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 skills add thatrebeccarae/claude-marketing --skill ab-testing-frameworkgit clone --depth 1 https://github.com/thatrebeccarae/claude-marketingWrote 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.
[](https://agentmods.dev/skills/thatrebeccarae/claude-marketing/ab-testing-framework)<a href="https://agentmods.dev/skills/thatrebeccarae/claude-marketing/ab-testing-framework"><img src="https://agentmods.dev/badge/skills/thatrebeccarae/claude-marketing/ab-testing-framework.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.01388 |
| Opus 5 | $0.00037 | $0.00694 |
| Sonnet 5 | $0.00015 | $0.00278 |
| Haiku 4.5 | $0.00007 | $0.00139 |
Grade A, and why
ab-testing-framework 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 8d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 sizes
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 147 lines · 74 tokens per session scan A 3403bd69091a
ab-testing-framework is a skill published in the GitHub repository thatrebeccarae/claude-marketing (132 stars, last pushed 3mo ago), licensed MIT. It adds 74 tokens to every session and 1,388 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
seo-validate
SEO validator: meta/OG, Schema.org, hreflang, Core Web Vitals, crawlability. Triggers: SEO, meta tags, Schema.org, hreflang, LCP, INP, CLS, Core Web Vitals, sitemap, crawlability.
csharp-patterns
C#/.NET: LINQ, async/await, DI, records, nullable refs, ASP.NET Core, EF Core, MediatR. Triggers: C#, .NET, dotnet, ASP.NET, EF Core, LINQ, record type, IServiceCollection.
ruby-patterns
Ruby/Rails: blocks, metaprogramming, ActiveRecord, Sidekiq, RSpec, Sorbet, Hanami. Triggers: Ruby, Rails, ActiveRecord, Sidekiq, RSpec, Gemfile, bundler, Hanami, Sorbet.
debug
Systematic debugging via logs, health checks, hypothesis-driven investigation. Triggers: debug, error, trace root cause, fix bug, reproduce symptom, investigation.
research-mastery
Hierarchical retrieval: KB → MCP/Context7 → web. Triggers: research, fact-check, verify, synthesize, cross-reference, multi-source, cite sources.
plan
Breaks features/goals into phased plans with task lists, agent assignments, dependencies. Triggers: plan feature, implementation roadmap, break down task, project phases.