Experiment design
Agentic personal OS to automate high-leverage workflows with Codex, Claude Code, Pi, OpenClaw and other coding agents/ runtime platforms.
npx -y skills add itseffi/agentic-os --skill experiment-designAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Design robust experiments to test product hypotheses. Define metrics, sample size, and success criteria.
SKILL.md
1.5 KB, as published. Nobody here has run it
Experiment Design
Design robust experiments to test product hypotheses.
When to Use
When you have a hypothesis and need to design an experiment to validate it.
The Process
1. Factor Breakdown
Analyze your goal and system:
- What factors could influence the outcome?
- Which are controllable vs. environmental?
- What are the key variables?
2. Experiment Structure
For each factor, define:
- Hypothesis: What you expect to happen
- Independent variable: What you're changing
- Dependent variable: What you're measuring
- Control group: Baseline comparison
- Experimental group: Who gets the change
- Measurement method: How you'll collect data
- Confounding variables: What else could affect results
3. Sample Design
- Who participates?
- How many needed for statistical significance?
- How will you recruit/select?
4. Timeline
- How long to run?
- When to check results?
- What's the minimum detectable effect?
5. Stop/Scale Rules
- What results mean "stop"?
- What results mean "scale"?
- What's inconclusive?
Output Format
For each experiment:
- Hypothesis statement
- Variables (independent, dependent)
- Groups (control, experimental)
- Sample size and selection
- Measurement approach
- Success criteria
- Stop/scale rules
When Not to Use
Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.