grill-me

Runs a structured interview session to challenge and refine a plan or design.

1|Updated Jul 23, 2026
One-click install
npx skills add https://github.com/sanjanb/my-agent-harness --skill grill-me-sanjanb
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: grill-me
Source: https://github.com/sanjanb/my-agent-harness/tree/main/skills/mp-grill-me
Command: npx skills add https://github.com/sanjanb/my-agent-harness --skill grill-me-sanjanb

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Plans and designs often contain hidden assumptions, gaps, and weak reasoning that only surface during implementation. This Skill subjects a plan to a relentless question-and-answer session so flaws are exposed before any code is written. ## Core Features & Use Cases - Adversarial Interviewing: Runs a /grilling session that probes a plan or design with tough, targeted questions. - Assumption Surfacing: Forces explicit justification of design decisions, edge cases, and trade-offs. - Use Case: Before handing an implementation plan to a coding agent, run a grilling session to stress-test the architecture, catch missing error handling, and tighten the scope. ## Quick Start Ask the agent to run a grilling session on your current implementation plan to challenge its assumptions.

Frequently Asked Questions about grill-me

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

FAQPage Schema
How do I stress-test an implementation plan before coding?

Run a grilling session on the plan, which subjects it to relentless targeted questions about assumptions, edge cases, and trade-offs. Weak points surface through the interview before any code is written.

What is a grilling session for plan review?

A grilling session is an adversarial interview where the agent relentlessly questions a plan or design. It forces explicit justification of decisions and exposes hidden gaps that silent review typically misses.

When should I use interview-based plan review?

Use it after drafting a plan or design but before implementation begins. It works best when you have a concrete proposal to defend, not for open-ended brainstorming or early ideation.

Can this skill be invoked automatically by the agent?

No, the skill disables model invocation and implicit invocation, so it only runs when explicitly requested by the user. This prevents unexpected interruptions during other workflows.

What are the limitations of interview-based design review?

The review quality depends on the plan's written detail and the user's answers during the session. It does not execute code, run tests, or verify technical feasibility empirically.