More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Assumption Stripper

    1

    Paste any plan, claim, or decision. Get its hidden assumptions listed, labeled (backed, unchecked, or shaky), ranked by what matters most, and a cheap test for each of the top three. Free, with no tools or setup needed.

    Free

    Security scanned
    Assumption Stripper

    Assumption Stripper

    Example session with this skill installed

    We're planning to raise our SaaS price from $40 to $48 per month (20%) for all customers next month. Monthly churn is about 3%, and three competitors charge $45-60. Run assumption stripper on this.

    • Read your context and instructions
    • Compiled the assumption stripper

    The claim: Raising the monthly price from $40 to $48 for every customer next month will increase revenue.

    Assumptions

    #AssumptionTypeStatusIf it's wrong
    1Customers value the product enough to pay 20% moreImpliedUncheckedCancellations rise and revenue falls
    2Churn stays near 3% after the increaseImpliedShakyThe 3% was measured at $40, so a price change is exactly the kind of event that can move it
    3Competitors at $45-60 set the price customers compare you toOutsideUncheckedCustomers may compare you to cheaper options or to doing nothing
    4Competitor plans offer comparable featuresOutsideUncheckedTheir higher prices may not apply to your product
    5One price increase fits every customer segmentImpliedShakyLight users may leave while heavy users would have paid more
    6Existing customers will accept a notice without pushbackImpliedUncheckedComplaints, downgrades, or quiet cancellations
    7The revenue gained outweighs the customers lostImpliedUncheckedNet revenue falls even though the price is higher
    8Next month is a safe time to change pricingImpliedUnknownRenewals, launches, or seasonality may confuse the result

    The three that matter most

    #2 - Churn after the increase. Everything else depends on it. A 20% rise breaks even only if fewer than about 16.7% of customers leave (1 - 1/1.2). You know your churn at the old price, not the new one.
    2.

    #5 - One price for everyone. The plan treats all customers as one group. You gave no usage or segment data, so it is unknown whether some customers are far more price-sensitive than others.
    3.

    #3 and #4 - Competitor comparison. The $45-60 range is the main support for the new price, but it only helps if those competitors are truly comparable.

    Cheapest tests

    AssumptionTestEffortWhat would change the plan
    #2 ChurnApply $48 to new sign-ups only for 30 daysLowIf sign-up conversion drops by more than about 16.7%, revenue per visitor falls
    #5 SegmentsSplit current customers by usage and compare who is likely to leaveA few hoursIf light users are a large share, consider a tiered price instead of one flat rise
    #3, #4 CompetitorsCompare feature lists and pricing pages for the three competitorsAbout an hourIf they offer much more, $48 may be hard to justify

    What looks sound: You have a measured baseline churn figure and a competitor price range, which is more than many price changes start with.

    Next step: Run the new-customer price test at $48 first. It checks the biggest assumption without touching your existing customers.

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

    About this skill

    Most plans fail on something nobody said out loud.

    Assumption Stripper takes a plan, claim, or decision and shows you what it quietly depends on. It does not tell you what to do. It shows you what your plan rests on, so you can check the weak parts before you spend money or time.

    What you get

    • A list of 6 to 10 assumptions, each written so it can be tested
    • A label on each one: Stated, Implied, or Outside, and Backed, Unchecked, or Shaky
    • The 3 assumptions that matter most, and why
    • A cheap test for each, with the rough effort and what result would change the plan
    • One next step

    Good for

    • Pricing changes and product launches
    • Business plans and forecasts
    • Hiring or investment decisions
    • Arguments or opinions you want pressure-tested
    • Personal decisions where you want to see what you're taking for granted

    How it behaves

    • It only uses what you give it. It does not invent numbers, studies, or market data.
    • It does not flatter the plan or deliver a verdict.
    • It works out break-even math when you provide the numbers.
    • It needs no tools, files, or network access.

    How to use it Install the skill, then tell your agent your plan and say something like "run assumption stripper on this," "what am I missing," or "poke holes in this."

    Works with any SKILL.md-compatible agent, including Claude Code, Cursor, Codex CLI, Gemini CLI, and VS Code Copilot.

    Want the full reasoning workflow? Assumption Stripper is the quick version. First Principles Engine goes further: it rebuilds the answer from fundamentals, states its confidence, and argues against its own conclusion.
    → Get it (and everything else) through my link: https://www.agensi.io/r/ZAHEERBABAR

    • Does not research the market, fetch data, or look up external facts. It only works with what you provide.
    • Does not invent numbers, studies, or competitor details. If information is missing, it labels it as Unknown.
    • Does not give a go / no-go verdict. It surfaces assumptions and cheap tests — the decision stays with you.
    • Not a substitute for professional legal, medical, tax, or large financial advice. High-stakes assumptions should still be checked by a qualified person.
    • Works best when you give at least a few sentences of context. Very short inputs produce more “Unknown” labels.

    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 any payment.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 18 days ago

    • Free with an Agensi account

    Permissions

    No special permissions declared or detected

    Listed18 days ago

    What's inside

    Frequently Asked Questions

    The Assumption Stripper uses a logic-based methodology to extract implied dependencies—the things that *must* be true for your plan to work—rather than just listing generic pros and cons. It categorizes these by certainty and provides specific, low-cost experiments to test your riskiest claims before you invest capital.

    This skill is designed for use within your existing AI agent workspace; once purchased, it can be activated within your agent's interface. It requires no complex installation or API keys, as it functions through specialized reasoning logic applied to your text inputs.

    No, the skill operates entirely on the data you provide to ensure privacy and focus. It analyzes the internal logic of your strategy and uses general business principles to identify gaps, rather than pulling potentially inaccurate or halluncinated live market data.

    You receive the full logic-based skill package, including the extraction matrix, risk ranking system, and the experiment design framework. Future logic refinements and updates to the validation methodology are included at no additional cost.

    The skill works best with specific, text-based plans such as product launch summaries, pricing model descriptions, or strategic investment memos. The more detail you provide about your intended logic, the more effectively the skill can identify the 'hidden' links you might have missed.

    No. It shows what your plan depends on and how to check the important parts. The decision stays with you.

    No. It works only with what you give it. If a number is missing, it says so instead of guessing.

    A few sentences are enough. If you give less, it lists the missing information as unknown assumptions and asks at most one question.

    Any agent that supports the SKILL.md standard, including Claude Code, Cursor, Codex CLI, Gemini CLI, and VS Code Copilot.

    Yes. There is no catch and no setup.

    New in Productivity