Ad Test Designer
aaron-he-zhu/aaron-marketing-skills
A skill your agent uses when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"…
A/B and multivariate testing methodology. An agent skill from thatrebeccarae/claude-marketing.
Install Ab Testing Framework
$ npx skills add thatrebeccarae/claude-marketing --skill ab-testing-framework -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install thatrebeccarae/claude-marketing ab-testing-framework --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ab-testing-framework .claude/skills/ab-testing-framework && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ab-testing-framework" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/ab-testing-framework into .claude/skills/ab-testing-framework/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ab-testing-framework", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/ab-testing-frameworkType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add thatrebeccarae/claude-marketing --skill ab-testing-framework -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install thatrebeccarae/claude-marketing ab-testing-framework --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ab-testing-framework .agents/skills/ab-testing-framework && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ab-testing-framework" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/ab-testing-framework into .agents/skills/ab-testing-framework/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ab-testing-framework", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add thatrebeccarae/claude-marketing --skill ab-testing-framework -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install thatrebeccarae/claude-marketing ab-testing-framework --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ab-testing-framework .cursor/skills/ab-testing-framework && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ab-testing-framework" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/ab-testing-framework into .cursor/skills/ab-testing-framework/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ab-testing-framework", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/thatrebeccarae/claude-marketing.git --path skills/ab-testing-framework--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add thatrebeccarae/claude-marketing --skill ab-testing-framework -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install thatrebeccarae/claude-marketing ab-testing-framework --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ab-testing-framework .gemini/skills/ab-testing-framework && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ab-testing-framework" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/ab-testing-framework into .gemini/skills/ab-testing-framework/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ab-testing-framework", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install thatrebeccarae/claude-marketing ab-testing-frameworkInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add thatrebeccarae/claude-marketing --skill ab-testing-framework -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ab-testing-framework .github/skills/ab-testing-framework && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ab-testing-framework" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/ab-testing-framework into .github/skills/ab-testing-framework/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ab-testing-framework", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add thatrebeccarae/claude-marketing --skill ab-testing-framework -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install thatrebeccarae/claude-marketing ab-testing-framework --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/thatrebeccarae/claude-marketing.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ab-testing-framework .opencode/skills/ab-testing-framework && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ab-testing-framework" agent skill from https://github.com/thatrebeccarae/claude-marketing/tree/main/skills/ab-testing-framework into .opencode/skills/ab-testing-framework/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ab-testing-framework", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ab-testing-framework- GitHub stars
- 162
- Token cost
- ~1.3k tokens
- SKILL.md length
- 553 words
- Files
- 4
- Skills in repo
- 55
- Repo updated
- First seen
- Licence
- MIT
At a glance
A/B and multivariate testing methodology. An agent skill from thatrebeccarae/claude-marketing.
- Works in 5 steps: Hypothesis → Sample Size Calculation → Test Execution Rules → …
- The user asks about A/B testing
- SKILL.md covers Install, Test Design Process, Common Testing Pitfalls and What to Test (Prioritized by…, plus 1 more section
- Calls git
What it does
Ab Testing Framework is an agent skill from thatrebeccarae/claude-marketing. A/B and multivariate testing methodology. Design experiments, calculate sample sizes, determine statistical significance, avoid common pitfalls, and interpret results. Platform-agnostic framework applicable to landing pages, emails, ads, pricing, and product features. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, or conversion experiments.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `EXAMPLES.md` and `REFERENCE.md`).
It sits in Marketing & SEO, covering A/B testing and Experimental design. The repository describes itself as: A full marketing department for Claude Code. Skill packs for Klaviyo, Shopify, GA4, Looker Studio, paid media, and more. Audit, optimize, and report using natural language. The licence is MIT.
When your agent uses it
- The user asks about A/B testing
- Experiment design
- Statistical significance
- Conversion experiments
Example prompts
- “/ab-testing-framework”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit a8a63ec. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Ab Testing Framework loads about 1.3k tokens when it runs. Until then it costs about 105 tokens; SKILL.md has 553 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from thatrebeccarae/claude-marketing at commit a8a63ec, republished under its MIT licence (© thatrebeccarae). 553 words, ~1,342 tokens.
Download SKILL.mdSave it as
.claude/skills/ab-testing-framework/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- ab-testing-framework
- description
- A/B and multivariate testing methodology. Design experiments, calculate sample sizes, determine statistical significance, avoid common pitfalls, and interpret results. Platform-agnostic framework applicable to landing pages, emails, ads, pricing, and product features. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, or conversion experiments.
- license
- MIT
- origin
- custom
- author
- Rebecca Rae Barton
- author_url
- https://github.com/thatrebeccarae
- metadata.version
- 1.0.0
- metadata.category
- analytics
- metadata.domain
- experimentation
- metadata.updated
- 2026-03-18
- metadata.tested
- 2026-03-18
- metadata.tested_with
- Claude Code v2.1
A/B Testing Framework
Design, run, and analyze conversion experiments with statistical rigor.
Install
git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/ab-testing-framework ~/.claude/skills/Test Design Process
Step 1: Hypothesis
Template: If we [change X], then [metric Y] will [increase/decrease] by [Z%] because [reason].
Good hypothesis: "If we change the CTA from Get Started to Start Free Trial, then signup rate will increase by 15% because it reduces uncertainty about cost."
Bad hypothesis: "If we change the button color, conversions will improve." (No reasoning, no expected magnitude.)
Step 2: Sample Size Calculation
To determine how long to run a test:
Required sample per variation = 16 * (p * (1-p)) / (MDE^2)
Where:
p = baseline conversion rate (as decimal)
MDE = minimum detectable effect (as decimal)| Baseline Rate | 10% MDE | 20% MDE | 30% MDE |
|---|---|---|---|
| 1% | 253,414 | 63,354 | 28,157 |
| 3% | 82,369 | 20,592 | 9,152 |
| 5% | 48,640 | 12,160 | 5,404 |
| 10% | 23,040 | 5,760 | 2,560 |
| 20% | 10,240 | 2,560 | 1,138 |
Minimum test duration: 2 full business weeks (to capture day-of-week effects), even if sample size is reached sooner.
Step 3: Test Execution Rules
- Random assignment — visitors must be randomly assigned to control/variant
- No peeking — do not check results before reaching sample size
- No mid-test changes — do not modify variants during the test
- Even traffic split — 50/50 for A/B, even splits for multivariate
- Single variable — change only one thing per test (unless multivariate)
- Full duration — run for the pre-calculated duration, not until significance
Step 4: Statistical Analysis
Frequentist Approach
Z-test for proportions:
Z = (p1 - p2) / sqrt(p_pooled * (1 - p_pooled) * (1/n1 + 1/n2))
Where:
p1, p2 = conversion rates of control and variant
p_pooled = (x1 + x2) / (n1 + n2)
n1, n2 = sample sizesp-value interpretation:
- p < 0.05: Statistically significant (95% confidence)
- p < 0.01: Highly significant (99% confidence)
- p >= 0.05: Not significant — do not declare a winner
Bayesian Approach
When to use Bayesian:
- Low traffic (small sample sizes)
- Need to make decisions faster
- Want probability of each variant being best (not just "significant or not")
Interpretation: "There is a 94% probability that Variant B is better than Control" vs frequentist "We reject the null hypothesis at 95% confidence."
Step 5: Decision Framework
| Result | Significance | Action |
|---|---|---|
| Variant wins | p < 0.05 | Implement variant |
| Control wins | p < 0.05 | Keep control, learn from failure |
| No difference | p >= 0.05 | Keep control, test something bigger |
| Variant wins | p = 0.05-0.10 | Consider traffic — may need more time |
Show full SKILL.md (224 more words)Show less
Common Testing Pitfalls
- Peeking — checking results early inflates false positive rate from 5% to 26%+
- Stopping early — reaching significance != reaching required sample size
- Testing too many variants — each variant needs full sample size
- Ignoring segments — overall winner may be loser for key segments
- Too small an effect — testing for 2% lift needs enormous sample sizes
- Not accounting for seasonality — run full weeks, avoid holidays
- Multiple metrics — primary metric must be pre-declared; secondary are directional
- Survivorship bias — only measuring users who complete, not those who abandon
- Simpson paradox — segment-level winners can reverse at aggregate level
- Novelty effect — new designs get temporary lift; re-test after 2-4 weeks
What to Test (Prioritized by Impact)
High Impact
- Value proposition / headline
- CTA text and placement
- Pricing and offer structure
- Form length (fields removed)
- Page layout (single column vs multi)
- Social proof presence and placement
Medium Impact
- Image/video vs static
- Testimonial format (text vs video)
- Navigation presence on landing pages
- Trust badges and security signals
- Urgency elements (countdown, stock)
Low Impact (Usually Not Worth Testing)
- Button color (unless extreme contrast issue)
- Font changes
- Minor copy tweaks
- Icon styles
- Footer content
Integration with Other Skills
- cro-auditor — CRO audit generates test hypotheses; this skill designs the experiments
- google-analytics — GA4 for experiment data and segment analysis
- copywriting-frameworks — Generate variant copy using proven frameworks
© thatrebeccarae, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files in skills/ab-testing-framework of thatrebeccarae/claude-marketing.
- SKILL.md
- EXAMPLES.md
- LICENSE
- REFERENCE.md
Open the folder on GitHubat commit a8a63ec
Compare with similar skills
Ab Testing Framework next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Ab Testing Framework this skillthatrebeccarae/claude-marketing | 162 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Ad Test Designeraaron-he-zhu/aaron-marketing-skills | 2.9k | 2 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Ab Test Analyzeririnabuht12-oss/marketing-skills | 3.9k | — | ~1.4k | Automated safety check: Pass | None | |
| Define Hypothesisproduct-on-purpose/pm-skills | 715 | — | ~966 | Automated safety check: Pass | Apache-2.0 | |
| A B Test DesignOwl-Listener/designer-skills | 2.9k | 1 repos | ~472 | Automated safety check: Pass | MIT | |
| Ab Test Planindranilbanerjee/digital-marketing-pro | 855 | 1 repos | ~2k | Automated safety check: Pass | MIT |
Similar skills
Ab Test Analyzer
irinabuht12-oss/marketing-skills
Statistical significance calculator for A/B test results with sample size requirements, segment breakdowns, and hypothesis generation.
Define Hypothesis
product-on-purpose/pm-skills
Defines a testable hypothesis with clear success metrics and a validation approach.
A B Test Design
Owl-Listener/designer-skills
Design an A/B experiment — hypothesis, variants, primary metric, and sample size.
Ab Test Plan
indranilbanerjee/digital-marketing-pro
Design a statistically rigorous A/B or multivariate test plan — If/Then/Because hypothesis, control and variant specs, required sample size per variant (absolute vs relative MDE via…
Ab Testing
ericrisco/rsc-harness
A skill your agent uses when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that won't go…
More from thatrebeccarae/claude-marketing
All 55 skills in this repoGoogle Analytics
thatrebeccarae/claude-marketing
Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements.
Content Creator
thatrebeccarae/claude-marketing
Comprehensive content marketing toolkit with brand voice analysis, SEO optimization scripts, content frameworks, social media strategy, and content calendar planning.
Klaviyo Analyst
thatrebeccarae/claude-marketing
Klaviyo marketing operations and analyst expertise. An agent skill from thatrebeccarae/claude-marketing.
Klaviyo Developer
thatrebeccarae/claude-marketing
Klaviyo API and developer integration expertise. An agent skill from thatrebeccarae/claude-marketing.
Looker Studio
thatrebeccarae/claude-marketing
Looker Studio (formerly Google Data Studio) expertise. An agent skill from thatrebeccarae/claude-marketing.
Shopify
thatrebeccarae/claude-marketing
Shopify e-commerce platform marketing expertise. An agent skill from thatrebeccarae/claude-marketing.
Related
Categories
Questions about Ab Testing Framework
What does Ab Testing Framework do?
A/B and multivariate testing methodology. An agent skill from thatrebeccarae/claude-marketing. Ab Testing Framework is an agent skill from thatrebeccarae/claude-marketing. A/B and multivariate testing methodology.
When should I use Ab Testing Framework?
Ab Testing Framework fits situations like: the user asks about A/B testing; experiment design; statistical significance; conversion experiments.
How do I install Ab Testing Framework in Claude Code?
Run `npx skills add thatrebeccarae/claude-marketing --skill ab-testing-framework -a claude-code`. Or copy the skill folder (skills/ab-testing-framework in thatrebeccarae/claude-marketing) into .claude/skills/ab-testing-framework in your project. Claude Code loads it when a task matches its description.
How do I install Ab Testing Framework in Codex?
Run `npx skills add thatrebeccarae/claude-marketing --skill ab-testing-framework -a codex`. Or copy the skill folder (skills/ab-testing-framework in thatrebeccarae/claude-marketing) into .agents/skills/ab-testing-framework in your project. Codex loads it when a task matches its description.
Can I use Ab Testing Framework in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add thatrebeccarae/claude-marketing --skill ab-testing-framework -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ab-testing-framework, .gemini/skills/ab-testing-framework, .github/skills/ab-testing-framework and .opencode/skills/ab-testing-framework in your project.
What does Ab Testing Framework need to run?
Going by SKILL.md and its folder, Ab Testing Framework needs the command-line tools its instructions call (git).
Does Ab Testing Framework access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Ab Testing Framework safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Ab Testing Framework use?
Ab Testing Framework is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Ab Testing Framework use?
About 1.3k tokens (SKILL.md is roughly 5.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Ab Testing Framework?
Skills that share tags, products or a category with Ab Testing Framework: Ad Test Designer (aaron-he-zhu/aaron-marketing-skills, 2.9k stars), Ab Test Analyzer (irinabuht12-oss/marketing-skills, 3.9k stars), Define Hypothesis (product-on-purpose/pm-skills, 715 stars) and A B Test Design (Owl-Listener/designer-skills, 2.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ab Testing Framework?
thatrebeccarae (a GitHub user) maintains it in thatrebeccarae/claude-marketing, which has 162 GitHub stars. The repository holds 55 skills in this directory. The repository was last updated on May 14, 2026.
Source: thatrebeccarae/claude-marketing on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.