More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+22 more

    Killcheck: find what kills the idea before you build it

    1

    Writes the press release and FAQ as if it already shipped, runs a pre-mortem, picks the riskiest assumption, sets kill criteria in advance and names the cheapest test. Ends in go, change or stop.

    $9

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Killcheck: find what kills the idea before you build it

    Killcheck: find what kills the idea before you build it

    Example session with this skill installed

    Killcheck this: a booking app that lets small hardware shops schedule stock checks with suppliers. Should we build it?

    • Read your context and instructions
    • Compiled the killcheck

    Stress test saved to stress-test.md. Press release, customer FAQ and internal FAQ are in the file; 3 FAQ answers were flagged as assumptions. All figures below are illustrative.

    IDEA        For small hardware shops, a booking app schedules supplier
            stock checks in one tap, instead of phone calls and WhatsApp.
VERDICT     CHANGE: demand is plausible but willingness to pay is untested;
            start with a concierge version, not an app.
RISKIEST    At least 5 of 20 shops will pay a deposit within 14 days.
KILL IF     under 3 deposits · by 2026-11-30 · spend cap $200
NEXT TEST   Concierge booking by hand for 3 shops, owner: you,
            cost: $0 plus 6 h, by 2026-11-15,
            success: 3 shops ask to keep it and 5 of 20 pay a deposit
TOP RISKS   1. They want it but would not pay (likely, serious)
            2. Suppliers ignore the bookings (likely, serious)
            3. Owner runs out of time alongside client work (unlikely, serious)
ASSUMPTIONS - Shops will switch from WhatsApp for this one job
            - Suppliers will accept bookings from an app
            - $15 a month is acceptable [unknown, no source]

    Red team: a supplier portal could add scheduling for free; a sceptical owner asks why not a shared calendar. The case for: no current tool links small shops to many suppliers. Neither changes the verdict.

    One recommendation: CHANGE to a concierge test first. Alternative in one line: STOP if 5 interviews show no current pain.

    Next steps

    • Run 5 shop interviews about their current workaround, no pitching.
    • Start the concierge version for 3 shops and track deposits against the kill line.
    • After 2026-11-30, re-run the verdict against these criteria without lowering the bar.

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

    About this skill

    Everyone you showed the idea to said they loved it, and nobody argued against it. A month of building later, compliments did not turn into sign-ups, and nobody paid.

    Killcheck spends an hour attacking the idea so you do not spend a month building the wrong thing. It ends in one call: GO, CHANGE or STOP.

    What it does

    • One-line statement: for who, does what job, so that what outcome, instead of which workaround. If it does not fit, the idea is not ready.
    • Press release and FAQ written as if it already shipped, with any unsourced number marked [unknown] and every "we hope" answer flagged as an assumption.
    • Pre-mortem assumes it failed a year later and sorts reasons into six buckets, each rated likely or unlikely and serious or survivable.
    • Riskiest assumption picked by likely wrong and most fatal, stated as a testable sentence.
    • Kill criteria set in advance: threshold, deadline and spend cap, before any test runs.
    • Cheapest test that could prove it wrong, with owner, cost, date and success line.
    • Red-team pass as a competitor, a sceptical buyer and the 2 a.m. maintainer, then the strongest case for it.

    How it works

    1. State the idea in one line.
    2. Write the press release, customer FAQ and internal FAQ.
    3. Pre-mortem, then pick the riskiest assumption.
    4. Lock kill criteria and design the cheapest test.
    5. Red team, then recommend once. You decide.

    Frameworks & tools

    Uses the working-backwards press release and FAQ, a pre-mortem and a red-team pass. No software required beyond your agent.

    Why this beats prompting it yourself

    "Is this idea good?" usually gets encouragement. Killcheck makes the failure analysis mandatory, counts actions (sign-ups, deposits, replies) instead of compliments, and fixes the kill line before results can move it.

    Use cases

    • New product or venture before real time or money.
    • Feature in an existing product, where the press release becomes the release note.
    • Offer or pricing tested with a real quote to three prospects.
    • Re-test after an experiment, against the original kill criteria.

    Known limitations

    Not for planning the build, market sizing or competitor research. Not worth running on small, cheap, reversible changes. It does not run the experiment for you.

    How to use

    Skills on Agensi run inside your AI agent. Copy the prompt, paste it into your agent, and it connects to Agensi and installs this skill for you. If a payment is needed, your agent shows it to you first.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill passes our trust checks below.

    Security scanned

    Passed 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 scanned

    Verified clean 1 day ago

    • Passed all security checks, Safe to install

    Listed1 day ago

    What's inside

    Frequently Asked Questions