Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Idea Reality Check

    1

    Stress-test a product idea against real users, existing solutions, prior art, and constraints, then recommend the cheapest next test.

    $1.79

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Idea Reality Check

    Idea Reality Check

    Example session with this skill installed

    I want to build an app that tells people whether a startup idea is worth pursuing, using public web evidence instead of a survey. Is this a real problem, what already exists, and what is the cheapest next test?

    • Read your context and instructions
    • Compiled the idea reality check

    The skill first splits the observed problem (founders waste time and money on unvalidated ideas) from the proposed app. It searches products and prior art across regions, including existing idea-validation tools, research skills, and consultancies. It lists similar offerings, notes what evidence is public vs missing, and flags hidden assumptions such as whether founders will pay for a report they could get by prompting an agent themselves. It then recommends one cheap next test, for example putting a single-page offer in front of a small set of founders and measuring whether they actually request a paid report, instead of defaulting to building an MVP. Findings are cited with links; unverifiable claims are marked as such.

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

    About this skill

    Idea Reality Check helps you evaluate a product, hardware, software, or service idea before you commit to building it. It separates the observed problem from the proposed solution, researches what people already use, looks for prior art, and tries to falsify the idea with sourced evidence.

    It does not invent market scores or talk you into building an MVP. The output is a Reality Check Report: hidden assumptions, an adversarial kill section, and one cheapest next experiment aimed at the most decision-critical unknown.

    Works as a portable SKILL.md skill with Codex, Claude Code, Cursor, and other agents that load the open skill format.

    Limitations

    This is a research skill, not legal, patent freedom-to-operate, or investment advice. Current-market findings depend on sources the agent can access at the time. It does not invent numeric market scores.

    This is a research skill, not legal, patent freedom-to-operate, or investment advice. Current-market findings depend on sources the agent can access at the time. It does not invent numeric market scores.

    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

    Money-back guarantee

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

    Trust & safety

    Security scan

    Security scan passed 3 days ago

    Permissions

    Write Files
    Browser
    Network Access
    Listed3 days ago

    What's inside

    Frequently Asked Questions

    Idea Reality Check helps you evaluate a product, hardware, software, or service idea before you commit to building it. It separates the observed problem from the proposed solution, researches what people already use, looks for prior art, and tries to falsify the idea with sourced evidence.

    The output is a Reality Check Report: hidden assumptions, an adversarial kill section, and one cheapest next experiment aimed at the most decision-critical unknown. It does not invent market scores or talk you into building an MVP.

    This is a research skill, not legal, patent freedom-to-operate, or investment advice. Current-market findings depend on sources the agent can access at the time. It does not invent numeric market scores.

    Works as a portable SKILL.md skill with Codex, Claude Code, Cursor, and other agents that load the open skill format.