One-click install
npx skills add https://github.com/honerlaw/agent-marketplace --skill grill-plan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grill-plan
Source: https://github.com/honerlaw/agent-marketplace/tree/main/plugins/minerva/skills/grill-plan
Command: npx skills add https://github.com/honerlaw/agent-marketplace --skill grill-plan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It reduces the risk of adopting an unclear or weak software/product plan by forcing the draft to be questioned until shared understanding is achieved.

Core Features & Use Cases

  • One-question-at-a-time grilling: Resolves the decision tree sequentially to avoid missing critical uncertainties.
  • User-answer alignment with a recommended interpretation: Leads each question with the LLM’s best inferred answer from the draft, then confirms or corrects.
  • Codebase-first clarification: Prefers checking existing repo knowledge before asking the user when the answer is already discoverable.
  • Load-bearing probing and draft edits: Presses on assumptions, ambiguities, success criteria quality, and scope drift, while updating the plan in conversation memory.
  • Supports multiple plan sources: Handles both in-context minerva drafts and ad-hoc user-provided plans (e.g., a referenced proposal).

Quick Start

Use the grill-plan skill when you have a drafted plan and want an AI to interview you step-by-step to surface gaps and align everyone before approval.

Frequently Asked Questions about grill-plan

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

FAQPage Schema
How do I stress-test a product plan to find weak assumptions?

Stress-testing a drafted plan requires an interactive process that questions load-bearing assumptions sequentially. This approach conducts one-question-at-a-time interviews, leading each with a recommended inference to surface ambiguities and update the plan.

What is the best way to align stakeholders on software design requirements?

Stakeholder alignment is achieved by resolving the decision tree sequentially through interactive questioning. This ensures shared understanding is reached before approval by pressing on scope drift and success criteria quality.

Can I use assumption testing on an ad-hoc plan without existing context?

Assumption testing applies to ad-hoc user-provided plans and system-generated proposal drafts. The process uses the provided plan context to guide what gets questioned, eliminating ambiguity regardless of the plan source.

How does interactive questioning work for requirements discovery?

Interactive questioning for requirements discovery works by asking one question at a time and preferring codebase lookups over user queries. It leads each question with the best inferred answer from the draft before confirming or correcting.

When do I need a plan review before implementation?

A plan review is needed when a drafted plan risks adopting weak assumptions. It forces the draft to be questioned until shared understanding is achieved, stopping only when an explicit stop signal is reached or ambiguity is eliminated.