agentsclimarketplace

App discovery scrutiny

Skill JPeetz/agent-skills/app-discovery-scrutiny

The definitive collection of cross-platform Agent Skills. Compatible with Claude Code, Codex, Cursor, OpenClaw, Gemini CLI, Copilot, Hermes. Curated weekly. Higher quality than any alternative.

Install
npx -y skills add JPeetz/agent-skills --skill app-discovery-scrutiny

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use this skill when the user wants to evaluate a mobile app idea for commercial viability — whether it's a clone opportunity, a market gap, or a new launch. Produces a harsh "Build / Pivot / Kill" verdict backed by competitive analysis and revenue modeling. Use when the user says things like "Is this app idea worth building?" "Should I clone this?" "Analyze this niche" "Evaluate this competitor" even if they don't use the word "scrutiny" or "dominance report." Mobile apps only — do not activate for CLI tools, SDKs, or SaaS.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.3 KB, as published. Nobody here has run it

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: market_signal (0.20), competition_gap (0.20), seo_aso (0.20), monetization (0.20), urgency (0.10), mobile_first (0.10 with 6/10 kill floor). Run as: echo '{"candidates":[...]}' | python3 scripts/score.py

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.