pmpromptclaude-plugin-product-management340 installs on skills.sh

Trustworthy Experiments

Use when asked to "run an A/B test".

Works in any agentClaude CodeCodexCursorClaude appChatGPT+ any other agent
pmprompt/claude-plugin-product-management
Security state: reviewed

3 static scans, 0 counted findings.

Edge checks it again each time your agent loads it.

SKILL.md1 file · 2.5 KB

From the pmprompt public repository. Edge did not write or edit this skill.

What it does

  • Use when asked to "run an A/B test", "design an experiment", "check statistical significance", "trust our results", "avoid false positives", or "experiment guardrails".
  • Helps design, run, and interpret controlled experiments correctly.
  • Based on Ronny Kohavi's framework from "Trustworthy Online Controlled Experiments".

How it works

  1. 1
    Copy

    Try for free gives you one prompt.

  2. 2
    Paste

    Paste it into Claude Code, Codex or Cursor.

  3. 3
    Ask

    Ask for the outcome. Your agent loads Trustworthy Experiments.

What you can inspect

3 static scans, 0 counted findings.

Security state at 2026-09-30: reviewed. Static scans check the code, not how well the skill works.

State definitions
SKILL.md2,549 bytes · Open on GitHub

Skill details

Security scansReviewed

3 static scans, 0 counted findings. Security state at 2026-09-30: reviewed. Edge checks it again each time your agent loads it.

Edge static checks (Edge-run): edge-static/1.0.1. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Raw findings: .

Cisco skill-scanner (Edge-run): cisco-skill-scanner/2.1.0. Scope: Local static, YARA, pipeline and behavioral analyzers; no LLM or AI Defense analysis. Raw findings: 1.

Semgrep Edge rules (Edge-run): semgrep/1.178.0+edge-rules.c15016a36fd3+offline-v1. Scope: Six Edge-authored static rules with Semgrep CE; offline execution and metrics disabled. Semgrep-maintained rules excluded. Raw findings: .

Edge static checks
Pass · 0 counted findings · 2026-09-27
Cisco skill-scanner
Pass · 0 counted findings · 2026-09-27
Semgrep Edge rules
Pass · 0 counted findings · 2026-09-27
Creator, source & licencepmprompt

From the pmprompt public repository. Edge did not write or edit this skill.

Revision
3114dbe33fa2c38f781414c0b835023508db445f
Package hash
sha256:0560a1b2ef9bf53cdac8388942978c9f91611d93afc117f7ec7a8d5b5d144751
Licence
MIT
Description
Use when asked to "run an A/B test", "design an experiment", "check statistical significance", "trust our results", "avoid false positives", or "experiment guardrails". Helps design, run, and interpret controlled experiments correctly. Based on Ronny Kohavi's framework from "Trustworthy Online Controlled Experiments".
Quoted from the skill’s own description
Read skill files1 file

1 file, 2.5 KB at revision 3114dbe33fa2.

Questions about Trustworthy Experiments

What does Trustworthy Experiments do?

Use when asked to "run an A/B test". Published by pmprompt (pmprompt/claude-plugin-product-management).

Is Trustworthy Experiments safe to use?

Edge security state: Reviewed (3 Edge-run static scans, scanned Sep 30, 2026). The Evidence tab shows the scan.

How do I use Trustworthy Experiments in Claude Code, Codex or Cursor?

Click Try for free, pick your agent and follow its one step. Edge is free, with no Edge account.

Similar skills

grill-me
mattpocock

A relentless interview to sharpen a plan or design.

+39K installs this weekDesign
web-design-guidelines
vercel-labs

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX"…

+27K installs this weekDesign
high-end-visual-design
leonxlnx

tasteskill 2.5.1, the anti-slop frontend skill. Builds professional company websites at the level of figma.com and x.ai: plain copy in a voi…

Design
emil-design-eng
emilkowalski

Emil Kowalski's design-engineering philosophy for UI polish, component design, animation decisions, and the invisible details that make soft…

+23K installs this weekDesign
mcp-builder
anthropics

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design…

+3.8K installs this weekDesign
extract-design-system
arvindrk

Extract design primitives from a public website and generate starter token files for your project.

+352 installs this weekDesign
AU
post-purchase-upsell-flow
autonnel

Design and implement one-click post-purchase upsells and downsells that raise average order value without hurting the main conversion rate.…

+8.2K installs this weekDesign
hallmark
nutlope

Design skill for websites and new pages that look designed, not generated. Use when the user asks to build or design something new, or names…

+11K installs this weekDesign