Skip to content
TrustedSkillsbeta
Back to all skills

Trustworthy Experiments

Checked
pmprompt·vlatest·other·MIT

This skill guides you to design and execute reliable experiments by prioritizing factual accuracy and minimizing bias for robust results.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add pmprompt/claude-plugin-product-management --skill trustworthy-experiments -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

pmprompt

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned pmprompt/claude-plugin-product-management at 3114dbe33f.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
3114dbe33f
Manifest
skills/trustworthy-experiments/SKILL.md
Scanned
1 file, 56 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

Trustworthy Experiments is a framework designed to guide you through running controlled experiments (A/B tests) that yield reliable and actionable results. It addresses common pitfalls in experimentation, aiming to minimize false positives and ensure the validity of findings. The skill draws on industry best practices and insights from experts like Ronny Kohavi, who has identified significant rates of experiment failure and invalid results due to factors like sample ratio mismatch.

When to use it

  • Designing A/B tests for product features or improvements.
  • Calculating appropriate sample sizes and experiment runtime for statistical power.
  • Validating the results of experiments before making decisions about implementation.
  • Diagnosing unexpected or suspicious experimental outcomes (Twyman's Law).
  • Selecting metrics that balance short-term gains with long-term value (OEC).

Key capabilities

  • Provides a framework for designing and executing reliable A/B tests.
  • Helps determine appropriate sample sizes and experiment duration.
  • Offers guidance on validating experimental results to avoid false positives.
  • Addresses the importance of choosing balanced metrics (OEC).
  • Supports diagnosing issues with experiment outcomes using Twyman's Law.

Example prompts

  • "Help me design an A/B test for [feature name] and determine the necessary sample size."
  • "I ran an experiment on [metric], but the results seem suspicious. Can you help me diagnose what might be wrong?"
  • "What metrics should I use to evaluate the success of [product change]?"

Tips & gotchas

  • Requires a sufficient user base (tens of thousands minimum) for valid results.
  • Controlled experiments are not appropriate for one-time decisions or situations lacking user choice.
  • Experiments require time; they aren't suitable for immediate decision-making.