Idea Verdict: Validation-First Opportunity Screener

    1

    - **SAVE:** a promising but not-yet-testable idea, parked behind a **dated, observable revival condition**.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Idea Verdict: Validation-First Opportunity Screener

    Example session with this skill installed

    I want to screen an idea for a $20/mo CLI tool that automates Docker cleanup for solo devs. I have 10 hours this week. My channel is a private Discord for DevOps freelancers.

    • Read your context and instructions
    • Compiled the idea verdict

    The idea has been screened against the internal rubric.

    Verdict: SAVE
    Provisional: The verdict is SAVE because the payment route (Field 8) and KYC status (Field 9) are currently marked as unknown. While the acquisition channel is strong, testing cannot begin without a verified way to accept the $20 payment.

    Intake Recap

    1. Buyer: Solo DevOps developers/freelancers.
    2. Pain: Manual Docker volume/image cleanup wasting ~1 hour weekly.
    3. Workaround: Manual docker system prune or custom bash scripts.
    4. Price point: $20/month.
    5. Channel: Private DevOps Discord (Permission: Maker is a moderator).
    6. Build/Test Budget: MVP 6h; Available 10h; Test 4h.
    7. Maintenance/Capacity: Est 2h/week; Available 5h/week.
    8. Payout route: UNKNOWN.
    9. KYC/Legal: UNKNOWN.
    10. Maker material: Expert in CLI tools and Docker.

    Evidence-vs-Assumption Ledger

    • Evidenced: Maker capacity (Field 6), Channel access (Field 5), Domain expertise (Field 10).
    • Assumed: Buyer willingness to pay $20 for a cleanup script (Field 4), specific pain frequency (Field 2).

    Why this verdict

    • K1-K5: NOT MET.
    • K6 (Money/Legal): UNKNOWN. Payout route not defined.
    • K7 (Capacity): NOT MET.

    Verdict Rationale: You have the hours and the audience, but no way to collect the "Real-Price Paid" metric required for a PASS.

    Revival Condition

    Gate: Verify Stripe or LemonSqueezy account eligibility and link a bank route by Friday, Oct 27.
    Consequence: Once verified, move to the 7-day Validation Plan below.

    7-day Validation Plan

    • Day 1-2: Configure payment link and build a single-command "Dry Run" CLI binary.
    • Day 3-5: Post "Dry Run" tool in Discord with a $20 "Early Access" buy link.
    • Day 6-7: Tally results.
    • PASS: 5+ paid customers.
    • PARTIAL: 2-4 paid customers (Extend test 7 days with one follow-up post).
    • FAIL: 0-1 paid customers.

    Next steps

    1. Select a payment processor (Stripe/Paddle/LemonSqueezy) and check your region's KYC requirements.
    2. Update Field 8 and 9 to flip this to a GO verdict.
    3. Draft the Discord announcement post focused on the "1-hour weekly waste" pain point.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Stop asking whether your idea is "good." Ask whether it deserves your next week.

    Before you spend nights building a product, answer ten specific questions: who pays, what hurts, what buyers do instead, your proposed price, the one place to reach them, the actual time and cash you can afford, maintenance capacity, payment readiness and your own head start.

    Idea Verdict gives one of three answers:

    • GO: enough concrete information to justify one carefully bounded 7-day test, not a guarantee of sales.
    • SAVE: a promising but not-yet-testable idea, parked behind a dated, observable revival condition.
    • KILL: at least one of seven explicit disqualifiers is met, with the reason and what must change before reconsidering it.

    What the skill gives you

    • Fixed ten-field intake: the same structure for every idea. The build and maintenance questions compare both estimated work and time/cash actually available. Missing answers are recorded as unknown, not filled with guesses.
    • Evidence-vs-assumption ledger: every material claim is labelled Evidenced (with its maker-reported basis) or Assumed (with the proof needed). You can see which parts of a GO have not yet been tested.
    • A seven-criterion kill screen: payer, pain, acquisition channel, build feasibility, payment blockers, maintenance capacity and essential capabilities/permissions — each explicitly scored MET, NOT MET or UNKNOWN.
    • One-channel validation plan: for GO, a 7-day plan to run now; for SAVE, a conditional plan that starts when the revival gate is met. Real-price purchases and legally permitted deposits are the strongest signals. Mere likes, views and uncommitted "I'd buy" replies never qualify as paid orders.
    • Numerically exhaustive PASS / PARTIAL / FAIL rules: an incomplete exposure is not misread as rejected demand. A PARTIAL allows at most one clearly defined extension, not endless tweaking.
    • A fully worked fictional example: see the complete intake, ledger, kill checks, budget comparisons, test and limitations before you run your own.

    How it works

    In your Agensi-connected AI agent, ask it to use Idea Verdict and describe one idea. Answer the ten fields in chat. The agent produces the verdict, the ten-field recap for correction, the evidence ledger and the next-step test where appropriate. The skill produces written reasoning and a plan; you run the buyer experiment.

    Requirement: an AI agent that can use Agensi through its MCP connection (such as Claude Code or Cursor), with Agensi sign-in and access to this skill. Connecting the agent to Agensi is a one-time prerequisite; this skill does not configure MCP on its own. Consult Agensi's current connection instructions if you have not connected it yet.

    Who it's for

    Solo builders, small app and template creators, independent developers and makers choosing what deserves the next week of work — especially when their available time, money and ability to get paid matter more than speculation about the size of a market.

    What you receive

    • The main SKILL.md workflow and quickstart.
    • A seven-kill-criterion rubric and explicit GO/SAVE/UNKNOWN policies.
    • Three one-channel validation templates: direct outreach, marketplace listing and buyer community.
    • One fully fictional, detailed worked example.

    These are skill materials loaded into your agent through Agensi, not a set of downloadable buyer files.

    What it does not do

    It does not browse and verify live policies, bank eligibility, demand, legal compliance or community permissions; send messages; create listings; charge customers; or run validation experiments. It is not a prediction of future sales and does not produce invented market-size figures. Your answers are treated as reports, not externally audited facts. A 7-day buying-signal test cannot establish lifetime retention, clinical safety, or profitability.

    See it in action (fictional illustrative output, not a real customer result)

    Input: "I spent two years at a small tattoo studio. Owners answer the same aftercare questions. I can DM 20 named studios, and I want to sell ten blank editable card designs for $24, so each studio adds its own approved wording. The pack will take about eight hours, and I have ten build hours/$30. My test takes four hours; I have six hours/$10 for that. I can spend two hours/$10 weekly on support. I already receive payments through my provider."

    Verdict: GO (provisional). Named payer, repeat-workaround evidence, one identified list of studios, and explicit build/test/maintenance capacity support a bounded test. Assumed: owners will pay $24, the eight-hour estimate will hold, and support will remain light. Kill checks: no criterion MET on the maker's supplied facts; payment and permission statements remain maker-reported. Next 7 days: prepare an actual deliverable pack and show a sample; contact exactly 20 named studios through the one direct-message channel; count replies about their own problem (R), concrete buying-step requests (A) and actual $24 orders (P). PASS: R ≥ 5, A ≥ 3 and P ≥ 2. FAIL: P = 0, or R < 3 with P < 2, after complete outreach. PARTIAL: everything else, or incomplete outreach, with one capped follow-up. These are proposed experimental thresholds, not proof that any studio purchased.

    Compatibility note

    Requires an Agensi MCP-connected, signed-in AI agent that can load and follow text-based SKILL.md skills. No separate local executable or dedicated API key is included. Connection/purchase approval are handled by Agensi and the buyer's agent.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Business & Operations.

    Requires Agensi MCP setup. Maker must provide all intake data; the skill does not browse the web for market sizes or demand. Does not execute the actual 7-day test or contact buyers.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 11 days ago

    Permissions

    Read Files
    Listed11 days ago

    What's inside

    Frequently Asked Questions

    This skill forces you to categorize claims as either 'Evidenced' or 'Assumed' and applies a rigid 7-point 'kill rubric' to prevent bias, ensuring you only spend time on ideas with a realistic path to acquisition and payment.

    You receive the logical framework and MCP-compatible instructions required to run the full screening process, including the 10-field intake system, the Evidence Ledgering logic, and the 7-day validation plan generator.

    Idea Verdict is designed for Agensi-compatible environments such as Claude Code or Cursor and requires an active Agensi MCP connection to function within your development workflow.

    The skill generates a day-by-day 7-day validation plan with specific numeric PASS/FAIL thresholds, though it does not perform the actual outreach or market research for you.

    Yes, once purchased, you will receive notifications of any logic refinements to the kill rubric or updates to the validation planning framework through the marketplace interface.

    It is highly effective for SaaS features, service-based hustles, and digital products, though it is limited to screening one specific business idea per execution cycle to maintain focus.

    New in Business & Operations