Experiment Design
Design concrete assumption tests using prototypes, demand tests or commitment tests. Use when turning research or selected ideas into experiments, comparing test methods or revising an experiment plan.
Install
/plugin marketplace add superhero-tech/superhero-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add superhero-tech/superhero-skills --skill experiment-designgit clone --depth 1 https://github.com/superhero-tech/superhero-skills.git /tmp/superhero-skills
mkdir -p ~/.claude/skills
cp -r /tmp/superhero-skills/plugins/product-discovery/skills/product-discovery/experiment-design ~/.claude/skills/experiment-designPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Experiment Design Turn research or selected concepts into a runnable experiment plan. Choose the method by the assumption and the decision it can inform. Respond and produce all artifacts in the user's conversation language. Use natural, descriptive language for titles as well as explanations. Before naming or summarizing tests, read `references/writing-quality.md`. Keep participant-facing copy separate from research terminology. ## Explain the experiment first Explain each experiment through five short, self-contained blocks, translated into the user's language. Keep the first three as the plain-language core: 1. **Hypothesis:** the person's problem and why a specific product change should lead to a desired behavior or outcome. Keep the broader product hypothesis distinct from the assumption this test can examine. 2. **Experiment:** what changes in practice, for whom, at which point in the product or service, using which method. Include the actual action or offer, such as button text. Explain any proposed feature before using shorthand like "the card" or an internal ID. 3. **Observable change:** what behavior should change, in which direction, for whom and how it will be observed. Define the measure, comparison or denominator and relevant context/window. Do not imply an increase from an unknown baseline.
Details
- Skill name
experiment-design- Repository
- superhero-tech/superhero-skills
- Path
plugins/product-discovery/skills/product-discovery/experiment-design/SKILL.md- License
- MIT
- Repo updated
- 13 November 2026
FAQ
What does the Experiment Design skill do?
Design concrete assumption tests using prototypes, demand tests or commitment tests. Use when turning research or selected ideas into experiments, comparing test methods or revising an experiment plan.
How do I install the Experiment Design skill?
Claude Code plugin: /plugin marketplace add superhero-tech/superhero-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Experiment Design popular?
It lives in superhero-tech/superhero-skills, which has 298 GitHub stars and 25 forks.
Related skills
Ab Test Design
298superhero-tech/superhero-skills
Design an A/B test and decide whether available traffic can detect a useful effect. Use when planning a randomized product comparison, checking sample size or test duration, or creating an interactive A/B test card.
Affinity Mapping
298superhero-tech/superhero-skills
Synthesize interview transcripts into evidenced themes and user needs, then render an interactive HTML evidence map. Use when synthesizing interviews, affinity mapping, or preparing opportunities for discovery.
Build Figma Library
298superhero-tech/superhero-skills
Build or extend a Figma token and component library from product documentation, code, or an existing UI. Prepare it for another agent by checking component properties, composition examples, and handoff, including publishing when reuse spans files. Use for reconstructing design systems and making libraries reusable; screen-only design and documentation of existing components have separate workflows.
Fix Flaky Tests
280intercom/2x-skills
Investigate and fix flaky or intermittently-failing tests in any framework and CI system — detects the framework, CI provider, and app profile, then applies the matching classification and fix patterns. Triggers on a flaky-test issue or CI URL, a test that "passes on retry" or "fails in CI but passes locally", a bot that skipped a test, or a request to reopen or dispute the closure or diagnosis of a flaky-test issue (for that case open the issue first; its title or label confirms scope even when the prompt has no flaky-test keywords).
Databricks Synthetic Data Gen
407databricks/databricks-agent-skills
Generate realistic synthetic data using Spark + Faker (strongly recommended). Supports serverless execution, multiple output formats (Parquet/JSON/CSV/Delta), and scales from thousands to millions of rows. For small datasets (<10K rows), can optionally generate locally and upload to volumes. Use when user mentions 'synthetic data', 'test data', 'generate data', 'demo dataset', 'Faker', or 'sample data'.
Performance Testing Review Multi Agent Review
514Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
Use when working with performance testing review multi agent review
Browse the most popular Claude skills, all testing & qa skills, or write your own with the skills generator.