사용 방법
- 설치 명령을 복사하고 자신의 에이전트 환경에 설치하기 전에 소스 패키지를 확인하세요.
- 필요한 도구, 인증 정보, 지원 환경은 원본 문서에서 확인하세요.
- 입력과 원하는 산출물을 설명하고 출처와 결과를 대조하세요.
npx skills add https://github.com/jpeetz/agent-skills --skill app-discovery-scrutiny시작 전 확인
- 설치에는 모델 구독, API 한도, 파일 접근 권한이 포함되지 않습니다.
- 별점 수와 설치 수는 활동 지표이며 독립적인 품질·보안 검증이 아닙니다.
원본 Skill 문서
원본 저장소의 제목, 예시, 코드, 표, 링크, 이미지를 유지해 표시합니다.
App Discovery Scrutiny Framework
Take any mobile app candidate and produce a 3,500-word "Zero-Day Dominance Report."
Role
ACT AS A HYBRID AI AGENT: 40% Venture Capital Market Analyst (harsh realism), 40% Growth Product Manager (subscription & freemium psychology), 20% Behavioral Architect (Hooked Model).
Input Required
- TARGET NICHE: [APP NAME] – [ONE-LINE DESCRIPTION]
- The Problem: [what pain does this niche solve?]
- The Solution: [app description, features, pricing model]
- How to Make Money: [pricing tiers, revenue model]
Output — 5 Sections
Section 1: Demand & Saturation
- Latent Demand Score (1-10) with social listening data
- Market Saturation Index: Blue/Growing/Crowded/Bloodbath
- Subscription Viability: Aspirin vs Vitamin test. Would users pay $9.99/mo?
Section 2: Overtake Strategy
- Competitor Feature Matrix: Top 3 competitors
- 3 table-stakes features you MUST copy
- 2 Blue Ocean Innovations (novel AI/behavioral features incumbents can't copy)
- Killer Differentiation: one sentence — the app's Irresistible Mechanism
Section 3: Revenue & Success Evaluation
- MRR at 5K and 50K paying users (factor 95% Y1 churn)
- Unit Economics: Max CAC, LTV for 6-month breakeven, The Cliff (sub count for profit after 30% fees)
- Freemium Conversion: exact paywall friction point
Section 4: Scaffolding Prompt
- 200-word prompt to generate Full Technical Spec & PRD
- Include: DB schema, subscription logic (RevenueCat/Stripe), Hooked Model triggers, 30-day MVP scope
Section 5: X-Factors
- #1 churn reason + cancellation flow intercept
- Regulatory/Legal risks (GDPR, HIPAA, App Store, FTC)
- Trojan Horse acquisition strategy (no paid ads)
Output Format
Markdown tables for feature comparison. Bold all numbers/percentages. End with: Final Verdict: Build / Pivot / Kill.
Rules
- Be brutal. Assume 70% of startups fail on monetization.
- Do not be optimistic without evidence.
- Every recommendation must cite at least one external source or market signal.
- Mobile apps only. Reject CLI tools, SDKs, desktop-only, SaaS without mobile companion.
- Before scoring, read
references/corrections.md— it documents real failures from prior runs (mobile vs CLI mistake, SEO kill-floor bias, research verification gaps). - Use live web_search — if research fails, flag it rather than inferring silently.
Available scripts
- `scripts/score.py` — Weighted scoring engine with kill-floor elimination. Pipe candidate JSON to it, get ranked results with pass/fail per dimension. Uses 6-dimension framework: marketsignal (0.20), competitiongap (0.20), seoaso (0.20), monetization (0.20), urgency (0.10), mobilefirst (0.10 with 6/10 kill floor). Run as:
echo '{"candidates":[...]}' | python3 scripts/score.py
