Agent skill

Craft Experiment Design

by amplitude in amplitude/builder-skills

Write a hypothesis, define success metrics, and plan a holdout strategy.

No licenceAuto-check passedResearch & Science

Install Craft Experiment Design

skills CLI
$ npx skills add amplitude/builder-skills --skill craft-experiment-design -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install amplitude/builder-skills craft-experiment-design --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/amplitude/builder-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/product-skills/skills/craft-experiment-design .claude/skills/craft-experiment-design && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
craft-experiment-design
GitHub stars
160
Token cost
~522 tokens
SKILL.md length
94 words
Files
1
Skills in repo
61
Repo updated
First seen
Licence
None found

At a glance

Write a hypothesis, define success metrics, and plan a holdout strategy.

  • Designing A/B tests
  • SKILL.md covers Prompt Template and Tips
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Experiment plans

What it does

Craft Experiment Design is an agent skill from amplitude/builder-skills. Write a hypothesis, define success metrics, and plan a holdout strategy. Use when designing A/B tests or experiment plans.

Its SKILL.md is about 520 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science, covering Experimental design, A/B testing and Product metrics. The repository describes itself as: Open-source AI skills for product managers — battle-tested by PMs at Amplitude.

When your agent uses it

  • Designing A/B tests
  • Experiment plans

Example prompts

  • “/craft-experiment-design”

What it can do on your machine

Read from SKILL.md and the folder at commit 51838c2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Craft Experiment Design loads about 522 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 94 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~522

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 94 words (~522 tokens).

“Write a hypothesis, define success metrics, and plan a holdout strategy.”

— opening of SKILL.md by amplitude
name
craft-experiment-design
suggest_when
User wants to test something, says "A/B test", "experiment", "should we test this", "hypothesis", or is planning a holdout strategy for a feature launch.

Read the full SKILL.md on GitHub

Files

Just SKILL.md in product-skills/skills/craft-experiment-design of amplitude/builder-skills.

Open the folder on GitHubat commit 51838c2

Compare with similar skills

Craft Experiment Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Craft Experiment Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Craft Experiment Design this skillamplitude/builder-skills160—~522Automated safety check: PassNone
Define Hypothesisproduct-on-purpose/pm-skills715—~966Automated safety check: PassApache-2.0
Measure Experiment Designproduct-on-purpose/pm-skills715—~1.1kAutomated safety check: PassApache-2.0
Ab Testingericrisco/rsc-harness174—~2.4kAutomated safety check: PassMIT
Hypothesis Testerjeremylongshore/tons-of-skills-marketplace2.8k—~2.6kAutomated safety check: PassMIT
Experiment Designermohitagw15856/pm-claude-skills1.4k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Define Hypothesis

    product-on-purpose/pm-skills

    Defines a testable hypothesis with clear success metrics and a validation approach.

    715 GitHub stars~966 tokensUpdated yesterday
    Marketing & SEOAuto-check passed
  • Measure Experiment Design

    product-on-purpose/pm-skills

    Designs an A/B test or experiment with variants, success metrics, sample size, and duration for an existing hypothesis.

    715 GitHub stars~1.1k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Ab Testing

    ericrisco/rsc-harness

    A skill your agent uses when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading significance/CI/power, CUPED, or rescuing tests that won't go…

    174 GitHub stars~2.4k tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed
  • Hypothesis Tester

    jeremylongshore/tons-of-skills-marketplace

    Structured hypothesis formulation, experiment design, and results interpretation for Product Managers.

    2.8k GitHub stars~2.6k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Experiment Designer

    mohitagw15856/pm-claude-skills

    Design statistically rigorous A/B tests and interpret experiment results.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Data Scientist

    magnus919/hermes-profiles

    PhD-level expertise in data science, statistics, and machine learning.

    282 GitHub stars~3.3k tokensUpdated 3 mo ago
    Research & ScienceAuto-check passed

More from amplitude/builder-skills

All 61 skills in this repo
  • 7 Powers Analysis

    amplitude/builder-skills

    Analyzes a business, product or feature with Hamilton Helmer's 7 Powers framework to judge competitive advantage and how long it will last.

    160 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Amplitude Custom Agent Builder

    amplitude/builder-skills

    Helps an Amplitude user design a custom agent by proposing use cases that fit their role and data, shaping a spec, and returning a Global Agent link that builds it.

    160 GitHub stars~2.5k tokensUpdated 2 mo ago
    Auto-check passed
  • Good Strategy Bad Strategy Kernel

    amplitude/builder-skills

    Evaluates or drafts a strategy using Rumelt's kernel of diagnosis, guiding policy and coherent actions, to expose goal lists posing as strategy.

    160 GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check passed
  • High Output Management Framework

    amplitude/builder-skills

    Applies Andy Grove's High Output Management ideas to diagnose where a team loses output and to design meetings, processes and management decisions.

    160 GitHub stars~1.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Playing to Win Strategy

    amplitude/builder-skills

    Walks a team through Lafley and Martin's five-choice cascade to pin down where to compete and how to win there.

    160 GitHub stars~1.7k tokensUpdated 2 mo ago
    Auto-check passed
  • Amazon Working Backwards

    amplitude/builder-skills

    Write a PR/FAQ for a product idea using Amazon's Working Backwards process.

    160 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Craft Experiment Design

What does Craft Experiment Design do?

Write a hypothesis, define success metrics, and plan a holdout strategy. Craft Experiment Design is an agent skill from amplitude/builder-skills. Write a hypothesis, define success metrics, and plan a holdout strategy.

When should I use Craft Experiment Design?

Craft Experiment Design fits situations like: designing A/B tests; experiment plans.

How do I install Craft Experiment Design in Claude Code?

Run `npx skills add amplitude/builder-skills --skill craft-experiment-design -a claude-code`. Or copy the skill folder (product-skills/skills/craft-experiment-design in amplitude/builder-skills) into .claude/skills/craft-experiment-design in your project. Claude Code loads it when a task matches its description.

How do I install Craft Experiment Design in Codex?

Run `npx skills add amplitude/builder-skills --skill craft-experiment-design -a codex`. Or copy the skill folder (product-skills/skills/craft-experiment-design in amplitude/builder-skills) into .agents/skills/craft-experiment-design in your project. Codex loads it when a task matches its description.

Can I use Craft Experiment Design in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add amplitude/builder-skills --skill craft-experiment-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/craft-experiment-design, .gemini/skills/craft-experiment-design, .github/skills/craft-experiment-design and .opencode/skills/craft-experiment-design in your project.

What does Craft Experiment Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Craft Experiment Design is instructions for the agent only.

Does Craft Experiment Design access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Craft Experiment Design safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Craft Experiment Design use?

No licence was found for Craft Experiment Design or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Craft Experiment Design use?

About 522 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Craft Experiment Design?

Skills that share tags, products or a category with Craft Experiment Design: Define Hypothesis (product-on-purpose/pm-skills, 715 stars), Measure Experiment Design (product-on-purpose/pm-skills, 715 stars), Ab Testing (ericrisco/rsc-harness, 174 stars) and Hypothesis Tester (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Craft Experiment Design?

amplitude (a GitHub organization) maintains it in amplitude/builder-skills, which has 160 GitHub stars. The repository holds 61 skills in this directory. The repository was last updated on July 24, 2026.

Source: amplitude/builder-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.