agentmods.dev

ad-creative-testing

ad-creative-testing is a skill for Claude Code from brainbytes-dev/everything-claude-marketing. It costs 26 tokens per session (3,468 once invoked), scanned A, original, MIT.

A structured way to test different advertising ideas, such as messages, formats, and creative angles, across platforms like Meta, Google, LinkedIn, TikTok, and YouTube.

In plain words
What is it for?
It helps plan ad experiments, compare creative combinations, find winning concepts, detect tired ads, and document testing results.
Why use it?
It replaces guesswork with planned comparisons and helps identify which ideas work before creative fatigue reduces campaign performance.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the everything-claude-marketing plugin — 72 skills, 22 commands, 18 agents, 2 hooks shipped together

not rated 10repo +1 7mo ago A scan 26 tokens original MIT

Good fit It helps plan ad experiments, compare creative combinations, find winning concepts, detect tired ads, and document testing results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/brainbytes-dev/everything-claude-marketing/ad-creative-testing
View source ↗ brainbytes-dev/everything-claude-marketing
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 brainbytes-dev/everything-claude-marketing --skill ad-creative-testing
Clone the repo
git clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketing

Made for: Claude Code.

Or install everything-claude-marketing, the plugin that ships this one along with the rest of its 72 skills, 22 commands, 18 agents, 2 hooks.

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-creative-testing

README.md
[![agentmods](https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/ad-creative-testing/github.svg)](https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/ad-creative-testing)
Your own site
<a href="https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/ad-creative-testing"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/ad-creative-testing/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-creative-testing

Your own site · 80×15
<a href="https://agentmods.dev/skills/brainbytes-dev/everything-claude-marketing/ad-creative-testing"><img src="https://agentmods.dev/badge/skills/brainbytes-dev/everything-claude-marketing/ad-creative-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,468 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 $0.00026 $0.03468
Opus 5.5 $0.00010 $0.01387
Sonnet 5.5 $0.00005 $0.00694
Haiku 4.5 $0.00003 $0.00347

Measured 2mo ago against content hash f5e40be2b6fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ad-creative-testing 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 2mo 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.

skills/paid-ads/ad-creative-testing/SKILL.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ad Creative Testing

When to Activate

Use this skill when:

  • Launching new ad campaigns that require creative testing
  • Optimizing existing campaigns with creative refreshes
  • Building a systematic testing framework for ad creative
  • Determining winning creative elements (hooks, formats, angles)
  • Detecting and addressing creative fatigue
  • Establishing a creative testing library and documentation process

First Questions

Before designing creative tests, clarify:

  1. What platform(s) are being tested on? (Meta, Google, LinkedIn, TikTok, YouTube)
  2. What is the current creative performance? (Baseline CTR, CPA, ROAS)
  3. What creative assets are available? (Images, video, UGC, product shots)
  4. What is the testing budget? (Determines number of simultaneous variants)
  5. What is the current conversion volume? (Need enough data for statistical significance)
  6. How quickly can new creative be produced? (Testing velocity depends on production speed)
  7. What has been tested before? (Don't repeat failed experiments without new hypotheses)

Core Rules

  1. Test concepts before details. A new messaging angle matters more than a different font color. Start with big swings.
  2. Isolate one variable at a time. If you change the image AND the headline, you don't know which made the difference.
  3. Let data decide, not opinions. The creative your team loves and the creative your audience loves are rarely the same.
  4. Statistical significance is non-negotiable. Small sample sizes lead to false conclusions. Don't declare winners too early.
  5. Winners decay. Every winning creative eventually fatigues. Plan for continuous testing, not one-and-done.
  6. Document everything. Without documentation, learnings are lost and tests get repeated.
  7. Testing is an investment, not an expense. Allocate 15-20% of ad budget specifically for creative testing.
  8. Bad creative tested is better than good creative guessed. Launch and learn. Overthinking kills momentum.

Read the full file on GitHub · 392 lines

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. 2mo ago First seen · 392 lines · 26 tokens per session scan A f5e40be2b6fc

Subscribe to this mod's changes

ad-creative-testing is a skill published in the GitHub repository brainbytes-dev/everything-claude-marketing (10 stars, last pushed 7mo ago), licensed MIT. It adds 26 tokens to every session and 3,468 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.

Analytics and metricsMarketing and SEO
Related

ad-creative-testing compared with skills from other repositories

ad-creative-testing next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ad-creative-testingbrainbytes-dev/everything-claude-marketingSkill107mo agoMITA26Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code