedIn ads, landing pages, banners, headlines, calls to action, and A/B test versions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gekkos-tech/agency-os/ad-copy
Install

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.

Any agent
npx skills add Gekkos-tech/agency-os --skill ad-copy
Clone the repo
git clone --depth 1 https://github.com/Gekkos-tech/agency-os

Made for: Claude Code.

Or install ad-creative, the plugin that ships this one along with the rest of its 8 skills, 2 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/gekkos-tech/agency-os/ad-copy/github.svg)](https://agentmods.dev/skills/gekkos-tech/agency-os/ad-copy)
Your own site
<a href="https://agentmods.dev/skills/gekkos-tech/agency-os/ad-copy"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/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.

agentmods 80×15 button for ad-copy

Your own site · 80×15
<a href="https://agentmods.dev/skills/gekkos-tech/agency-os/ad-copy"><img src="https://agentmods.dev/badge/skills/gekkos-tech/agency-os/ad-copy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 162 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,964 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 $0.00162 $0.01964
Opus 5 $0.00081 $0.00982
Sonnet 5 $0.00032 $0.00393
Haiku 4.5 $0.00016 $0.00196

Measured 11d ago against content hash d8ad39d02a31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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.

plugins/ad-creative/skills/ad-copy/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ad Copy — Performance Copywriting (DE + EN)

Write conversion-focused copy for ads and landing pages in German, English, or both. Output is finished, publishable text — not concepts, not briefs.

© GEKKOS Tech. Licensed under MIT.

Before writing

Establish from the brief (infer and state assumptions if missing):

  1. Language(s): DE, EN, or both. If the market is DACH and the user didn't specify, default to German and offer English variants.
  2. Funnel stage: cold (never heard of the brand), warm (knows the problem/brand), hot (retargeting, cart, comparison shoppers).
  3. Voice position: locate the brand on the tonality matrix in references/tonality-matrix.md before writing a single line. State the chosen cell.
  4. German address form: run the Du/Sie decision tree (below) and state the decision.
  5. Channel + placement: determines length limits and register (see tonality matrix, platform axis).

Headline systems

Four systems. Pick the system that matches funnel stage and channel; write within it, don't mix systems inside one headline.

1. Benefit-led

Formula: [Outcome] in/ohne/without [timeframe/pain] — lead with what the customer gets, stated concretely.

  • EN: "Payroll done in 4 minutes. Every month."
  • DE: "Lohnabrechnung in 4 Minuten. Jeden Monat." Use for: cold traffic, search ads (matches query intent), products with a clear measurable outcome.

2. Curiosity

Formula: [Specific subject] + [information gap] — open a gap the reader can only close by clicking. Must pay off; never bait.

  • EN: "The onboarding email 9 out of 10 SaaS teams get wrong."
  • DE: "Der Fehler, den fast jedes Onboarding-Mailing macht." Use for: content-adjacent ads, advertorials, warm audiences. Avoid for: search (intent mismatch), regulated categories.

3. Social-proof

Formula: [Number/name of adopters] + [what they did/found].

  • EN: "14,000 clinics switched. Here's why."
  • DE: "14.000 Praxen sind umgestiegen. Aus gutem Grund." Use for: skeptical audiences, high-consideration B2B, retargeting. Proof must be real and current.

Read the full file on GitHub · 108 lines

Files

What ships with it

1 file 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.

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. 11d ago First seen · 108 lines · 162 tokens per session scan A d8ad39d02a31

Subscribe to this mod's changes

ad-copy is a skill published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 2mo ago), licensed MIT. It adds 162 tokens to every session and 1,964 once invoked, about $0.0008 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

apple-container

Apple's open-source container CLI to build, run, and manage OCI/Linux containers as lightweight per-container VMs on Apple-silicon macOS — no Docker daemon required. Use when the user mentions the container CLI, "apple container", running or building containers on macOS without Docker/Podman, container run, container…

sanjay3290/ai-skills · 146 tokens

atlassian

Manage Jira issues and Confluence wiki pages in Atlassian Cloud. Use when: (1) searching/creating/updating Jira issues with JQL, (2) searching/reading/creating Confluence pages with CQL, (3) managing Jira workflows, transitions, and comments, (4) browsing Confluence spaces and page hierarchies. Supports OAuth 2.1 via…

sanjay3290/ai-skills · 96 tokens

elevenlabs

Convert documents and text to audio using ElevenLabs text-to-speech. Use this skill when the user wants to create a podcast, narrate a document, read aloud text, generate audio from a file, or convert text to speech.

sanjay3290/ai-skills · 51 tokens

outline

Search, read, and manage Outline wiki documents. Use when: (1) searching wiki for documentation, (2) reading wiki pages or articles, (3) listing wiki collections or documents, (4) creating or updating wiki content, (5) exporting documents as markdown. Works with any Outline wiki instance (self-hosted or cloud).

sanjay3290/ai-skills · 71 tokens

google-drive

Interact with Google Drive - search files, find folders, list contents, download files, upload files, create folders, move, copy, rename, and trash files. Use when user asks to: search Google Drive, find a file/folder, list Drive contents, download or upload files, create folders, move files, or organize Drive…

sanjay3290/ai-skills · 85 tokens

playwright-cli

Automates browser interactions for testing and validating your own web applications using playwright-cli. Use when you need terminal-first browser control for navigation, form filling, screenshots, tracing, bound browser sessions, debugging, or generating Playwright test code. Only use against applications you own or…

testdino-hq/playwright-skill · 64 tokens