metric-design-experimentation

metric-design-experimentation is a skill for Claude Code from Avyayalaya/pm-skills-arsenal. It costs 72 tokens per session (23,674 once invoked), scanned A, a copy of metric-design-experimentation, MIT.

A product-measurement guide for defining success, organising metrics, planning A/B tests, studying retention cohorts, and detecting misleading or manipulated metrics. A North Star metric is the main measure of product progress; A/B testing compares two versions with controlled groups.

In plain words
What is it for?
Building metric hierarchies, choosing a North Star metric, pairing growth measures with safeguards, planning statistically valid experiments, analysing retention over time, and investigating metric gaming or denominator changes.
Why use it?
Teams can mistake a rising number for real improvement, especially when users change their behaviour or the measurement method changes; this provides checks for those problems.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/sample_size_calculator.py --baseline <rate> --mde <percent> --alpha 0.05 --power 0.80 --daily-traffic <N>.

Part of the pm-skills plugin — 12 skills, 1 hook, 1 MCP server shipped together

Good fit Building metric hierarchies, choosing a North Star metric, pairing growth measures with safeguards, planning statistically valid experiments, analysing retention over time, and investigating metric gaming or denominator changes.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Avyayalaya/pm-skills-arsenal
agentmods
npx agentmods add skills/avyayalaya/pm-skills-arsenal/metric-design-experimentation

Made for: Claude Code.

Or install pm-skills, the plugin that ships this one along with the rest of its 12 skills, 1 hook, 1 MCP server.

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 metric-design-experimentation

README.md
[![agentmods](https://agentmods.dev/badge/skills/avyayalaya/pm-skills-arsenal/metric-design-experimentation/github.svg)](https://agentmods.dev/skills/avyayalaya/pm-skills-arsenal/metric-design-experimentation)
Your own site
<a href="https://agentmods.dev/skills/avyayalaya/pm-skills-arsenal/metric-design-experimentation"><img src="https://agentmods.dev/badge/skills/avyayalaya/pm-skills-arsenal/metric-design-experimentation/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 metric-design-experimentation

Your own site · 80×15
<a href="https://agentmods.dev/skills/avyayalaya/pm-skills-arsenal/metric-design-experimentation"><img src="https://agentmods.dev/badge/skills/avyayalaya/pm-skills-arsenal/metric-design-experimentation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 23,674 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.
Origin 94% copy Near-identical to another mod 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 $0.00072 $0.23674
Opus 5 $0.00036 $0.11837
Sonnet 5 $0.00014 $0.04735
Haiku 4.5 $0.00007 $0.02367

Measured 12d ago against content hash 86a699d82ff0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

metric-design-experimentation 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 12d 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

This is a copy

94% identical to metric-design-experimentation — 84 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/metric-design-experimentation/SKILL.md · 1,552 lines

How it starts

The opening of the file, as written. The whole thing — 1,552 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Purpose

Produce a complete Measurement Framework — metric hierarchy (North Star → L1 → L2 → input), leading/lagging indicator pairs with temporal lag classification, counter-metric design that resists Goodhart's Law, experiment plans with statistical validity, and retention cohort methodology. The output is not a dashboard mockup or a list of KPIs — it is a metric engineering system: instrumented to detect problems early, paired to resist gaming, and validated causally. The artifact a PM cannot produce unaided.

When to Use / When NOT to Use

Use this skill when:

  • Launching a new product or feature and need to define what success looks like before building
  • Designing an A/B test or experiment plan with proper statistical rigor
  • An existing metric feels "off" — you suspect proxy divergence, gaming, or Simpson's paradox
  • Building a metric hierarchy for a team or org (North Star → team-level → input metrics)
  • Setting up retention cohort analysis to detect PMF erosion early
  • Evaluating whether a metric improvement is real or an artifact of denominator shift

Do NOT use this skill when:

  • You need SaaS finance metric definitions (MRR, ARR, CAC, LTV formulas → use a finance metrics reference)
  • You need dashboard layout or visualization design (that's a BI/design task)
  • You need to analyze experiment results that already exist (use the computation scripts directly)
  • You need customer research methodology (→ Discovery & Research skill — that's primary research, this is measurement design)

Anti-inputs (what this skill does NOT handle):

  • Finance metric calculation formulas (→ SaaS finance reference skills)
  • Data pipeline architecture (→ engineering)
  • Dashboard UI design (→ BI tooling)
  • Customer interview design (→ Discovery & Research skill)

Example

Prompt: We're a B2B project management SaaS that just raised Series B. We have ~8,000 paying customers (60% SMB self-serve, 40% mid-market sales-assisted). Our board wants a North Star Metric. The CEO wants to use MRR. I think MRR is too lagging. Help me design the right metric framework.

Read the full file on GitHub · 1,552 lines

Files

What ships with it

2 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.

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. 12d ago First seen · 1,552 lines · 72 tokens per session scan A 86a699d82ff0

Subscribe to this mod's changes

metric-design-experimentation is a skill published in the GitHub repository Avyayalaya/pm-skills-arsenal (6 stars, last pushed 3mo ago), licensed MIT. It adds 72 tokens to every session and 23,674 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to metric-design-experimentation, differing in 84 lines, and is treated as a copy.

Related

Other skills, from other repositories

metric-design-experimentation

Use when designing a metric framework, selecting a North Star metric, building a metric decomposition tree, designing A/B experiments, setting up retention cohort analysis, or diagnosing whether a metric is being gamed. Encodes NSM rubrics, Goodhart's Law countermeasures, statistical validity for PMs, and retention…

Avyayalaya/agent-prime · 72 tokens

A/B Test Validation

Validating A/B test implementations including traffic splitting accuracy, statistical significance calculation, metric tracking, and experiment cleanup.

PramodDutta/qaskills · 27 tokens

north-star-metric-finder

Identifies a candidate North Star Metric (NSM) for a product - the single metric that captures the value the product delivers to its customers and predicts long-term business growth. Tests candidates against five criteria and surfaces input metrics that move it. Use when: north star metric, NSM, single metric that…

varunk130/ai-customer-discovery-skills · 86 tokens

product-manager

Senior PM agent with 6 knowledge domains, 30+ frameworks, 12 templates, and 32 SaaS metrics with formulas. Pure Markdown, zero scripts.

elproximoframework/Skills_Ingenieria · 36 tokens

html-ppt-zhangzara-long-table

OpenDesign's unit-economics and BYOK cost model: the assumptions, the sensitivity, and why it scales. Built as a decision-grade data & finance deck for CFO, investors.

nexu-io/open-design · 49 tokens

dummy-dataset

Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.

phuryn/pm-skills · 48 tokens