agentleFS
Adelie-SquadAdelie-Squad/solosquad/skills/hypothesis-design/SKILL.md

hypothesis-design

Skill25 starsChanged 9 days agoMITView on GitHub

XYZ hypothesis + If-Then-Because + V/U/V/F assumption 분류. PM 자체 reasoning. ≥2 approaches 비교 강제.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Hypothesis Design Skill

XYZ Hypothesis

[X%] of [Y segment] will [Z behavior] within [T period], because [R rationale]

상세 schema 는 skills/problem-definition/assets/05-xyz-hypothesis.md 참조 (cross-reference).

If-Then-Because

If [intervention] is delivered to [segment]
Then [measurable result] within [period]
Because [causal mechanism]

XYZ 보다 가벼운 형식. early-stage exploration 시 사용.

V/U/V/F Assumption Classifier

각 가설의 핵심 가정을 4 카테고리로 분류 후 위험도 평가:

카테고리질문위험 시 검증 방법
Value사용자가 이 변화로 가치를 얻는가?concierge MVP, fake door
Usability사용자가 발견/사용 가능한가?usability test, prototype
Viability비즈니스 / 운영 가능한가?financial model, capacity check
Feasibility기술적으로 가능한가?technical spike, prototype

가장 risky assumption 부터 experiment 우선순위 결정.

≥ 2 approaches 룰

hypotheses:
  - id: h1
    xyz: "..."
    pros: [...]
    cons: [...]
    v_u_v_f_risk: { v: high, u: low, v2: low, f: low }
  - id: h2
    xyz: "..."
    pros: [...]
    cons: [...]
    v_u_v_f_risk: { v: low, u: high, v2: low, f: medium }
recommended: h1
recommendation_rationale: "h1 의 V 위험이 더 testable. h1 fail 시 h2 로 pivot."

HARD GATE: hypothesis → experiment-design 진입 조건

  • ≥2 hypotheses 비교
  • 각 hypothesis 의 V/U/V/F risk 평가
  • recommended + falsification 명시
  • confidence ≥ 60

Reference

  • RO-PNA XYZ format
  • David Bland "Testing Business Ideas" — V/U/V/F (V=Value, U=Usability, V=Viability, F=Feasibility)
  • gstack approaches ≥2 rule

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.