Skip to main content
skill CX Codex

cro-optimization · rampstackco — Claude Code skill: A/B testing and conversion rate optimization

cro-optimization — a skill for structured conversion rate optimization: audit your funnel, generate test hypotheses, design experiments, and analyze results statistically. Runs you through the full cycle from diagnosis to rollout decision.

MIT 307 installs ★ 1,107 updated 2026-10-19

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add rampstackco/claude-skills --skill cro-optimization -a claude-code
Open on GitHub

What cro-optimization does

Works in four phases. First, audit the funnel with quantitative data (drop-off points, traffic segmentation), session replays, heatmaps, and user interviews to surface friction points. Second, turn findings into testable hypotheses grounded in evidence, prioritized by impact, confidence, and ease. Third, design the test: calculate required sample size, set minimum duration to capture full business cycles, define decision criteria before launch, and watch for common traps (peeking, overlapping tests, testing during atypical periods). Fourth, interpret results and decide whether to ship, iterate, or kill the variant.

Requires current conversion rates, access to analytics data, and an A/B testing tool. Tests typically run 2 to 8 weeks. Not suitable for traffic under ~5,000 monthly conversions per variant or for strategy-level questions that need qualitative research first. Stack-agnostic: works with any testing and analytics platform.

What it helps with

  • identify bottlenecks and drop-off points in a conversion funnel
  • calculate sample size and minimum test duration for statistical power
  • interpret test results and avoid false positives or premature conclusions
  • prioritize which hypotheses to test first based on impact and confidence
  • decide whether to ship a winning variant or revisit the hypothesis

Example prompts for the agent

  • Audit my checkout funnel and show me where users abandon and why
  • Design an A/B test to increase primary button click-through. What sample size and duration do I need?
  • I ran a test: control 12%, variant 13.2% with 10,000 visitors. Is this statistically significant?

How to install cro-optimization

1Skills CLI (Vercel)

npx skills add rampstackco/claude-skills --skill cro-optimization -a claude-code

2Manually: put the files in place

~/.claude/skills/cro-optimization/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/cro-optimization/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about cro-optimization

How do I install cro-optimization in Claude Code?

Run npx skills add rampstackco/claude-skills --skill cro-optimization -a claude-code in your terminal, then open ~/.claude/skills/cro-optimization/SKILL.md to verify.

What does the cro-optimization skill do?

It runs conversion rate optimization as a structured discipline: audit your funnel, generate hypotheses from findings, design tests with proper sample size calculation, and interpret results to decide whether to ship or iterate.

What traffic volume do I need to use this skill?

Roughly 5,000 conversions per month per variant. Below that threshold, tests lack statistical power and results won't be reliable.

Source text

SKILL.md · MIT
---
name: cro-optimization
description: "Run conversion rate optimization through hypothesis-driven testing including audit, hypothesis generation, test design, statistical analysis, and rollout decisions. Use this skill whenever the user wants to optimize conversion, run A/B tests, audit a funnel, generate test hypotheses, design experiments, or analyze test results. Triggers on conversion optimization, CRO, A/B test, split test, multivariate test, hypothesis, conversion funnel, funnel audit, experiment design, statistical significance, lift, optimization. Also triggers when the user has a conversion problem and isn't sure where to start, or when test results are ambiguous and need interpretation."
category: growth
catalog_summary: "Hypothesis-driven testing, conversion optimization"
display_order: 2
---

# CRO Optimization

Run conversion rate optimization as a structured discipline: audit → hypothesize → test → decide. Stack-agnostic. Tool-agnostic.

This skill is for running tests against existing pages and flows. For writing landing page copy from scratch, use `landing-page-copy`. For setting up the analytics that make CRO possible, use `analytics-strategy`.

---

## When to use

- Converting traffic at lower rate than expected
- Specific funnel step has high drop-off
- Pages with high traffic that could move the needle if optimized
- A/B testing infrastructure exists (or can be set up)
- Statistical significance and sample size questions

## When NOT to use

- Without sufficient traffic to test (under ~5,000 monthly conversions per variant)
- Pre-launch (no users to test on yet)
- Strategy or messaging-level questions that need qualitative research first
- Brand-defining choices (CRO can't optimize a fundamentally wrong brand)

---

## Required inputs

- The page or flow under optimization
- Current conversion rate and traffic volume
- Access to analytics (event tracking, funnel data)
- An A/B testing tool (or willingness to set one up)
- Time and budget for testing (typically 2 to 8 weeks per test)

---

## The framework: 4 phases

### 1. Audit

Diagnose before treating.

**Quantitative audit:**

- **Funnel data.** Where are users dropping off? The biggest drop is the biggest opportunity.
- **Segmentation.** Does the funnel perform differently by source, device, geography, audience type?
- **Performance data.** Are slow pages dragging conversions?
- **Search Console / on-site search.** What are users looking for that they can't find?

**Qualitative audit:**

- **Session replay.** Watch 20+ sessions of users on the target flow. Note friction, confusion, hesitation.
- **Heatmaps.** Where do users click? Where do they scroll? Where do they not?
- **User interviews / surveys.** Why did users not convert? Survey people who started but abandoned.
- **Form analytics.** Which fields cause abandonment? Which cause errors?
- **Customer support tickets.** What conversion-related questions come in?

**Heuristic audit:**

- Apply CRO heuristics to the flow:
  - Is the value proposition clear in 5 seconds?
  - Is there a single primary CTA per page?
  - Is the form length appropriate to the offer?
  - Is the trust/social proof present?
  - Are objections handled?
  - Is the page accessible? (Accessibility issues hurt conversion silently.)

The audit produces a list of suspected friction points. Each becomes a hypothesis candidate.

### 2. Hypothesis

A testable statement.

**Hypothesis structure:**

> Because [observation from audit], we believe that [change] will produce [predicted outcome] for [user segment], because [reason].

**Example:**

> Because session replays show users abandoning at the shipping step (audit), we believe that adding visible shipping cost to the product page (change) will increase add-to-cart conversion by 5 percent (outcome) for desktop users (segment), because users are surprised by shipping cost and abandon (reason).

**Hypothesis quality criteria:**

- Specific change (not "improve the design")
- Measurable outcome (with a target)
- Grounded in evidence (audit, research, prior tests)
- Tied to a known mechanism (why would this work?)

**Hypothesis prioritization (ICE or PIE):**

- **Impact:** How much could this move the metric?
- **Confidence:** How likely is the hypothesis to be right?
- **Ease:** How easy to test? (Time, complexity, risk)

Score each 1 to 10. Highest combined scores test first.

### 3. Test design

A test that produces an unambiguous answer.

**Sample size and duration:**

Use a sample size calculator (most A/B tools have one) before launching. Inputs:

- Baseline conversion rate
- Minimum detectable effect (the smallest lift you'd care about)
- Statistical power (typically 80%)
- Significance level (typically 95%)

This produces required sample size per variant. Run the test until that sample is reached, OR for a minimum duration that captures full business cycle (typically 2 weeks minimum, to cover weekends and weekly patterns).

**Common test setup mistakes:**

- Stopping the test the moment significance is hit (peeking)
- Running tests for too short to capture a full business cycle
- Running multiple overlapping tests on the same flow
- Testing during atypical periods (Black Friday, holidays, major campaigns)
- Excluding mobile when 50%+ of traffic is mobile (or vice versa)
- Testing on too small a slice of traffic (low statistical power)
- Not segmenting analysis (overall lift can hide negative impact on a segment)

**Test parameters to define before launch:**

- Primary metric (one)
- Guardrail metrics (do not go down)
- Sample size
- Duration (minimum and maximum)
- Decision criteria (when to ship, when to kill, when to extend)
- Segments to analyze in addition to overall

### 4. Decide

After the test concludes.

**Decision framework:**

| Outcome | Decision |
|---|---|
| Variant clearly wins (>95% significance, exceeds minimum effect) | Ship variant. Document. Continue testing. |
| Variant clearly loses | Kill. Capture the lesson. Iterate hypothesis. |
| Inconclusive (neither significant) | Larger test, different angle, or move on. Don't ship "tied" variants. |
| Small lift, lots of variance | Probably not worth shipping. Even if "winner," may not replicate. |
| Wins overall, loses for important segment | Investigate segment. Consider segment-specific solution. |

**Anti-patterns:**

- "It looks like it's winning, ship it" before reaching significance
- Shipping a variant because the team wants to (HiPPO - highest paid person's opinion)
- Killing tests too early because they look bad
- Re-running tests until they "win" (false positive risk)
- Not capturing the learning when a test loses

---

## Statistical foundations

### Significance and confidence

A 95% significance level means: if there were truly no difference between variants, there's only a 5% chance you'd see results this extreme by chance.

That's not the same as "95% chance the variant wins."

Most CRO tools report Bayesian probabilities ("95% chance of being best"). Read the methodology your tool uses.

### Sample size

Conversion testing needs more sample than people intuit. Quick reference:

| Baseline rate | Minimum detectable effect | Sample per variant |
|---|---|---|
| 2% | 10% relative lift | ~75,000 |
| 2% | 20% relative lift | ~19,000 |
| 5% | 10% relative lift | ~30,000 |
| 5% | 20% relative lift | ~7,500 |
| 10% | 10% relative lift | ~14,000 |
| 10% | 20% relative lift | ~3,500 |

(Approximate. Use a calculator.)

If your monthly conversions per variant don't reach these numbers, A/B testing won't produce reliable results. Iterate via design and qualitative research instead.

### Multiple testing

The more variants and metrics tested simultaneously, the more false positives. Adjust significance thresholds for multiple comparisons (Bonferroni or similar).

---

## Workflow

1. **Audit.** Quantitative + qualitative + heuristic.
2. **Generate hypotheses.** From audit findings. Apply hypothesis structure.
3. **Prioritize.** ICE or PIE. Top 3 to 5 to test next.
4. **Design the test.** Sample size, duration, primary and guardrail metrics, decision criteria.
5. **Implement.** Build variants. QA carefully (broken variants invalidate tests).
6. **Run.** Don't peek. Don't stop early.
7. **Analyze.** Overall and by segment. Note interesting patterns regardless of significance.
8. **Decide.** Ship, kill, or extend.
9. **Document.** Hypothesis, design, results, decision, lesson.
10. **Compound.** Apply lessons to next round of hypotheses.

---

## Failure patterns

- **Testing without audit.** Random changes, random results.
- **Vague hypotheses.** "Make it better" is not a hypothesis.
- **Peeking and early stopping.** Bias toward false positives.
- **Underpowered tests.** Not enough sample for a real conclusion.
- **HiPPO override.** Highest paid person's opinion overrides the data.
- **Testing during atypical periods.** Holidays distort results.
- **Single metric obsession.** Conversion ups but average order value craters. Net loss.
- **No guardrail metrics.** Testing for one outcome, missing damage to others.
- **Documentation gap.** Wins captured, losses forgotten. Same hypothesis re-tested 3 times.
- **Treating each test in isolation.** Compounding learning across tests is where CRO programs really win.

---

## Output format

Default output: a markdown test plan at `cro-test-[hypothesis-slug].md` per test. After the test runs, append the results section.

Structure:

```markdown
# Test: [Hypothesis short name]

## Hypothesis
Because [observation], we believe that [change] will produce [outcome] for [segment], because [reason].

## Audit evidence
[What evidence supports this hypothesis]

## Test design
- Primary metric:
- Guardrail metrics:
- Sample size required:
- Duration: minimum X, maximum Y
- Variant traffic split:
- Segments to analyze:

## Decision criteria
- Ship if: [conditions]
- Kill if: [conditions]
- Extend if: [conditions]

## Results (filled after test)
- Sample reached:
- Duration actual:
- Primary metric: [variant vs control + significance]
- Guardrail metrics: [results]
- Segment analysis: [findings]

## Decision
[Ship / Kill / Extend / Iterate] - [Why]

## Lesson
[What this teaches us, regardless of outcome]
```

---

## If required data is unavailable

This skill's output depends on data, measurements, or tool results it cannot generate on its own. When a required input, tool, or data source is unavailable or unverifiable, the sanctioned output is the deliverable with the gap stated: what was needed, what was actually obtained or verified, and which parts of the output are affected. Fabricating, estimating, or interpolating a required number to complete the deliverable is never sanctioned. A stated gap is a complete answer.

---

## Reference files

- [`references/hypothesis-library.md`](references/hypothesis-library.md) - Common high-impact hypothesis patterns by funnel stage.

© rampstackco · MIT · rampstackco/claude-skills

Similar skills

All skills for Marketing and content →

cro-optimization by other authors comes first.

cro-optimization ognjengt cro-optimization reads a landing page, by link or as HTML/CSS, and returns a conversion audit: what blocks signups, what to fix first. CX Codex +1 1,300installs signup-flow-cro Alireza Rezvani signup-flow-cro walks your signup funnel step by step, names the worst drop-off point and suggests fixes for fields, copy and auth options. CX Codex +1 606installs page-cro OpenClaudia The page-cro skill walks an agent through a landing page audit: above the fold, forms, social proof, load speed. Useful when a page gets traffic but few conversions. CX Codex +1 520installs conversion-optimization kostja94 conversion-optimization guides conversion rate optimization, hypothesis design, and A/B test planning. Useful when users drop off during signups, checkout, or landing page visits. CX Codex +1 1,500installs conversion-rate-optimization manojbajaj95 conversion-rate-optimization audits marketing pages and capture forms, pinpoints friction, and builds test hypotheses. Use it when landing page signups stall or before launching ad campaigns. CX Codex +1 357installs growth-experimenter daffy0208 growth-experimenter runs structured A/B tests and funnel experiments across AARRR stages to improve acquisition, activation, and retention. CX Codex +1 160installs cro-methodology wondelai cro-methodology audits landing pages and funnels for conversion leaks using the CRE framework. Designs evidence-backed A/B testing hypotheses based on customer objections. CX Codex +1 6,600installs

From the same set102

The whole set →
analytics-strategy The analytics-strategy skill designs measurement frameworks: event taxonomy, KPI hierarchy, dashboard architecture, and attribution models. Use it to plan analytics from scratch or audit your existing tracking setup. CX Codex +1 309installs funnel-flow-architecture The funnel-flow-architecture skill maps funnel paths across audience segments and stages, connecting entry points to nurture sequences and offers. Use it when growth tools feel disconnected or everyone gets the same flow. CX Codex +1 309installs monitoring-and-alerting monitoring-and-alerting guides the design of web app monitoring architectures, SLO definitions, error budgets, and on-call paging policies to stop alert fatigue. CX Codex +1 308installs scheduler-and-booking-design scheduler-and-booking-design — a skill for designing booking flows that qualify leads and convert higher than a generic calendar link. Availability logic, qualification fields, routing by rep seniority, call prep automation. CX Codex +1 307installs seo-offpage The seo-offpage skill plans off-page SEO work around backlinks, digital PR, brand mentions, and citations. Use it for link audits, outreach, and authority-building plans. CX Codex +1 306installs competitor-experience-audit The competitor-experience-audit skill compares brand, UX, and site design across leading sites in a vertical. Use it to set an experience bar before building a new site. CX Codex +1 305installs ads-creative-development ads-creative-development is a Claude Code skill covering ad creative production at scale: hook patterns, video formats, variation systems, and fatigue diagnosis. CX Codex +1 303installs backup-and-disaster-recovery backup-and-disaster-recovery is a skill for Claude Code and Codex that plans backups, sets recovery targets, and runs restoration drills after outages. CX Codex +1 302installs

Project sponsors

Companies that keep this analytics open