More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Idea Discovery (Idea to Validated Product)

    1

    Runs a product discovery cycle. Brainstorms 10+ evidence-cited idea cards from a market scan's territories (or the user's own seed ideas), scores each on a…

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    About this skill

    Runs a product discovery cycle. Brainstorms 10+ evidence-cited idea cards from a market scan's territories (or the user's own seed ideas), scores each on a 6-dimension triage rubric (problem severity, reachability, founder fit, build fit, differentiation, effort), applies hard kills, and outputs a ranked triage list with a top-3 callout.

    Use when the user wants startup, SaaS, app or side-project ideas, wants to brainstorm or compare product ideas, has a list of ideas to rank, or has finished a market scan and wants to mine its territories, or says "help me come up with a side-project idea I could actually sell".

    Works in Claude Code, Codex, Gemini CLI, Cursor and Copilot. Live-tested on Claude Code, Codex and Gemini CLI (eval grade A). Part of Idea to Validated Product by Abiodun Anifowose, where it works alongside the pack's other skills.

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

    Requires profile.md for founder-fit scoring. Needs web access for evidence verification. Python 3 required for ID/slug utilities and rendering scripts.

    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 25 days ago

    Software
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access
    Environment Variables
    Listed25 days ago

    What's inside

    Frequently Asked Questions

    The skill uses a 'hard-kill' rubric to evaluate ideas against six dimensions, including problem severity and founder fit. If an idea fails to meet minimum thresholds in these critical areas, it is automatically moved to a 'killed' directory with a logged explanation, preventing you from wasting time on low-potential concepts.

    Yes, you can choose a 'hybrid mode' that allows you to input your own seed ideas to be benchmarked against the 10+ new opportunities the skill generates. This provides a side-by-side comparison to help you determine if your current concepts are actually better than market-driven alternatives.

    This skill is designed for AI agents with Python execution and web-browsing capabilities. It requires local filesystem access to manage the discovery logs and generated reports, and works best when provided with a founder profile for personalized scoring.

    You will receive the complete skill package including the logic for the six-dimension triage, the Python scripts for ID generation, and report templates for HTML, XLSX, and PDF exports. The purchase also includes any future version updates and documentation on how to configure your founder profile.

    Unlike generic prompts that provide 'fluff' ideas, this skill mandates evidence-backed research. Every idea card is required to cite specific URLs for problem statements and distribution strategies, ensuring the output is grounded in real market data rather than creative speculation.

    New in Agents & Orchestration