Hypothesis 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 hypothesis-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
Formulate clear, testable hypotheses for product experiments. Use when designing experiments to validate solutions.
SKILL.md
1.5 KB, 331 tokens by cl100k_base, as published. Nobody here has run it
Product Hypothesis Design
Formulate clear, testable hypotheses for product experiments.
When to Use
When you have a product problem and need to design an experiment to validate a solution.
The Process
1. Identify the Experiment Goal
- What user problem are you addressing?
- What change do you think will help?
2. Draft Hypothesis Statement
Use this structure:
[Action] will cause [Outcome] to [Direction] for [Users] under [Conditions]
All 5 components required:
- Action: What you're doing
- Outcome: What metric changes
- Direction: Increase/decrease/improve
- Users: Who's affected
- Conditions: When/where this applies
3. Check for Specificity
- Is the action clearly defined?
- Is the outcome measurable?
- Are users and conditions specific?
4. Develop Measurement Plan
- What metrics prove success?
- How will you collect data?
- What's the sample size?
5. Narrative Check
Convert to story format:
Currently, [user] is experiencing [problem].
We believe that by [change], we'll see [outcome].
We'll know we're right when [metric] changes by [amount].
Quality Check
- Is the hypothesis falsifiable?
- Can you measure the outcome?
- Is the timeframe realistic?
- Are success criteria clear?
When Not to Use
Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.
What ships with it: 1 file
196 B alongside SKILL.md
agents/
- openai.yaml196 B