Agent skill

Feasibility Assessor

by Mathews-Tom in Mathews-Tom/armory

Evaluates whether a business idea is technically buildable and financially viable.

MITAuto-check passedBusiness, Finance & HR

Install Feasibility Assessor

skills CLI
$ npx skills add Mathews-Tom/armory --skill feasibility-assessor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Mathews-Tom/armory feasibility-assessor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Mathews-Tom/armory.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/feasibility-assessor .claude/skills/feasibility-assessor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
feasibility-assessor
GitHub stars
329
Token cost
~2.1k tokens
SKILL.md length
872 words
Files
5 (incl. references)
Skills in repo
80
Repo updated
First seen
Licence
MIT

At a glance

Evaluates whether a business idea is technically buildable and financially viable.

  • Works in 5 steps: Input Classification → Financial Analysis → Technical Analysis → …
  • : feasibility assessment
  • SKILL.md covers Phase 1: Input Classification, Phase 2: Financial Analysis, Phase 3: Technical Analysis and Phase 4: Integrated…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Feasibility Assessor is an agent skill from Mathews-Tom/armory. Evaluates whether a business idea is technically buildable and financially viable. Covers unit economics (CAC, LTV), revenue modeling, break-even, and go/no-go verdicts. Triggers on: "feasibility assessment", "viability analysis", "unit economics", "build vs buy", "go/no-go decision", "ROI projection".

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `evals/cases.yaml`, `references/financial-viability.md` and `references/technical-risk.md`).

It sits in Business, Finance & HR, covering Financial modeling and Feature launches and release readiness. The repository describes itself as: Curated, production-grade skills for AI coding agents. Battle-tested workflows for developers who use AI seriously. The licence is MIT.

When your agent uses it

  • : feasibility assessment
  • Viability analysis
  • Go/no-go decision

Example prompts

  • “feasibility assessment”
  • “viability analysis”
  • “unit economics”
  • “/feasibility-assessor”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Input Classification
  2. Financial Analysis
  3. Technical Analysis
  4. Integrated Feasibility Score
  5. Report Generation

What it can do on your machine

Read from SKILL.md and the folder at commit 4594fb7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Feasibility Assessor loads about 2.1k tokens when it runs, and up to ~9k if it reads all its reference files. Until then it costs about 81 tokens; SKILL.md has 872 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Mathews-Tom/armory at commit 4594fb7, republished under its MIT licence (© Mathews-Tom). 872 words, ~2,114 tokens.

Download SKILL.mdSave it as .claude/skills/feasibility-assessor/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
feasibility-assessor
description
Evaluates whether a business idea is technically buildable and financially viable. Covers unit economics (CAC, LTV), revenue modeling, break-even, and go/no-go verdicts. Triggers on: "feasibility assessment", "viability analysis", "unit economics", "build vs buy", "go/no-go decision", "ROI projection".
metadata.version
1.0.1
metadata.category
review
metadata.tags
feasibility, unit-economics, viability, business-case
metadata.difficulty
advanced
metadata.phase
define

Feasibility Assessor

Evaluate business ideas and features across two tracks: financial viability and technical feasibility. Produce an integrated verdict with actionable de-risking recommendations.

Phase 1: Input Classification

Determine the input type:

  • Idea pitch: informal description of a concept
  • Feature spec: defined requirements for a product addition
  • Repo/codebase: existing code to evaluate for extension or pivot
  • Business plan: structured document with financials

Extract from the input:

  1. Value proposition (what problem it solves, for whom)
  2. Target customer segment
  3. Pricing intent or revenue model
  4. Technology stack (stated or implied)
  5. Competitive landscape awareness

If critical inputs are missing, ask targeted clarifying questions before proceeding. Minimum viable inputs: value proposition and target customer.

Phase 2: Financial Analysis

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").

Unit Economics
  1. Calculate Customer Acquisition Cost (CAC) — fully loaded: marketing spend + sales cost + overhead allocation per acquired customer
  2. Calculate Customer Lifetime Value (LTV) — ARPU multiplied by average customer lifetime, adjusted for gross margin
  3. Compute LTV:CAC ratio — minimum viable: 3:1
  4. Determine contribution margin per unit sold or per customer served
  5. Calculate payback period — months until cumulative gross profit from a customer exceeds CAC

State every assumption explicitly. Flag assumptions with high sensitivity (small change flips the outcome).

Revenue Modeling
  1. Identify all revenue streams and size each one
  2. Assess pricing strategy fit: cost-plus, value-based, competitive, freemium-to-paid
  3. Apply conversion rate assumptions — use industry benchmarks from reference material
  4. Model churn and retention — apply cohort decay curves where possible
Break-Even Analysis
  1. Separate fixed costs (rent, salaries, infrastructure baseline) from variable costs (COGS, transaction fees, support per user)
  2. Calculate break-even point in units, customers, or revenue
  3. Model three scenarios:
    • Pessimistic: 50th percentile conversion, high churn, slow growth
    • Base: industry-average assumptions
    • Optimistic: top-quartile performance
Path to Profitability
  1. Project gross margin trajectory over 12-24 months
  2. Model operating expense scaling (linear vs step-function vs economies of scale)
  3. Estimate funding requirements and runway at current burn
  4. Compare against industry benchmarks for time-to-profitability

Phase 3: Technical Analysis

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").

Architecture Assessment

Classify complexity:

LevelDescriptionExamples
1 — SimpleStandard CRUD, single serviceLanding page, basic CMS, form-based app
2 — ModerateMulti-service integration, auth, paymentsE-commerce, SaaS dashboard, API platform
3 — ComplexDistributed systems, real-time, high availabilityMarketplace, streaming platform, fintech
4 — NovelR&D required, unproven at scaleML-driven product, novel protocol, hardware+software

Evaluate:

  • Technology stack maturity and ecosystem support
  • Infrastructure requirements and cost scaling curve
  • Third-party dependency count and criticality
Build Estimation
  1. Define MVP scope — the minimum feature set that tests the core value proposition
  2. Estimate development timelines:
    • Optimistic: experienced team, known stack, minimal unknowns
    • Realistic: standard team, some learning curve, normal blockers
    • Pessimistic: new domain, integration challenges, regulatory overhead
  3. Identify required team skills and availability
  4. Run build vs buy vs partner analysis for each major component
Show full SKILL.md (367 more words)Show less
Risk Scoring

Score each dimension 1-5 (1 = low risk, 5 = critical risk):

DimensionWhat It Measures
Technical noveltyProven tech (1) vs active R&D required (5)
Integration complexitySelf-contained (1) vs many external APIs (5)
Scale readinessArchitecture handles 100x with config changes (1) vs requires re-architecture (5)
Data riskPublic/owned data, no regulation (1) vs restricted data, heavy compliance (5)
Security/complianceNo 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.

Phase 4: Integrated Feasibility Score

Financial Viability
  • Viable: LTV:CAC > 3:1, payback < 18 months, clear path to positive unit economics
  • Risky: LTV:CAC 1.5-3:1, payback 18-36 months, unit economics depend on scale
  • Not viable: LTV:CAC < 1.5:1, payback > 36 months, negative contribution margin
Technical Feasibility
  • Straightforward: complexity level 1-2, all risk dimensions < 3
  • Challenging: complexity level 2-3, one or two dimensions at 3-4
  • High-risk: complexity level 3-4, multiple dimensions at 4+
  • Research-grade: complexity level 4, any dimension at 5
Overall Verdict
FinancialTechnicalVerdict
ViableStraightforwardGreen — proceed
ViableChallengingYellow — proceed with caution, mitigate tech risks
RiskyStraightforwardYellow — validate financial assumptions first
RiskyChallengingYellow — high uncertainty, run cheap experiments
Not viableAnyRed — reconsider fundamentals
AnyHigh-risk/ResearchRed — reduce technical unknowns before committing
Assumption Sensitivity

Identify the top 3-5 assumptions that most influence the verdict. For each, state:

  • Current assumed value
  • Threshold value that would flip the assessment
  • How to validate cheaply
De-risking Recommendations

Rank experiments by cost-to-run vs information-value. Prioritize experiments that validate the riskiest assumptions at the lowest cost.

Phase 5: Report Generation

Structure the output as:

Executive Summary
  • One-paragraph verdict with go/no-go signal
  • Top 3 risks and top 3 strengths
Financial Dashboard (if applicable)
  • Unit economics table: CAC, LTV, LTV:CAC, contribution margin, payback period
  • Revenue projection under 3 scenarios (table or description)
  • Break-even point and timeline
Technical Scorecard (if applicable)
  • Complexity classification
  • Risk dimension scores (table)
  • MVP scope and timeline estimate
  • Critical dependencies and mitigation
Sensitivity Analysis
  • Which assumptions, if wrong, flip the verdict
  • Threshold values for each critical assumption
  • Ordered list of actions, cheapest validation first
  • Clear owners or skill requirements for each step
  • Decision gates: what evidence triggers proceed vs pivot vs stop

© Mathews-Tom, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in skills/feasibility-assessor of Mathews-Tom/armory.

  • SKILL.md
  • evals/cases.yaml
  • references/financial-viability.md
  • references/technical-risk.md
  • references/unit-economics.md

Open the folder on GitHubat commit 4594fb7

Compare with similar skills

Feasibility Assessor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Feasibility Assessor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Feasibility Assessor this skillMathews-Tom/armory329—~2.1kAutomated safety check: PassMIT
Creating Financial ModelsChen-zexi/open-ptc-agent7293 repos~1.3kAutomated safety check: PassMIT
Equity ResearchrollingSirius/equity-research-skill453—~1.5kAutomated safety check: PassMIT
SaaS Metrics Coachrongxinzy/RongxinAI1542 repos~1.3kAutomated safety check: PassMIT
Startup Financial Modelingnicepkg/auto-company19511 repos~2.8kAutomated safety check: PassNone
Stock Value AnalyzerFunnyKun/stock-value-analyzer141—~3.3kAutomated safety check: PassNone

Similar skills

  • Creating Financial Models

    Chen-zexi/open-ptc-agent

    This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions

    729 GitHub starsUsed in 3 repos~1.3k tokens
    Business, Finance & HRAuto-check passed
  • Equity Research

    rollingSirius/equity-research-skill

    撰写机构级个股投资研究报告(二级市场深度研究)。Use whenever the user wants to research, analyze, or value a specific publicly-traded stock — e.g.

    453 GitHub stars~1.5k tokensUpdated 1 mo ago
    Business, Finance & HRAuto-check passed
  • SaaS Metrics Coach

    rongxinzy/RongxinAI

    SaaS financial health advisor. An agent skill from rongxinzy/RongxinAI.

    154 GitHub starsUsed in 2 repos~1.3k tokens
    Business, Finance & HRAuto-check passed
  • Startup Financial Modeling

    nicepkg/auto-company

    This skill should be used when the user asks to "create financial projections", "build a financial model", "forecast revenue", "calculate burn rate", "estimate runway", "model cash flow", or…

    195 GitHub starsUsed in 11 repos~2.8k tokens
    Business, Finance & HRAuto-check passed
  • Stock Value Analyzer

    FunnyKun/stock-value-analyzer

    基于邱国鹭《投资中最简单的事》方法论的股票价值分析器(v2.0 双层架构)。通过"三好原则"(好行业、好公司、好价格)系统评估一只股票是否值得投资。v2.0 在原定性框架之上注入一套可量化、可复现的硬模型层——反向 DCF 反解市场隐含增速、情景概率加权估值、EPV 盈利能力价值、分行业估值路由、杜邦三/五因子分解、ROIC vs WACC、Piotroski F-Score、Beneish…

    141 GitHub stars~3.3k tokensUpdated 3 mo ago
    Business, Finance & HRAuto-check passed
  • Dcf Valuation

    edinetdb/dexter-jp

    Performs discounted cash flow (DCF) valuation analysis to estimate intrinsic value per share for Japanese listed companies.

    312 GitHub stars~1.1k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed

More from Mathews-Tom/armory

All 80 skills in this repo
  • Architecture Reviewer

    Mathews-Tom/armory

    Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) with scored reports.

    329 GitHub stars~4.6k tokensUpdated 4 days ago
    Auto-check passed
  • Concept To Image

    Mathews-Tom/armory

    Turn concepts into static HTML visuals exported as PNG or SVG files via HTML/CSS/SVG.

    329 GitHub stars~2.6k tokensUpdated 4 days ago
    Auto-check passed
  • Watch

    Mathews-Tom/armory

    A skill your agent uses when analyzing an existing video URL or local recording: "watch this video", "analyze youtube video", "summarize this video", "youtube transcript", "find this moment", "what…

    329 GitHub stars~2.8k tokensUpdated 4 days ago
    Auto-check passed
  • Code Refiner

    Mathews-Tom/armory

    Deep code simplification and refactoring preserving behavior across Python, Go, TypeScript, Rust.

    329 GitHub stars~3.1k tokensUpdated 4 days ago
    Auto-check passed
  • Concept To Video

    Mathews-Tom/armory

    Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition.

    329 GitHub stars~4.9k tokensUpdated 4 days ago
    Auto-check passed
  • Decision Map

    Mathews-Tom/armory

    Maps the unresolved architecture, policy, and scope decisions that must be answered before planning can start: one durable decision ticket per question on the issue tracker, typed and blocker-linked…

    329 GitHub stars~2.7k tokensUpdated 4 days ago
    Auto-check passed

Questions about Feasibility Assessor

What does Feasibility Assessor do?

Evaluates whether a business idea is technically buildable and financially viable. Feasibility Assessor is an agent skill from Mathews-Tom/armory. Evaluates whether a business idea is technically buildable and financially viable.

When should I use Feasibility Assessor?

Feasibility Assessor fits situations like: : feasibility assessment; viability analysis; go/no-go decision.

How do I install Feasibility Assessor in Claude Code?

Run `npx skills add Mathews-Tom/armory --skill feasibility-assessor -a claude-code`. Or copy the skill folder (skills/feasibility-assessor in Mathews-Tom/armory) into .claude/skills/feasibility-assessor in your project. Claude Code loads it when a task matches its description.

How do I install Feasibility Assessor in Codex?

Run `npx skills add Mathews-Tom/armory --skill feasibility-assessor -a codex`. Or copy the skill folder (skills/feasibility-assessor in Mathews-Tom/armory) into .agents/skills/feasibility-assessor in your project. Codex loads it when a task matches its description.

Can I use Feasibility Assessor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Mathews-Tom/armory --skill feasibility-assessor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feasibility-assessor, .gemini/skills/feasibility-assessor, .github/skills/feasibility-assessor and .opencode/skills/feasibility-assessor in your project.

What does Feasibility Assessor need to run?

SKILL.md names no scripts, command-line tools or credentials: Feasibility Assessor is instructions for the agent only.

Does Feasibility Assessor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Feasibility Assessor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Feasibility Assessor use?

Feasibility Assessor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Feasibility Assessor use?

About 2.1k tokens (SKILL.md is roughly 8.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.9k tokens, read only when the agent opens those files.

What are the alternatives to Feasibility Assessor?

Skills that share tags, products or a category with Feasibility Assessor: Creating Financial Models (Chen-zexi/open-ptc-agent, 729 stars), Equity Research (rollingSirius/equity-research-skill, 453 stars), SaaS Metrics Coach (rongxinzy/RongxinAI, 154 stars) and Startup Financial Modeling (nicepkg/auto-company, 195 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Feasibility Assessor?

Mathews-Tom (a GitHub user) maintains it in Mathews-Tom/armory, which has 329 GitHub stars. The repository holds 80 skills in this directory. The repository was last updated on October 6, 2026.

Source: Mathews-Tom/armory on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.