ab-test-analysis

ab-test-analysis is a skill for Claude Code from phuryn/pm-skills. It costs 54 tokens per session (879 once invoked), scanned A, original, MIT.

A skill for evaluating A/B tests, experiments that compare two versions of something to see which performs better. It checks sample size, test setup, statistical significance, confidence ranges, and the decision to ship, extend, or stop.

In plain words
What is it for?
Use it to analyze conversion results or uploaded experiment data, validate test duration and randomization, calculate significance and lift, and decide what to do next.
Why use it?
A result that looks better can be caused by too little data, a badly run test, or random variation. This skill checks those issues before turning the result into a product decision.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the pm-data-analytics plugin — 3 skills, 3 commands shipped together

Good fit Use it to analyze conversion results or uploaded experiment data, validate test duration and randomization, calculate significance and lift, and decide what to do next.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/phuryn/pm-skills/ab-test-analysis
About the project

phuryn/pm-skills is a marketplace of reusable skills, commands, and plugins that guide AI assistants through product-management work such as discovery, strategy, planning, metrics, launches, and growth. It is for product managers and teams using Claude Code, Cowork, or compatible assistants. The catalogue entries are the project's own workflows and extensions.

phuryn/pm-skills · 26,097 stars · on GitHub · productcompass.pm

Install

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.

Any agent
npx skills add phuryn/pm-skills --skill ab-test-analysis
Clone the repo
git clone --depth 1 https://github.com/phuryn/pm-skills

Made for: Claude Code.

Or install pm-data-analytics, the plugin that ships this one along with the rest of its 3 skills, 3 commands.

Wrote 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.

agentmods badge for ab-test-analysis

README.md
[![agentmods](https://agentmods.dev/badge/skills/phuryn/pm-skills/ab-test-analysis/github.svg)](https://agentmods.dev/skills/phuryn/pm-skills/ab-test-analysis)
Your own site
<a href="https://agentmods.dev/skills/phuryn/pm-skills/ab-test-analysis"><img src="https://agentmods.dev/badge/skills/phuryn/pm-skills/ab-test-analysis/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ab-test-analysis

Your own site · 80×15
<a href="https://agentmods.dev/skills/phuryn/pm-skills/ab-test-analysis"><img src="https://agentmods.dev/badge/skills/phuryn/pm-skills/ab-test-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 879 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk pass 4 Mar 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium analysis-evasion · line 1
    Suspicious Unicode normalization or mixed-script content
    Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.00879
Opus 5 $0.00027 $0.00439
Sonnet 5 $0.00011 $0.00176
Haiku 4.5 $0.00005 $0.00088

Measured 9d ago against content hash 9956966671d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ab-test-analysis 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 9d 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.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

pm-data-analytics/skills/ab-test-analysis/SKILL.md · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A/B Test Analysis

Evaluate A/B test results with statistical rigor and translate findings into clear product decisions.

Context

You are analyzing A/B test results for $ARGUMENTS.

If the user provides data files (CSV, Excel, or analytics exports), read and analyze them directly. Generate Python scripts for statistical calculations when needed.

Instructions

  1. Understand the experiment:

    • What was the hypothesis?
    • What was changed (the variant)?
    • What is the primary metric? Any guardrail metrics?
    • How long did the test run?
    • What is the traffic split?
  2. Validate the test setup:

    • Sample size: Is the sample large enough for the expected effect size?
      • Use the formula: n = (Z²α/2 × 2 × p × (1-p)) / MDE²
      • Flag if the test is underpowered (<80% power)
    • Duration: Did the test run for at least 1-2 full business cycles?
    • Randomization: Any evidence of sample ratio mismatch (SRM)?
    • Novelty/primacy effects: Was there enough time to wash out initial behavior changes?
  3. Calculate statistical significance:

    • Conversion rate for control and variant
    • Relative lift: (variant - control) / control × 100
    • p-value: Using a two-tailed z-test or chi-squared test
    • Confidence interval: 95% CI for the difference
    • Statistical significance: Is p < 0.05?
    • Practical significance: Is the lift meaningful for the business?

    If the user provides raw data, generate and run a Python script to calculate these.

  4. Check guardrail metrics:

    • Did any guardrail metrics (revenue, engagement, page load time) degrade?
    • A winning primary metric with degraded guardrails may not be a true win
  5. Interpret results:

    Outcome Recommendation
    Significant positive lift, no guardrail issues Ship it — roll out to 100%
    Significant positive lift, guardrail concerns Investigate — understand trade-offs before shipping
    Not significant, positive trend Extend the test — need more data or larger effect
    Not significant, flat Stop the test — no meaningful difference detected
    Significant negative lift Don't ship — revert to control, analyze why

Read the full file on GitHub · 83 lines

Changes

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.

  1. 9d ago First seen · 83 lines · 54 tokens per session scan A 9956966671d6

Subscribe to this mod's changes

ab-test-analysis is a skill published in the GitHub repository phuryn/pm-skills (26,097 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 879 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

pmm-resume

Resume reviewer and tailoring engine for Product Marketing Managers (IC to VP, including AI PMM roles). Takes baseline resume + job description → dissects JD → ranks bullets by impact fit → rebuilds complete resume in one pass. Trigger on: resume + JD paste, "tailor this", "which bullets for this role", "rebuild for…

stefanoskarakasis/Product-Marketing-Skills · 103 tokens

beachhead-segment

Identifies and scores your highest-priority beachhead segment using four-dimension scoring (Burning Pain, Willingness to Pay, Winnability, Referral Potential) with blocking gates. Reads brain context (ICP, positioning, competitive landscape, proof points) and, when available, guardrails from prior beachhead decisions…

stefanoskarakasis/Product-Marketing-Skills · 88 tokens

prd

Guides Product Managers and Product Marketing Managers to co-create complete Product Requirements Documents with embedded Solution Stories. Reads brain context (positioning, ICP, Revenue Levers) to anchor PRDs in strategy. Outputs: structured Solution Story for GTM communications + full PRD for execution alignment.

stefanoskarakasis/Product-Marketing-Skills · 59 tokens

pre-mortem

Identifies and pressure-tests failure modes for any strategic initiative (product launch, pricing change, GTM pivot, new market entry, feature rollout) by running a cross-functional risk exercise. Loads brain context (ICP, positioning, competitive landscape) and, when available, guardrails from prior pre-mortems…

stefanoskarakasis/Product-Marketing-Skills · 82 tokens

prioritization-frameworks

Selects and applies the right prioritization framework (9 frameworks: Opportunity Score, ICE, RICE, Eisenhower, Impact vs Effort, Risk vs Reward, Kano, Weighted Decision Matrix, MoSCoW) with PMM interpretation layer and GTM launch tier output (T1–T4). Reads brain context (ICP, positioning, revenue levers) and, when…

stefanoskarakasis/Product-Marketing-Skills · 92 tokens

retro

Structured GTM retrospective for cross-functional squads anchored to OKRs and launch outcomes. Produces diagnostic root causes and actionable decisions, not venting. Loads brain context and, when available, guardrails from prior sessions logged in the user's own workspace. Use for post-launch reviews, GTM cycle…

stefanoskarakasis/Product-Marketing-Skills · 85 tokens