ab-test
Skill1 starsChanged 8 months agoMITView on GitHub
v4.0 Meta-Level A/B Test Generator (Data-Driven Splitting)
6 other projects use a version of this.
Adopted by
Most recently taken up by
- ali-demirbas/ab-test-playbooktheir own version, first seen Oct 21, 2026
- m-binimran/marketing-packtheir own version, first seen Oct 15, 2026
- akachandan1/proofstacktheir own version, first seen Oct 11, 2026
- sidchaudhary/gtm-skillstheir own version, first seen Aug 21, 2026
- Aetheria-Labs1/storefront-skillstheir own version, first seen Aug 7, 2026
- sergeeey/Claude-cod-top-2026their own version, first seen May 13, 2026
Used with
Projects with it also use email-sequence.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkillemail-sequence
Design and draft multi-email sequences with full copy, timing, branching logic, exit conditions, and performance benchmarks. Use when building onboarding, lead nurture, re-engagement, win-back, or product launch flows, when you need a complete drip campaign with A/B test suggestions, or when mapping a sequence end-to-end with a flow diagram.
Also in 3 projects that use this
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- sergeeey/Claude-cod-top-2026★ 9same name
- Aetheria-Labs1/storefront-skills★ 8same name
- m-binimran/marketing-pack★ 1same name
- sidchaudhary/gtm-skills★ 1same name
- akachandan1/proofstack★ 0same name
- ali-demirbas/ab-test-playbook★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- ad-copySkill
- brand-strategySkill
- competitor-analysisSkill
- content-calendarSkill
- email-campaignSkill
- lead-generationSkill
- marketing-campaignSkill
- product-descriptionSkill
- sales-objectionSkill
- seo-contentSkill
- social-media-postSkill
- viral-hookSkill
- visual-promptSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Cross-Reference Brand Voice: If brand-voice.md is present, strictly follow the brand's tone.
- Very specific: line 15
Check for
--guidedFlag: If enabled, ask 3 questions about the "Target Metric" and "Past Results" before generating. - Distinctive: line 19
Create TWO (2) scientifically distinct variations (Group A: Control vs.
- Distinctive: line 28
Only change ONE variable between A and B to maintain statistical validity.
- Distinctive: line 30
Never make false claims in either variation.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
🧪 v4.0 "The Strategic Scientist" execution model
You are now acting as the Masterpiece A/B Test Generation Engine.
🛠 Operational Workflow
- Read Meta-Logic: Load the configuration from
ab-test/meta.json. - Load Global Context: Consult
core/global-constraints.jsonandcore/marketing-triggers.json. - Cross-Reference Brand Voice: If
brand-voice.mdis present, strictly follow the brand's tone. - Confirm the CORE VARIABLE: Identify the ONE thing being tested (Hook, CTA, Tone, Angle).
- Check for
--guidedFlag: If enabled, ask 3 questions about the "Target Metric" and "Past Results" before generating. - Parameter Injection: Process: $ARGUMENTS
🎯 Generative Directive
- Create TWO (2) scientifically distinct variations (Group A: Control vs. Group B: Test).
- Variation A must follow established industry best practices for $ARGUMENTS.
- Variation B must test ONE high-impact psychological variable from
core/marketing-triggers.json.
🧠 Psychology Breakdown (REQUIRED)
- Primary Hypothesis: Explain what you expect to learn from this test.
- Conversion Strategy: Detail the psychological trigger that differs between A and B.
🚫 Constraints
- Only change ONE variable between A and B to maintain statistical validity.
- Both versions must strictly meet the
core/global-constraints.jsonfor character/hashtag limits. - Never make false claims in either variation.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

