experiment-designer SKILL.md skillA

experiment-designer from rizwanzafaris/product-manager-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rizwanzafaris/product-manager-os/experiment-designer@git:20260919.72235e0

Pins git:20260919.72235e0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
rizwanzafaris/product-manager-os
Path
skills/experiment-designer/SKILL.md
Versions recorded
2
Latest version
git:20260919.72235e0, committed Sep 19, 2026
First version recorded
Sep 3, 2026
Size
10,601 bytes
Repository stars
4
License
MIT

Turn an assumption or a growth bet into an experiment brief with a mechanism-stated hypothesis, one primary metric, guardrails with floors, an exposure design, a sample size reasoned from the minimum detectable effect, and stop rules written before launch. Use when a growth plan bet needs a test, when an assumption register row is low confidence and high impact, when a price change should be tried on a slice first, or when someone says "let us just A/B it". Takes the assumption, the metric…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Experiment Designer: a test that can fail, sized before it runs

Experiments fail before they start. The hypothesis has a direction and no mechanism, the metric is chosen after the data arrives, the sample size is a guess, someone peeks on day three, and a "win" ships that quietly hurt retention. This skill writes the decision rule while everyone is still ignorant of the result, and sizes the test from the effect that would change the decision rather than the effect the team hopes for.

## Files this skill drives

- [../../templates/operate/experiment-brief.md](../../templates/operate/experiment-brief.md), every section
- [../../frameworks/discovery/assumption-mapping.md](../../frameworks/discovery/assumption-mapping.md), the test card before and the learning card after (Bland and Osterwalder, Testing Business Ideas, 2019)
- [../../templates/definition/assumptions-register.md](../../templates/definition/assumptions-register.md), the row under test, moved to TESTING
- [../../templates/planning/growth-plan.md](../../templates/planning/growth-plan.md), the bet it serves and the ledger row it ends in
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rizwanzafaris/product-manager-os/experiment-designer@sha256:20f735499c400baf

The line at the top of this page pins the label git:20260919.72235e0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_66c3dy2mk4bnfqqw.svg)](https://markdownregistry.com/a/art_66c3dy2mk4bnfqqw)

6 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Sep 3, 2026 and Sep 19, 2026, about one every 16 days.

versioncommittedcommitsizeaudit
git:20260919.72235e0 latest2026-09-19 72235e0 10,601 BA view · diff
git:20260903.a2ef42e2026-09-03 a2ef42e 8,906 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (10601 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

rizwanzafaris/product-manager-os · 4 stars · license MIT · pushed 2026-11-04 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_66c3dy2mk4bnfqqw
GET https://markdownregistry.com/api/v1/resolve?ref=rizwanzafaris/product-manager-os/experiment-designer
GET https://markdownregistry.com/api/v1/blob/20f735499c400baf2c5ccaf8a5ee79084d861ba2715ffef041247345ca850306

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from rizwanzafaris/product-manager-os

AGENTS.md AGENTS.md file
rizwanzafaris/product-manager-os · AGENTS.md
git:20260914.e52221a · audit A · 4 stars
CLAUDE.md CLAUDE.md file
rizwanzafaris/product-manager-os · CLAUDE.md
git:20260915.2a64226 · audit A · 4 stars
tutor SKILL.md skill
rizwanzafaris/product-manager-os · learn/skills/tutor/SKILL.md · Teaching-posture reuse of the Conductor's question machinery for deliberate practice on fictional products. Use when a…
git:20260911.61cbcf4 · audit A · 4 stars
regulated-ai-prd SKILL.md skill
rizwanzafaris/product-manager-os · modules/regulated/SKILL.md · Write and pressure-test a PRD for an AI or agentic system. Use when a product manager is specifying a feature where the…
git:20260901.4d78d32 · audit A · 4 stars
ai-prd SKILL.md skill
rizwanzafaris/product-manager-os · skills/ai-prd/SKILL.md · Write and pressure-test a PRD for an AI or agentic system. Use when a product manager is specifying a feature where the…
git:20260919.72235e0 · audit A · 4 stars
competitive-intel SKILL.md skill
rizwanzafaris/product-manager-os · skills/competitive-intel/SKILL.md · Produce a sourced competitor teardown (offer, pricing, positioning, gaps) where every claim carries a URL and a date…
git:20260919.72235e0 · audit A · 4 stars
conductor SKILL.md skill
rizwanzafaris/product-manager-os · skills/conductor/SKILL.md · Interview-driven operation of the six-stage product loop. Use when a user says "start" on a new product, "resume" or…
git:20260921.9fa707d · audit A · 4 stars
decision-memo SKILL.md skill
rizwanzafaris/product-manager-os · skills/decision-memo/SKILL.md · Write a decision memo a decider can act on in one read: the situation, the options priced, the door type, one…
git:20260921.2bf6847 · audit A · 4 stars
design-review SKILL.md skill
rizwanzafaris/product-manager-os · skills/design-review/SKILL.md · Run a design critique prep, a Gate 3 design review, a live-build design check before Gate 4, or an accessibility…
git:20260919.72235e0 · audit A · 4 stars
escalation SKILL.md skill
rizwanzafaris/product-manager-os · skills/escalation/SKILL.md · Turn a stuck decision or a blocked dependency into a one-page brief (Situation, Impact, Urgency, Options…
git:20260919.72235e0 · audit A · 4 stars
feedback-synthesis SKILL.md skill
rizwanzafaris/product-manager-os · skills/feedback-synthesis/SKILL.md · Turn a pile of raw customer feedback into evidence-weighted themes that land in the discovery templates. Use when a PM…
git:20260919.72235e0 · audit A · 4 stars
gtm-launch-planner SKILL.md skill
rizwanzafaris/product-manager-os · skills/gtm-launch-planner/SKILL.md · Tier a launch, choose the first cohort, build the channel plan, and draft the comms and readiness lines so Gate 5 finds…
git:20260919.72235e0 · audit A · 4 stars

Every file in rizwanzafaris/product-manager-os

Other files named experiment-designer

experiment-designer SKILL.md skill
alirezarezvani/claude-skills · .gemini/skills/experiment-designer/SKILL.md
git:20260509.0c7d19d · audit C · 29,490 stars
experiment-designer SKILL.md skill
mohitagw15856/pm-claude-skills · plugins/pm-advanced/skills/experiment-designer/SKILL.md · Design statistically rigorous A/B tests and interpret experiment results. Use when asked to design an experiment, run…
git:20261011.d31ce81 · audit A · 1,475 stars

Browse by kind, by grade A, or by owner.