Design Brainstorming

    1

    Agree on the design before writing code: a few targeted questions, 2-3 approaches with trade-offs, then build.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    About this skill

    For non-trivial work (a new feature, a new project, an architectural refactor) Claude first reads the context, asks only the questions it cannot answer from the code, and proposes two or three approaches with their trade-offs. Once you pick one, it writes the design down if it is worth keeping and moves on to implementation. A short section covers presentations and teaching material.

    Targeted fixes and tasks with explicit instructions skip the whole process.

    Adapted from obra/superpowers (MIT, Jesse Vincent). Source and other skills: https://github.com/thomascasali/memoteca

    Meant for non-trivial work. It deliberately stays out of targeted fixes, minimal edits and tasks that already come with explicit instructions.

    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

    1 use

    Times used to date

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    • Free with an Agensi account

    Permissions

    Read Files
    Write Files
    Listed1 month ago
    Updated9 days ago

    What's inside

    Frequently Asked Questions

    On non-trivial requests: a new feature, a new project, a new presentation, an architectural refactor, or any task with several plausible approaches. Targeted fixes, minimal edits and tasks with explicit instructions skip it.

    No. It reads the context first and only asks what it cannot work out from the code or the files, then proposes two or three approaches with their trade-offs.

    It is adapted from the brainstorming skill in obra/superpowers (MIT, Jesse Vincent). The source, in Italian and English, is at https://github.com/thomascasali/memoteca

    New in Productivity

    Free