Skip to main content
skill CX Codex

experiment-design · microsoft — Claude Code skill for experiment design and MVE

experiment-design — a reference pack for running experiments: turning unknowns into testable hypotheses, screening out non-experiments, and keeping scope tight enough for decision-ready results.

CC-BY-4.0 ★ 1,627 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add microsoft/hve-core --skill experiment-design -a claude-code
Open on GitHub

What experiment-design does

The skill walks through the whole experiment lifecycle. Unknowns become testable hypotheses, demos and mini-MVPs get called out instead of being run as experiments, and scope stays minimum-but-sufficient.

Five reference files sit inside. problem-framing.md maps a business outcome to data-science problem classes, mve-coaching.md handles Minimum Viable Experiment work, experiment-readiness.md helps pick which experiment to run at all, and rpi-research-preparation.md covers experiments with bounded prior art. provenance.md marks what is upstream guidance and what is a repository convention.

Problem-class framing exposes candidates but never picks one. Experiment work assumes a direction already exists and ends with the team choosing. It applies beyond data science: architecture, LLM, performance, UX, prototyping, and hardware experiments all fit.

Installation is a single npx command in Claude Code; the skill lands at ~/.claude/skills/experiment-design/SKILL.md.

What it helps with

  • map a business outcome to data-science problem classes
  • name demos and mini-MVPs instead of running them as experiments
  • pick the experiment whose result changes the most downstream work
  • record every input precisely enough for another person to repeat the run
  • shape a falsifiable hypothesis tied to a stated rationale

Example prompts for the agent

  • Frame our business outcome into candidate data-science problem classes and show the entry-test reasoning for each.
  • Coach us through a Minimum Viable Experiment for the direction we already chose.
  • Read experiment-readiness.md and help us pick which experiment to run from our candidate list.

How to install experiment-design

1Skills CLI (Vercel)

npx skills add microsoft/hve-core --skill experiment-design -a claude-code

2Manually: put the files in place

~/.claude/skills/experiment-design/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/experiment-design/

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

Questions about experiment-design

How do I install experiment-design in Claude Code?

Run npx skills add microsoft/hve-core --skill experiment-design -a claude-code. The skill lands at ~/.claude/skills/experiment-design/SKILL.md.

What does experiment-design do?

It is a reference pack for experiment work: framing business outcomes into data-science problem classes, forming and vetting hypotheses, choosing which experiment to run, and preparing it for reproducible execution.

Which kinds of experiments does it cover?

Data feasibility, architecture, LLM, performance, use-case, UX, prototyping, and hardware. Not just data science.

How does problem-class framing differ from experiment framing?

Problem-class framing asks what kind of problem you have. Experiment framing asks what to test about a direction already chosen. The skill keeps the two separate and does not apply experiment vetting to a framing request.

Source text

SKILL.md · CC-BY-4.0
---
name: experiment-design
description: "Experiment design reference for problem-class framing, Minimum Viable Experiment coaching, hypothesis formation, vetting and red flags, and experiment readiness. Use when translating a stated business outcome into candidate data-science problem classes, or when framing, vetting, scoping, or evaluating an experiment of any kind, including data feasibility, architecture, LLM, performance, use-case, UX, prototyping, and hardware experiments."
license: CC-BY-4.0
user-invocable: false
metadata:
  authors: "Microsoft (MVE coaching synthesis); Microsoft (Code With Engineering Playbook); Google LLC (machine-learning problem framing)"
  spec_version: "1.1"
  last_updated: "2026-09-18"
  content_based_on: "HVE Core original MVE coaching material; HVE Core original cross-paradigm routing; https://microsoft.github.io/code-with-engineering-playbook/design/design-reviews/recipes/engineering-feasibility-spikes/; https://microsoft.github.io/code-with-engineering-playbook/design/design-reviews/trade-studies/; https://developers.google.com/machine-learning/problem-framing/problem; https://developers.google.com/machine-learning/guides/rules-of-ml"
---

# Experiment Design Reference Pack

## Goal

Support experiment work end to end: turning unknowns into testable hypotheses, screening out work that is not a real experiment, and scoping it so the result is comparable and decision-ready.

Support the step that precedes it as well: translating a stated business outcome into candidate data-science problem classes with the reasoning that produced them, so a practitioner knows what kind of problem is on the table before deciding what to test.

The two concerns stay distinct. Problem-class framing exposes candidates and never selects one. Experiment work assumes a candidate direction already exists and concludes by selecting an experiment with the team.

This pack is general purpose. It applies to data feasibility, architecture, LLM, performance, use-case, UX, prototyping, and hardware experiments, not to data science alone.

## Inputs

* The problem statement, customer context, and business driver
* The stated business outcome, when the active concern is problem-class framing
* Known unknowns, assumptions, and risks
* The decision the experiment is meant to unblock
* Prior experiment results, when a sequence of experiments is in flight

## Reference index

Read only the reference that matches the active concern.

| Reference                                                             | Read this when                                                                                                                                                                             |
|-----------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| [problem-framing.md](references/problem-framing.md)                   | Translating a stated business outcome into candidate data-science problem classes, applying per-paradigm entry tests, ordering discriminating questions, or recording assignable gaps      |
| [mve-coaching.md](references/mve-coaching.md)                         | Framing an MVE, forming or sharpening hypotheses, applying vetting criteria and red flags, designing the experiment, evaluating results, or producing session and backlog-bridge artifacts |
| [experiment-readiness.md](references/experiment-readiness.md)         | Deciding which experiment to run at all: turning a risk landscape into candidates, prioritizing among competing unknowns, comparing options with evidence, or re-prioritizing mid-flight   |
| [rpi-research-preparation.md](references/rpi-research-preparation.md) | Preparing an experiment with bounded prior-art or current-constraint Research while keeping validation and experiment verdicts with their current owners                                   |
| [provenance.md](references/provenance.md)                             | Confirming what is upstream guidance, what is HVE Core derivation or repository convention, and where upstream is silent                                                                   |

A confirmed problem-class framing request reads [problem-framing.md](references/problem-framing.md) only. Experiment requests read [mve-coaching.md](references/mve-coaching.md) or [experiment-readiness.md](references/experiment-readiness.md) by concern.

## Success criteria

* Problem-class framing returns the surviving candidate problem classes with the entry-test reasoning that kept or discarded each one, and never returns a selection, a ranking, or a confidence score.
* Every framing claim is visibly either a cited entry test or repository-original routing, and no claim implies that a universal external standard governs cross-paradigm routing.
* An unanswered framing question becomes a recorded gap with an answer holder and a coordinator, and the remaining analysis continues.
* Each hypothesis is testable, specific, falsifiable, and tied to a stated rationale.
* The experiment selected is the one whose result changes the most downstream work, chosen from a candidate list rather than from the first idea proposed.
* Work that is a demo, a mini-MVP, or an already-answered question is named as such rather than run as an experiment.
* Every input that could change the result is recorded precisely enough that another person could repeat the experiment and get a comparable answer. An identifier without a version is a label, not a reproducible reference.
* Experiment scope stays minimum-but-sufficient, and experiment code is treated as disposable.

## Constraints

* Reproduce only the minimum text necessary for a specific technical point, and paraphrase everything else. Attribute every reference and describe accurately what each reference reproduces.
* Label repository conventions as substitutions rather than upstream recommendations.
* Keep experiment framing separate from experiment infrastructure. This pack decides whether and how an experiment is worth running; it does not stand up tooling.
* Keep problem-class framing separate from experiment framing. Problem-class framing asks what kind of problem this is; experiment framing asks what to test about a direction already chosen. Do not apply experiment vetting criteria, red flags, or readiness prioritization to a confirmed problem-class framing request.
* Never rank, score, threshold, or recommend a candidate problem class. The practitioner is the subject-matter expert who chooses.

## Ownership boundaries

| Concern                                                                                                                              | Owner                                                                              |
|--------------------------------------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------|
| Candidate problem classes for a stated business outcome, entry-test reasoning, discriminating questions, and assignable framing gaps | This pack, through [problem-framing.md](references/problem-framing.md)             |
| Whether a proposed outcome is achievable with available data and evidence                                                            | `feasibility`, the evidence-led feasibility study reference                        |
| MVE session directory, artifact filenames, placement, and tracking-file hygiene                                                      | `experiment-designer.instructions.md`, applied automatically to MVE tracking paths |
| Phase order, gates, session writes, and coaching flow                                                                                | The consuming experiment agent                                                     |
| ML environments, reproducibility, tracking, model evaluation, abstractions, and readiness                                            | `ml-experimentation`, the ML-specific experimentation reference                    |
| Pipeline mechanics, data tiering, replay, validation, and DS/MLOps test technique                                                    | `dataops`, the DataOps and testing reference                                       |
| Metric names, instruments, units, cardinality, and PII-safe telemetry                                                                | `telemetry-foundations`, the OpenTelemetry-aligned instrumentation skill           |
| Data sensitivity classification and DPIA thresholds                                                                                  | `privacy-standards`, the privacy classification reference                          |

## Stop rules

* For a confirmed problem-class framing request, an unstated business outcome is the sole stop before candidate analysis. [problem-framing.md](references/problem-framing.md) owns that stop and its job-specific exceptions. The experiment stop rules below govern experiment requests only.
* Stop and name the red flag when the request is a demo, a scaled-down product build, or a question already answered elsewhere. Then offer either the falsifiable hypothesis hiding underneath it or an explicit non-experiment path, rather than halting on the refusal.
* Stop and separate concerns when the request is production implementation rather than experiment design.
* Stop and state the gap when the request depends on guidance this pack does not provide, such as a universal framework, tool, or metric choice made without project context.

## Attribution

This pack declares `CC-BY-4.0`.

[mve-coaching.md](references/mve-coaching.md) is repository-original content under CC BY 4.0. It is not derived from any upstream source and cites no upstream URL.

[problem-framing.md](references/problem-framing.md) layers three source treatments. Its machine-learning entry tests are informed by Google for Developers machine-learning guidance, licensed CC BY 4.0; that material is paraphrased and reorganized, both upstream URLs are cited, and changes are stated. It points readers to the NEOS Guide for optimization problem types as a citation only, and states no NEOS classification of its own. Its cross-paradigm routing, the broader analytical-fit judgement, and the gap and output contract are repository-original.

[experiment-readiness.md](references/experiment-readiness.md) is HVE Core guidance informed by two Microsoft CSE Code With Engineering Playbook documentation pages, which are licensed CC BY 4.0. It paraphrases rather than reproduces, generalizes the upstream practices beyond engagement-shaped engineering work, cites both upstream URLs, and states that changes were made.

See [provenance.md](references/provenance.md) for the consolidated source map and derivation labels.

© microsoft · CC-BY-4.0 · microsoft/hve-core

Similar skills

All skills for Agent setup: memory, context, orchestration →

experiment-design by other authors comes first.

experiment-design lingzhi227 experiment-design is a Claude Code skill that turns research ideas into staged experiments with baselines, datasets, metrics, and ablations. It supports planning experiments for a paper. CX Codex +1 1,800installs experiment-design rampstackco experiment-design is a skill for designing A/B tests, multivariate experiments, and holdouts so results answer the question being asked. CX Codex +1 285installs experiment-design Yeachan-Heo experiment-design is a Claude Code skill that collects practices for reproducible experiments, from seeding to pre-registering an analysis plan. It supports runs and A/B tests another person must rerun. CX Codex +1 1installs paper-reading-experiment-design franklee16 The paper-reading-experiment-design skill turns a research method’s claims into an experiment plan, covering evidence, metrics, baselines, and checks. Use it once the method has a clear thesis and target. CX Codex +1 ★ 240repo stars paper-planning EvoScientist paper-planning — a skill that plans an academic paper before writing starts: story, experiments, figures and a 4-week timeline. CX Codex +1 434installs power-analysis gaasher power-analysis is a Claude Code skill for sizing a two-group study and drafting its preregistration. It runs during planning, before data collection, for A/B tests, simple RCTs, and evaluations of two models or configurations. CX Codex +1 ★ 185repo stars research-data-analysis hanhuark research-data-analysis gives the agent a routine for baseline cases, hypothesis-driven DOE and plots that show uncertainty. Built for engineering experiments and simulations. CX Codex +1 ★ 26repo stars experiment-bridge wanshuiyin experiment-bridge is a Claude Code skill that turns an experiment plan into code, runs it on a GPU, and collects first results for auto-review. CX Codex +1 555installs scientific-thinking Agents365-ai scientific-thinking is a skill for analyzing research findings, evaluating evidence, and constructing rigorous arguments. It separates facts from interpretations and calibrates conclusions to evidence quality. CX Codex +1 308installs

From the same set148

The whole set →
Jira Backlog Executor Jira Backlog Executor executes a dispatched set of Jira changes or returns query results for one confirmed project. It checks the project binding before mutations. CX Codex +1 ★ 1,627repo stars Accessibility Reviewer Accessibility Reviewer is a Claude Code subagent that profiles the repo, runs WCAG 2.2 and ARIA APG checks, verifies findings, and writes an audit report. CX Codex +1 ★ 1,627repo stars rpi-plan-critique rpi-plan-critique is a Claude Code skill that independently reviews RPI implementation plans without editing them, checking task credibility against supplied evidence before coding begins. CX Codex +1 ★ 1,627repo stars DT Learning Tutor DT Learning Tutor — a tutor subagent that walks you through Design Thinking: nine methods, comprehension checks between modules, pacing that follows your level. CX Codex +1 ★ 1,627repo stars video-to-gif video-to-gif converts video clips into optimized animated GIFs using two-pass FFmpeg palette generation. Useful for crafting UI demos and docs previews directly inside the CLI. CX Codex +1 ★ 1,627repo stars powershell This rule sets conventions for PowerShell scripts, modules, and data files. Claude Code applies them to .ps1, .psm1, and .psd1 files. CX Codex +1 ★ 1,627repo stars PowerPoint Subagent PowerPoint Subagent executes PowerPoint operations: extracts slide content to YAML, builds decks from YAML and styles, validates quality using vision checks. Use it to automate presentation creation in Claude Code. CX Codex +1 ★ 1,627repo stars hve-slides hve-slides is a Claude Code skill for creating, updating, and auditing interactive HTML presentations in HVE Core, with presenter controls and keyboard navigation. CX Codex +1 ★ 1,627repo stars

Project sponsors

Companies that keep this analytics open