agentleFS
Adelie-SquadAdelie-Squad/solosquad/skills/prioritization/SKILL.md

prioritization

Skill25 starsChanged 8 days agoMITView on GitHub

9 framework (RICE/ICE/Kano/Opportunity Score/MoSCoW/Weighted/Eisenhower/Value-vs-Effort/Cost-of-Delay) 비교 후 컨텍스트 맞춤 selection + 계산.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Prioritization Skill

9 Framework 매트릭스

Framework형식적용 컨텍스트
RICE(Reach × Impact × Confidence) / Effort분기 로드맵, 기능 우선순위
ICE(Impact + Confidence + Ease) / 3빠른 직관 비교, ≤10 후보
KanoMust-have / Performance / Excitement / Indifferent / Reverse신규 기능 분류
Opportunity ScoreImportance × (1 - Satisfaction)Discovery 단계, unmet need
MoSCoWMust / Should / Could / Won'tRelease 단위 분류
WeightedΣ (weight × score)다기준 의사결정 (technical + business)
EisenhowerUrgent × Important 2×2Solo founder 일정
Value vs Effort2×2 matrixquick wins 식별
Cost of Delay$$ / week의존성 / 시간민감 작업

Framework 선택 가이드 (post-labeling)

PM 이 후보 framework 를 직접 처방하지 않고, 컨텍스트에서 어떤 분류가 자연스러운지 식별:

  • 후보가 N≥20 → RICE
  • 후보가 N≤10 + 빠른 비교 → ICE
  • discovery 단계, unmet need 발굴 → Opportunity Score
  • release scope 결정 → MoSCoW
  • 신규 vs 기존 mix → Kano
  • 시간 민감 / 의존성 → Cost of Delay

계산 예시 (RICE)

candidates:
  - title: "feature A"
    reach: 1000        # 분기 영향 사용자 수
    impact: 2          # 0.25 / 0.5 / 1 / 2 / 3 scale
    confidence: 0.7    # 0-1
    effort: 2          # person-month
    rice_score: 700    # (1000 * 2 * 0.7) / 2

  - title: "feature B"
    reach: 500
    impact: 3
    confidence: 0.5
    effort: 1
    rice_score: 750

출력

{
  "framework_used": "RICE",
  "framework_rationale": "후보 23개 → RICE 적합",
  "ranked": [
    { "id": "feature-B", "score": 750, "rank": 1 },
    { "id": "feature-A", "score": 700, "rank": 2 }
  ],
  "recommended": ["feature-B"],
  "deferred": ["feature-X"]
}

Anti-Sycophancy

  • ❌ "feature B 가 더 좋아 보입니다"
  • ✅ "feature B 가 RICE 750 으로 1위. effort < 2 인 조건에서. effort 가 1.5 이상으로 재추정되면 feature A 가 1위로 역전."

Reference

  • phuryn/pm-skills/pm-execution/prioritization-frameworks (9 framework)
  • Intercom RICE framework
  • Kano model

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.