Shrimp Brainstorming: Structured Idea Discovery for AI Agents

Repositorytonbistudio/shrimp-brainstormingTool

Shrimp Brainstorming is an open-source agent skill, designed for platforms like Hermes Agent, that turns raw project or business ideas into evidence-backed specs through user-guided research.

Key points

  1. Transforms vague concepts into actionable decisions through agent research, stress-testing, and user feedback.
  2. Abandons rigid questionnaire funnels, asking clarifying questions only when strictly necessary for research.
  3. Outputs a standardized folder structure including concept-brief.md, research-ledger.md, and final-spec.md.
  4. Introduces structured evaluation concepts such as Shrimp Verdict, Decision Frontier, and Fog of War.
  5. Distributed as a SKILL.md file compatible with Hermes Agent under an MIT license.

Why it matters

Typical LLM brainstorming often turns into aimless chat or overly rigid discovery interviews. This skill establishes an evidence-driven workflow that documents decisions, pivots, and trade-offs directly in clear handoff artifacts.

Analysis

The project solves the issue of poorly tracked and under-researched project ideation. Technologically, it is implemented as a prompt- and workflow-based agent skill (SKILL.md with markdown templates), configured for runtimes such as Hermes Agent. It targets developers, entrepreneurs, and product managers who want to use AI agents for rigorous ideation rather than superficial chats. With 30 stars and 1 fork, the project is in an early stage of maturity but provides a concrete, usable framework for research-driven handoff specifications.

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Video

    Video:Tonbi's AI Garage

    Shrimp Brainstorming: Stress-Testing Project Ideas with AI Agents Before Writing Code

    Tonbi presents a structured workflow for evaluating half-baked project and business ideas using a dedicated Telegram bot. Powered by the open-source 'Shrimp Brainstorming' skill, the agent conducts competitor research, challenges assumptions, delivers an unvarnished verdict, and outputs a specification file for coding agents.

    AI & LLMs· Demo

  • Repository:mohitagw15856/pm-claude-skills

    PM Skills: Agent Framework Collection for AI Assistants

    PM Skills is an MIT-licensed repository providing over 1,100 structured agent skills in plain Markdown. It equips models across Claude, ChatGPT, Gemini, Cursor, and Codex with step-by-step frameworks for professional duties and critical life events.

    1.3kstarsHTML

    AI & LLMs· Resource

  • Repository:NousResearch/hermes-agent

    Hermes Agent: Self-Improving Open Source AI Agent by Nous Research

    Hermes Agent is a cross-platform, self-improving AI agent designed with an autonomous learning loop, cross-session memory, and integration into multiple messaging platforms and terminal interfaces.

    240.8kstarsPython

    AI & LLMs· Tool

  • Repository:github/spec-kit

    Spec Kit: Open-Source Toolkit for Spec-Driven Development with AI Agents

    GitHub's Spec Kit is an open-source framework designed for Spec-Driven Development (SDD). It helps software teams define requirements clearly before implementation, guiding AI coding agents through structured workflows.

    133.6kstarsPython

    AI & LLMs· Tool

  • Link:Telescope Ltd

    BuilderOS: Structured Agent Workflow from Idea to Launch

    BuilderOS by Telescope Ltd is a collection of modular agent skills designed to turn coding agents like Claude Code, Codex, or Cursor into disciplined collaborators. It guides builders through four phases—ideate, plan and design, build, and launch—using chained Markdown specifications stored in the project's docs/ directory.

    AI & LLMs· Tool

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.