trellis-brainstorm

Convert ambiguous product requests into PRD-backed planning artifacts through evidence-first interviews.

92|8|Updated May 15, 2026
One-click install
npx skills add https://github.com/LonelyHerbivore/Trellis-Herbivore --skill trellis-brainstorm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trellis-brainstorm
Source: https://github.com/LonelyHerbivore/Trellis-Herbivore/tree/main/.cursor/skills/trellis-brainstorm
Command: npx skills add https://github.com/LonelyHerbivore/Trellis-Herbivore --skill trellis-brainstorm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill resolves unclear or ambiguous feature requests by turning them into shared requirements and planning artifacts before any implementation begins, reducing rework and misalignment.

Core Features & Use Cases

  • Relentless requirements interview with convergence: asks one high-value question at a time and updates PRD after each answer.
  • Evidence-first decision making: searches the repository/codebase for answers before asking the user, ensuring questions focus on intent and remaining gaps.
  • Planning artifact generation: seeds prd.md and creates or updates design.md and implement.md for complex tasks to make execution and acceptance testable.

Quick Start

Use the trellis-brainstorm skill when you need to clarify requirements for a new feature or complex task and you want a PRD-backed MVP plan with explicit open questions.

Frequently Asked Questions about trellis-brainstorm

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn ambiguous product requests into MVP plans?

To turn ambiguous product requests into MVP plans, use an evidence-first interview process that asks one high-value question at a time, automatically seeds a PRD, and updates planning artifacts after each decision to align scope and reduce rework.

What is the best way to align scope for complex technical tasks?

Aligning scope for complex tasks requires searching the repository codebase first for existing evidence, then asking targeted questions about intent to fill remaining gaps, and finally generating explicit design and implementation plans to make execution testable.

How do I create a PRD from an unclear feature request?

Creating a PRD from an unclear request involves conducting a relentless requirements interview that converges on shared requirements, automatically seeding a prd.md file, and iteratively updating it with each user decision.

Does requirements brainstorming work without manually writing design documents?

Requirements brainstorming can automatically generate or update design.md and implement.md files for complex work, ensuring that execution and acceptance criteria are fully testable without manually writing separate design documents from scratch.

When should I use a one-question-at-a-time interview for architecture decisions?

Use a one-question-at-a-time interview for architecture decisions when there are multiple feasible technical approaches and scope or risk choices are not yet decided, allowing evidence-first repository inspection to guide the questioning.