- name
SKILL.md
스킬 파일은 게시자의 저장소에 그대로 있습니다.
복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add deanpeters/Product-Manager-Skills --skill epic-hypothesis -a cursor -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add deanpeters/Product-Manager-Skills --skill epic-hypothesis -a claude-code -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add deanpeters/Product-Manager-Skills --skill epic-hypothesis -a codex -y복사한 명령을 터미널에 붙여넣습니다. 이 SKILL.md가 해당 에이전트에 설치됩니다.
npx skills add deanpeters/Product-Manager-Skills --skill epic-hypothesis -a grok -y복사한 메시지를 Grok Bot 채팅에 보냅니다. Bot이 GitHub에서 이 SKILL.md를 가져와 모든 Bot이 공유하는 스킬에 추가합니다.
Install this skill: https://github.com/deanpeters/Product-Manager-Skills/tree/HEAD/plugins/pm-define/skills/epic-hypothesis게시자 제공
Frame epics as testable hypotheses using an if/then structure that articulates the action or solution, the target beneficiary, the expected outcome, and how you'll validate success. Use this to manage uncertainty in product development by making assumptions explicit, defining lightweight experiments ("tiny acts of discovery"), and establishing measurable success criteria before committing to full build-out.
This is not a requirements spec—it's a hypothesis you're testing, not a feature you're committed to shipping.
Works best with: The initiative or epic idea, in whatever form it currently exists — a sentence is enough. Also useful: The target user, the outcome you expect, and how you might measure it (the skill helps you sharpen all three).
Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended ARGUMENTS: line — counts as answers already given. Use it and skip whatever it covers; don't re-ask.
Arriving empty-handed? That works too. The skill asks what the initiative is and who it's for, then builds the if/then hypothesis with you.
Example invocation: Frame as an epic hypothesis: adding usage-based alerts so account admins catch overages before invoice shock.
Inspired by Tim Herbig's Lean UX hypothesis format, the structure is:
If/Then Hypothesis:
Tiny Acts of Discovery Experiments:
Validation Measures:
Use template.md for the full fill-in structure.
Before drafting an epic hypothesis, ensure you have:
skills/problem-statement/SKILL.md)skills/proto-persona/SKILL.md)skills/jobs-to-be-done/SKILL.md)If missing context: Run discovery interviews or problem validation work first.
Fill in the template:
### If/Then Hypothesis
**If we** [action or solution on behalf of the target persona]
**for** [target persona]
**Then we will** [attain or achieve a desirable outcome or job-to-be-done for the persona]
Quality checks:
skills/proto-persona/SKILL.md)Examples:
Before building the full epic, define lightweight experiments to test the hypothesis:
### Tiny Acts of Discovery Experiments
**We will test our assumption by:**
- [Experiment 1: low-cost, fast test]
- [Experiment 2: another low-cost, fast test]
- [Add more as necessary]
Experiment types:
Quality checks:
Examples:
Specify what success looks like and the timeframe for evaluation:
### Validation Measures
**We know our hypothesis is valid if within** [timeframe in days or weeks]
**we observe:**
- [Desirable quantitative, measurable outcome]
- [Desirable qualitative, measurable outcome]
- [Add more as necessary]
Quality checks:
Examples:
Once the hypothesis is validated, break the epic into user stories:
### Epic: [Epic Name]
**Stories:**
1. [User Story 1 - reference `skills/user-story/SKILL.md`]
2. [User Story 2]
3. [User Story 3]
See examples/sample.md for full epic hypothesis examples.
Mini example excerpt:
**If we** provide one-click Google Calendar integration
**for** trial users managing multiple meetings
**Then we will** increase activation rate from 40% to 50%
Symptom: "If we build a dashboard, then we will have a dashboard"
Consequence: You're describing output, not outcome. This doesn't test anything.
Fix: Focus on the user outcome: "If we build a dashboard showing real-time task status, then PMs will spend 50% less time asking for status updates."
Symptom: "We'll test our assumption by building the full feature"
Consequence: You've committed to building before validating. Not a hypothesis—it's a feature commitment.
Fix: Design lightweight experiments (prototypes, concierge tests, landing pages) that take days/weeks, not months.
Symptom: "We know it's valid if users are happy"
Consequence: Success criteria are subjective and unmeasurable.
Fix: Define specific, falsifiable metrics: "80% of surveyed users rate the feature 4+ out of 5" or "Response time drops by 50%."
Symptom: "We know it's valid if within 6 months revenue increases"
Consequence: Too slow to inform decisions. By then, you've already built it.
Fix: Aim for 2-4 week validation cycles. If you can't measure in that timeframe, choose a leading indicator (e.g., activation rate, not annual revenue).
Symptom: "We already told the CEO we're shipping this, so we have to validate it"
Consequence: Experiments are theater—you're going to build it regardless of results.
Fix: Frame epics as hypotheses before making commitments. If stakeholders need certainty, explain the risk of building unvalidated features.
skills/problem-statement/SKILL.md — Hypothesis should address a validated problemskills/proto-persona/SKILL.md — Defines the "for [persona]" sectionskills/jobs-to-be-done/SKILL.md — Informs the "then we will" outcomeskills/user-story/SKILL.md — Validated epics decompose into user storiesskills/user-story-splitting/SKILL.md — How to break validated epics into storiesprompts/backlog-epic-hypothesis.md in the https://github.com/deanpeters/product-manager-prompts repo.Skill type: Component
Suggested filename: epic-hypothesis.md
Suggested placement: /skills/components/
Dependencies: References skills/problem-statement/SKILL.md, skills/proto-persona/SKILL.md, skills/jobs-to-be-done/SKILL.md
Used by: skills/user-story/SKILL.md, skills/user-story-splitting/SKILL.md
Frame an epic as a testable hypothesis with target user, expected outcome, and validation method. Use when defining a major initiative before roadmap, discovery, or delivery planning.
---name: epic-hypothesisdescription: Frame an epic as a testable hypothesis with target user, expected outcome, and validation method. Use when…---# plugins/pm-define/skills/epic-hypothesis/SKILL.mdFAQ
게시자에게서 plugins/pm-define/skills/epic-hypothesis/SKILL.md를 다운로드하거나 경로를 복사해 저장소를 엽니다. PlugMCP는 스킬을 목록에 올릴 뿐 파일을 호스팅하지 않습니다.
게시자가 https://github.com/deanpeters/Product-Manager-Skills에서 관리합니다.
Claude, Cursor, Codex, Grok Build는 게시자의 저장소에서 추가한 SKILL.md를 읽을 수 있습니다. Grok Bot은 채팅에서 스킬의 GitHub 폴더 링크를 보내면 설치합니다.