Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Idea Forge: Turn Ideas into Product Specs

    1

    Turn rough product ideas into scoped requirements, explicit assumptions and testable acceptance criteria.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Idea Forge: Turn Ideas into Product Specs

    Example session with this skill installed

    I want to build a simple habit tracker app. I need an MVP PRD and the data model. I'll use React and Supabase. Core feature is just logging a habit once a day.

    • Read your context and instructions
    • Compiled the idea forge

    I have analyzed your habit tracker concept. Based on your React/Supabase stack, I have defined the MVP scope, focusing on a single daily log entry to minimize complexity.

    Habit Tracker MVP PRD

    Product Concept

    A minimalist habit tracking application allowing users to define daily goals and record completion with a single action.

    Assumptions Register

    AssumptionReasonConfidenceImpactValidation
    Single timezoneSimplifies MVP logicHighLowConfirm user location needs
    Daily resetCore value propHighHighUser feedback

    MoSCoW Prioritization

    • Must-Have: User authentication (Supabase Auth), Create/Delete habits, Daily check-in toggle.
    • Should-Have: Streak counters, simple progress visualization.
    • Could-Have: Push notifications, categories.
    • Out-of-Scope: Social sharing, historical data export.

    Data Model

    -- Habits Table
    Table habits {
      id uuid [pk, default: `uuid_generate_v4()`]
      user_id uuid [ref: > users.id]
      name varchar
      created_at timestamp
    }
    
    -- Completions Table
    Table completions {
      id uuid [pk]
      habit_id uuid [ref: > habits.id]
      completed_at date [note: 'Stored as date to prevent multiple logs per day']
      
      Indexes {
        (habit_id, completed_at) [unique]
      }
    }
    

    User Stories

    US-01 | Priority: High | Role: User

    • Capability: I want to mark a habit as done for the current day.
    • Value: To track my consistency and build momentum.
    • Acceptance Criteria:
      • Given I am logged in and have an active habit.
      • When I click the completion toggle.
      • Then the system records the entry for today's date.

    Next steps

    1. Review the data model unique constraints for daily logs.
    2. Confirm if you need historical editing (logging for yesterday).
    3. Initialize the Supabase schema using the provided SQL structure.

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

    About this skill

    Idea Forge is a single instruction skill for an AI agent that can read SKILL.md and work with user-supplied context. Place the skill in your agent's documented skill location after checking its format requirements. Installation compatibility has not been tested.

    The instructions guide the agent through a structured review or planning workflow. This draft package contains the skill document, not a standalone application. Its source marks the release as NOT READY FOR RELEASE.

    The problem

    Unstructured requests can hide missing requirements, weak evidence and unsafe assumptions. This skill specifies what the agent should examine, how to report uncertainty and what the output should contain.

    What you get

    PartIncluded
    Instruction skill1 SKILL.md
    Bundled scripts0
    Reference files0
    Plugin manifestNone found
    LicenseNot supplied

    How it works

    The agent follows the instructions using its own available tools. The package does not supply an executable engine. Every conclusion still needs evidence from the user's input.

    Uses

    Draft a compact MVP PRD. Request a focused deliverable with evidence and stated limitations. Try: "Draft a compact MVP PRD for the supplied input. State assumptions and identify what needs verification."

    Expand a full specification. Request a focused deliverable with evidence and stated limitations. Try: "Expand a full specification for the supplied input. State assumptions and identify what needs verification."

    Write technical requirements. Request a focused deliverable with evidence and stated limitations. Try: "Write technical requirements for the supplied input. State assumptions and identify what needs verification."

    Review an existing PRD. Request a focused deliverable with evidence and stated limitations. Try: "Review an existing PRD for the supplied input. State assumptions and identify what needs verification."

    Update requirement identifiers. Request a focused deliverable with evidence and stated limitations. Try: "Update requirement identifiers for the supplied input. State assumptions and identify what needs verification."

    Maintain an assumptions register. Request a focused deliverable with evidence and stated limitations. Try: "Maintain an assumptions register for the supplied input. State assumptions and identify what needs verification."

    Define Given/When/Then criteria. Request a focused deliverable with evidence and stated limitations. Try: "Define Given/When/Then criteria for the supplied input. State assumptions and identify what needs verification."

    Plan delivery phases. Request a focused deliverable with evidence and stated limitations. Try: "Plan delivery phases for the supplied input. State assumptions and identify what needs verification."

    Guardrails

    Do not claim tests passed, changes were applied or external actions completed without evidence. Review permissions and uncertainty before acting. The underlying agent determines actual access and data handling.

    Who it is for

    People who want structured assistance for this domain and can review the result. The current draft is not for buyers expecting tested software, a complete command-line tool or verified platform integrations.

    Safe handling

    Only provide inputs you are authorized to process. The package has no bundled executable scripts, network client or credentials. This does not make the host AI agent offline: its provider and tool settings determine how data is processed.

    Does not perform market research. Architecture recommendations must be manually validated. Requires specific input prompts to trigger different operating modes.

    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 1 month ago

    Permissions

    Read Files

    Reads supplied documents and relevant local project files through the agent. May produce reports and proposed changes. No bundled scripts, binaries, credentials or mandatory network client were found. Host-agent tools and provider determine actual runtime permissions.

    Listed1 month ago

    What's inside

    Frequently Asked Questions

    The skill supports four modes: Quick (for MVPs), Full (for comprehensive SaaS planning), Developer (focused on technical specs and schemas), and Review (for auditing existing documents for logic gaps).

    You receive a robust set of implementation-ready assets, including a structured PRD, user stories with acceptance criteria, data models, API schemas, and an assumptions register.

    Unlike standard prompts, this skill uses a structured clarification process to force you to address hidden assumptions and technical contradictions, preventing the 'fluff' and scope creep typical of generic AI generation.

    Yes, the skill is designed to audit and refactor existing documentation, identifying contradictions, missing edge cases, and outdated requirements while maintaining consistent ID tracking.

    All documentation is exported in standard Markdown format, making it easy to copy-paste directly into project management tools like Jira, Linear, GitHub, or Notion.

    This skill focuses purely on product scoping and technical architecture; it does not perform external market research, competitor analysis, or visual UI/UX design.

    New in Business & Operations