From armory
Assesses business ideas for technical feasibility and financial viability via unit economics (CAC, LTV), revenue modeling, break-even analysis, and go/no-go verdicts.
npx claudepluginhub mathews-tom/armory --plugin armoryThis skill uses the workspace's default tool permissions.
Evaluate business ideas and features across two tracks: financial viability and technical feasibility. Produce an integrated verdict with actionable de-risking recommendations.
Implements Playwright E2E testing patterns: Page Object Model, test organization, configuration, reporters, artifacts, and CI/CD integration for stable suites.
Guides Next.js 16+ Turbopack for faster dev via incremental bundling, FS caching, and HMR; covers webpack comparison, bundle analysis, and production builds.
Discovers and evaluates Laravel packages via LaraPlugins.io MCP. Searches by keyword/feature, filters by health score, Laravel/PHP compatibility; fetches details, metrics, and version history.
Evaluate business ideas and features across two tracks: financial viability and technical feasibility. Produce an integrated verdict with actionable de-risking recommendations.
Determine the input type:
Extract from the input:
If critical inputs are missing, ask targeted clarifying questions before proceeding. Minimum viable inputs: value proposition and target customer.
Reference: references/unit-economics.md, references/financial-viability.md
Skip this phase only when the request is purely technical (e.g., "can we build X with Y stack").
State every assumption explicitly. Flag assumptions with high sensitivity (small change flips the outcome).
Reference: references/technical-risk.md
Skip this phase only when the request is purely financial (e.g., "are the unit economics viable for a SaaS at $29/mo").
Classify complexity:
| Level | Description | Examples |
|---|---|---|
| 1 — Simple | Standard CRUD, single service | Landing page, basic CMS, form-based app |
| 2 — Moderate | Multi-service integration, auth, payments | E-commerce, SaaS dashboard, API platform |
| 3 — Complex | Distributed systems, real-time, high availability | Marketplace, streaming platform, fintech |
| 4 — Novel | R&D required, unproven at scale | ML-driven product, novel protocol, hardware+software |
Evaluate:
Score each dimension 1-5 (1 = low risk, 5 = critical risk):
| Dimension | What It Measures |
|---|---|
| Technical novelty | Proven tech (1) vs active R&D required (5) |
| Integration complexity | Self-contained (1) vs many external APIs (5) |
| Scale readiness | Architecture handles 100x with config changes (1) vs requires re-architecture (5) |
| Data risk | Public/owned data, no regulation (1) vs restricted data, heavy compliance (5) |
| Security/compliance | No sensitive data (1) vs PCI/HIPAA/SOC2 required (5) |
Composite technical risk = weighted average. Flag any dimension scoring 4+ as a blocker requiring mitigation plan.
| Financial | Technical | Verdict |
|---|---|---|
| Viable | Straightforward | Green — proceed |
| Viable | Challenging | Yellow — proceed with caution, mitigate tech risks |
| Risky | Straightforward | Yellow — validate financial assumptions first |
| Risky | Challenging | Yellow — high uncertainty, run cheap experiments |
| Not viable | Any | Red — reconsider fundamentals |
| Any | High-risk/Research | Red — reduce technical unknowns before committing |
Identify the top 3-5 assumptions that most influence the verdict. For each, state:
Rank experiments by cost-to-run vs information-value. Prioritize experiments that validate the riskiest assumptions at the lowest cost.
Structure the output as: