Ad Creative Testing

Turn one winning ad into a creative testing plan for TikTok and Meta. Decodes why an ad won (hook, argument, buyer, format), plans concepts that Meta's Andromeda and TikTok treat as genuinely different (buyer × angle × format × first frame, not caption swaps), sets how many creatives to launch, the budget per test and when to judge, writes file and ad names that make results readable, reads hook rate, hold rate, CTR and CPA to find which part failed, and says when to kill, iterate or scale. Use when someone asks how many ads to test, how to make ad variants, why their variants all perform the

38 stars 7 forksTesting & QA Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add vargHQ/skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add vargHQ/skills --skill ad-creative-testing
Manual install
git clone --depth 1 https://github.com/vargHQ/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/ad-creative-testing ~/.claude/skills/ad-creative-testing

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Turn one winning ad into a creative testing plan

Winners are rare. In Motion's 2026 benchmark (578,750 Meta creatives, $1.29B spend), only 5–8% of ads became winners (spend ≥10× the account median and ≥$500). One agency's 1,780 AI creatives produced 8 that crossed $100K in spend (self-reported). The plan exists to find the rare winner cheaply, then milk it.

## 1. The rule that changed: similar ads count as one

Meta groups ads that look or feel alike as variations of one creative and says iteration "should not replace true creative diversification" ([Meta](https://www.facebook.com/business/news/demystifying-creative-diversification)). Agencies report that the same opening or the same look ranks as the same ad, and that 30 face and setting swaps of one winner made CPA triple. TikTok asks for 3–5 *very different* creatives per ad group and at least 12 new videos a month on Smart+ and GMV Max.

**So a variant is a new concept**: a different buyer, angle, format or first frame. A new caption, colour or voice on the same video is not a variant.

## 2. Decode before you multiply

For the current winner (or the competitor ad that has run 30+ days), write down:

| Part | Question | Example |
|---|---|---|
| Hook | Pain callout, result shown, or visual interrupt? | Result shown: a clean oven at 0:00 |
| Argument | Why buy: speed, price, proof, transformation, comparison? | Speed: "60 seconds" |
| Buyer | Who actually bought (not the targeting)? | Renters, 25–35 |
Read the full skill on GitHub

Details

Skill name
ad-creative-testing
Repository
vargHQ/skills
Path
ad-creative-testing/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Ad Creative Testing skill do?

Turn one winning ad into a creative testing plan for TikTok and Meta. Decodes why an ad won (hook, argument, buyer, format), plans concepts that Meta's Andromeda and TikTok treat as genuinely different (buyer × angle × format × first frame, not caption swaps), sets how many creatives to launch, the budget per test and when to judge, writes file and ad names that make results readable, reads hook rate, hold rate, CTR and CPA to find which part failed, and says when to kill, iterate or scale. Use when someone asks how many ads to test, how to make ad variants, why their variants all perform the

How do I install the Ad Creative Testing skill?

Claude Code plugin: /plugin marketplace add vargHQ/skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Ad Creative Testing popular?

It lives in vargHQ/skills, which has 38 GitHub stars and 7 forks, and is included in 1 curated skill list.

Related skills

AI Ad Compliance Check

38

vargHQ/skills

Turns an AI video ad into a compliance report for TikTok Shop, TikTok ads, Meta, YouTube, the FTC, New York's synthetic-performer law and the EU AI Act before it runs: varg video_analyze pulls every shot, spoken and on-screen claim and person, each claim is matched to the seller's evidence, the visuals are checked against TikTok Shop's AI product rules (no fake effects, before/after, changed quantity or size), people and voices against the FTC fake-testimonial rule, and the result is a pass / fix / block list with the rule, source and date, a rewrite for each fix, and the AI labels to set on e

AI, LLMs & AgentsIn 1 list

AI Parody Video

38

vargHQ/skills

Plan and make a short AI parody video: a known movie scene, TV format or news shot with one wrong element, 10 to 45 seconds, built to be shared. Gives the joke structure, six formats measured on clips with 60 thousand to 9 million views (scene recast with new dialogue, original-vs-remake, one-prompt sitcom sketch, fake live news shot, character monologue, silent slapstick), which production route each one takes, prompt templates for the sketch and the news shot, subtitle and caption rules, and a plain list of what is allowed with real people, known characters, studio footage and cloned voices,

AI, LLMs & AgentsIn 1 list

AI Ugc Ad Video

38

vargHQ/skills

Open-source alternative to Arcads: AI UGC ads with an AI actor holding your real product. Casts a creator whose age matches the claim in the room where the problem happens, writes a phone-real script (a yapper, unboxing, street interview or in-car take) with every line in the prompt, locks the face, the voice and the product label across shots, prompts camera flaws and breaths so it doesn't look waxy, generates on Seedance 2.5, Kling 4 or Creatify through varg, and labels it. It never puts a first-person testimonial or result in an AI mouth (FTC rule) and never targets TikTok Shop presenters (

AI, LLMs & AgentsIn 1 list

Five Forces Pressure Test

33

AnugamChakra/think-like-a-strategy-consultant

Rates an industry on Porter's Five Forces to judge whether the market is structurally worth competing in, flags dangerous force interactions, and is honest about where the model misleads. Use this skill whenever the user asks how attractive an industry is, says "run Five Forces", "is this a good market to be in", "what's the industry structure", or "how hard is this market". Trigger it whenever the question is about industry attractiveness rather than a company's own position. Do NOT use it to decide whether and how a specific company should enter a market — that is market-entry-analyzer's job

Testing & QA

TDD Guide

40

ArogyaReddy/alirezarezvani-claude-skills

Test-driven development skill for writing unit tests, generating test fixtures and mocks, analyzing coverage gaps, and guiding red-green-refactor workflows across Jest, Pytest, JUnit, Vitest, and Mocha. Use when the user asks to write tests, improve test coverage, practice TDD, generate mocks or stubs, or mentions testing frameworks like Jest, pytest, or JUnit. Handles test generation from source code, coverage report parsing (LCOV/JSON/XML), quality scoring, and framework conversion for TypeScript, JavaScript, Python, and Java projects.

Testing & QA11

Hypothesis First Coach

33

AnugamChakra/think-like-a-strategy-consultant

Helps the user form a sharp, testable hypothesis early and identify the single fastest test to confirm or kill it, instead of gathering data endlessly. Use this skill whenever someone is drowning in analysis, says "I have too much to look at", "what should I check first", "what's my hypothesis", or is about to research every branch of a problem equally. Trigger it when a user has structured a problem but hasn't yet committed to a point of view, or when they keep gathering information without forming one. Do NOT use it when the problem itself is still vague — run problem-framer first — or when

Testing & QA

Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.