agentleFS
Sign inStart free
itseffiitseffi/agentic-os/.agents/skills/hypothesis-design/SKILL.md

hypothesis-design

Skill114 starsChanged 10 months agoMITView on GitHub

Formulate clear, testable hypotheses for product experiments. Use when designing experiments to validate solutions.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When you have a product problem and need to design an experiment to validate a solution.

    line 12
  2. Distinctive:

    Conditions: When/where this applies

    line 32
  3. Distinctive:

    Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free