OpenClaudia

Install

npx openclaudia install --all

This is third-party code. Review the repository files before installing.

What it does

The set is grouped into SEO and site audits, content writing, email, social, ads, analytics, conversion, research and growth. Some skills only provide a method, such as A/B test design with sample size calculation or landing page copy. Others work with external services: SemRush, Ahrefs, Google Search Console and Analytics, Google Ads and HubSpot, send email through Resend, and post to Discord, Slack, Telegram and Bluesky. The openclaudia installer copies the chosen skills into the Claude Code skills directory.

Who it is for. For marketers and founders of small products willing to run marketing from the terminal through an agent.

Example request

Plan an A/B test for the sign-up button: 3 percent conversion, 20,000 visits per month

Limitations

Integration skills need your own keys and often paid plans: SemRush, Ahrefs, Similarweb, HubSpot, Resend and others. Russian ad and analytics services are not supported, and some foreign APIs are unavailable from Russia or need a foreign card. Claude Code is the main target, other agents go through npx skills.

How to disable. Delete the skill folders from ~/.claude/skills or the project's .claude/skills and revoke any service keys you issued.

Security check

• Integration skills send emails and publish posts on your behalf
• They need keys to ad, analytics and CRM services

README in short

The README compares the set with paid marketing tools and shows installation via npx openclaudia, npx skills or manual copying. Skills are listed in grouped tables with short purposes. A usage guide lives in USAGE.md, and contribution steps are described. MIT licensed.

SKILL.md

---
name: ab-test-setup
description: Design, plan, and analyze A/B tests with statistical rigor. Use when the user asks about A/B testing, split testing, experiment design, statistical significance, sample size calculation, test duration, multivariate testing, or conversion experiments. Trigger phrases include "A/B test", "split test", "experiment", "statistical significance", "sample size", "test duration", "which version wins", "conversion experiment", "hypothesis test", "variant testing".
---

# A/B Test Design and Analysis

You are an expert in experimentation and A/B testing. When the user asks you to design a test, calculate sample sizes, analyze results, or plan an experimentation roadmap, follow this framework.

## Step 1: Gather Test Context

Establish: page/feature being tested, current conversion rate, monthly traffic, primary metric, secondary metrics, guardrail metrics, duration constraints, testing platform (Optimizely, VWO, custom).

## Step 2: Hypothesis Framework

### Hypothesis Template

```
OBSERVATION: [What we noticed in data/research/feedback]
HYPOTHESIS: If we [specific change], then [metric] will [change] by [amount],
            because [behavioral/psychological reasoning].
CONTROL (A): [Current state]
VARIANT (B): [Proposed change]
PRIMARY METRIC: [Single metric that determines winner]
GUARDRAILS: [Metrics that must not degrade]
```

### Hypothesis Categories

- **Clarity**: "Users don't understand what we offer" -- test headline, value prop
- **Motivation**: "Users aren't motivated to act" -- test social proof, urgency, benefits
- **Friction**: "Process is too difficult" -- test form length, step count, layout
- **Trust**: "Users don't trust us" -- test testimonials, guarantees, badges
- **Relevance**: "Content doesn't match intent" -- test personalization, segmentation

Related