hypothesis-tree

Structure complex questions into MECE testable hypotheses for product analysis.

Updated Apr 29, 2026
One-click install
npx skills add https://github.com/dev-khoi/AURA-conHack-2026 --skill hypothesis-tree-dev-khoi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: hypothesis-tree
Source: https://github.com/dev-khoi/AURA-conHack-2026/tree/main/.opencode/skills/hypothesis-tree
Command: npx skills add https://github.com/dev-khoi/AURA-conHack-2026 --skill hypothesis-tree-dev-khoi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Ambiguous product questions like "why is growth slow" or "why is churn rising" are hard to act on without structure. This Skill decomposes vague concerns into a MECE hypothesis tree so teams can prioritize and test explanations systematically instead of guessing. ## Core Features & Use Cases - Structured Decomposition: Converts vague concerns into specific, measurable questions and breaks them into mutually exclusive, collectively exhaustive hypothesis branches. - Prioritization Framework: Scores hypotheses by available evidence, test effort, and impact to decide what to test first. - Output Templates: Provides ready-to-use hypothesis tree diagrams, testing plans, and evidence summary tables. - Use Case: Investigating why signup conversion dropped below 30% by branching into awareness, ability, motivation, and technical hypotheses, then ranking which to validate first. ## Quick Start Ask the AI to build a hypothesis tree for why your feature adoption is below target and produce a prioritized testing plan.

Frequently Asked Questions about hypothesis-tree

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I structure a hypothesis tree for a product problem?▼

Start by framing a specific measurable question, then brainstorm first-level hypotheses organized to be mutually exclusive and collectively exhaustive. Decompose each branch until hypotheses are directly testable, usually within three levels.

What makes a good hypothesis in product analysis?▼

A strong hypothesis is specific, testable, falsifiable, and actionable. It should state a measurable claim like "checkout abandonment is above 70% on mobile" with clear criteria for being proven wrong and a decision tied to each outcome.

What does MECE mean in hypothesis trees?▼

MECE stands for Mutually Exclusive, Collectively Exhaustive. Branches must not overlap with each other, and together they must cover all possible explanations, such as splitting users into new versus returning rather than vague overlapping groups.

How do I prioritize which hypotheses to test first?▼

Score each hypothesis on available evidence, test effort, and impact if true. Prioritize hypotheses with high impact, low testing effort, and little existing evidence, then record them in a testing plan with method, timeline, and owner.

When should I use a hypothesis tree versus Five Whys?▼

Use a hypothesis tree when you need broad MECE coverage of an ambiguous question with multiple possible causes. Use Five Whys to drill deep into a single confirmed hypothesis; the two methods complement each other.