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.
npx agentmods add skills/brainbytes-dev/everything-claude-marketing/ab-testingnpx skills add brainbytes-dev/everything-claude-marketing --skill ab-testinggit clone --depth 1 https://github.com/brainbytes-dev/everything-claude-marketingWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00031 | $0.02775 |
| Opus 5 | $0.00015 | $0.01388 |
| Sonnet 5 | $0.00006 | $0.00555 |
| Haiku 4.5 | $0.00003 | $0.00278 |
Grade A, and why
ab-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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
A/B Testing for Marketing
When to Activate
- Testing landing page variations to improve conversion rate
- Optimizing email subject lines, copy, or design
- Comparing ad creatives, headlines, or CTAs
- Evaluating pricing page layouts or offers
- Running feature experiments for product-led growth
- Resolving internal debates about what works with data instead of opinions
- Building a systematic testing program
First Questions
- What are you testing? (Landing page, email, ad, pricing, feature)
- What is your primary conversion metric? (Sign-up, purchase, click, engagement)
- What is your current conversion rate for this metric?
- How much traffic or volume do you have? (Monthly visitors, email list size, daily ad impressions)
- What is the minimum improvement that would be meaningful to the business?
- What testing tool are you using? (Google Optimize successor, VWO, Optimizely, LaunchDarkly, in-house)
- Have you run tests before? What has your win rate been?
Hypothesis Formation
The If/Then/Because Format
Every test must start with a hypothesis. No hypothesis = no learning regardless of outcome.
Template:
If we [change this specific thing], then [this metric] will [increase/decrease] by [estimated amount], because [reason based on data, research, or user insight].
Examples:
- "If we shorten the sign-up form from 6 fields to 3, then sign-up completion rate will increase by 15%, because our funnel analysis shows 40% drop-off at the form step and user research indicates friction from too many fields."
- "If we add social proof (customer count) above the fold on pricing, then trial sign-ups will increase by 10%, because our exit surveys show 'trust' as the #2 concern for prospects."
What Makes a Good Hypothesis
- Based on data or user insight, not a hunch.
- Specific about what changes and what metric is affected.
- Includes a directional estimate (forces you to think about magnitude).
- Falsifiable — you can clearly prove it wrong.
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.
- 2d ago First seen · 252 lines · 31 tokens per session scan A d7d81e085c6a
ab-testing is a skill published in the GitHub repository brainbytes-dev/everything-claude-marketing (5 stars, last pushed 5mo ago), licensed MIT. It adds 31 tokens to every session and 2,775 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…