How do I install the Skill Grill Me skill?

Run npx skillmds@latest add saitarrun/skill-grill-me in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Skill Grill Me safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Skill Grill Me?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Skill Grill Me free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Skill Grill Me?

saitarrun (@saitarrun) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Skill Grill Me by saitarrun — Agent Skill

Name: Skill Grill Me
Author: saitarrun

Skill Grill Me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me", "stress test", "poke holes", "challenge my plan".

saitarrun f09cebb 2.6 KB Updated Sep 17, 2026

File contents

Skill: Grill Me

Relentless design/plan review via structured interview. Walk down each branch of the decision tree, resolving dependencies between decisions one-by-one. Reach shared understanding by testing assumptions and exposing gaps.

Process

Parse the plan/design — Identify key decisions, dependencies, assumptions
Ask one question at a time — Deep on one branch; await answer before moving
Explore codebase first — If a question is answerable by code inspection, do that instead of asking
Provide recommended answer — For each question, suggest what you think is the right call (so user can react faster)
Resolve branch completely — Don't jump to another decision until this one is fully understood
Walk dependency tree — Only move to dependent decisions once blockers are cleared
Reach shared understanding — Stop when both agree on the plan or user signals done

Question Structure

For each question:

**Q: [Question]**

My take: [Your recommended answer + reasoning]

What do you think?

When to Explore Code Instead

If user hasn't answered a question yet:

Design decision that's already implemented? Read the code.
Architecture pattern already in repo? Grep for examples.
Library choice already wired? Check package.json / imports.

This avoids asking about settled questions.

Decision Tree Example

Plan: Add user authentication

├─ Auth mechanism? (OAuth vs. session vs. JWT)
│  └─ Once decided → ask: which provider?
│     └─ Once decided → ask: token expiry strategy?
│        └─ Once decided → ask: refresh token rotation?
│
├─ DB schema for sessions/tokens?
│  └─ Once decided → ask: cleanup/revocation strategy?
│
├─ Rate limiting & brute force?
│  └─ Once decided → ask: lockout duration vs. progressive delay?

Only ask dependent questions after parent is resolved.

Stopping

User says: "stop grill", "that's enough", "I'm confident now"
You decide: "We've resolved the full decision tree and reached agreement."

Status: Ready for design reviews, plan stress-testing, and decision validation
Best for: Complex features, architectural decisions, security-critical design, high-risk plans

---name: skill-grill-medescription: Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me", "stress test", "poke holes", "challenge my plan".---# Skill: Grill MeRelentless design/plan review via structured interview. Walk down each branch of the decision tree, resolving dependencies between decisions one-by-one. Reach shared understanding by testing assumptions and exposing gaps.## Process1. **Parse the plan/design** — Identify key decisions, dependencies, assumptions2. **Ask one question at a time** — Deep on one branch; await answer before moving3. **Explore codebase first** — If a question is answerable by code inspection, do that instead of asking4. **Provide recommended answer** — For each question, suggest what you think is the right call (so user can react faster)5. **Resolve branch completely** — Don't jump to another decision until this one is fully understood6. **Walk dependency tree** — Only move to dependent decisions once blockers are cleared7. **Reach shared understanding** — Stop when both agree on the plan or user signals done## Question StructureFor each question:```**Q: [Question]**My take: [Your recommended answer + reasoning]What do you think?```## When to Explore Code InsteadIf user hasn't answered a question yet:- Design decision that's already implemented? Read the code.- Architecture pattern already in repo? Grep for examples.- Library choice already wired? Check package.json / imports.This avoids asking about settled questions.## Decision Tree Example```Plan: Add user authentication├─ Auth mechanism? (OAuth vs. session vs. JWT)│ └─ Once decided → ask: which provider?│ └─ Once decided → ask: token expiry strategy?│ └─ Once decided → ask: refresh token rotation?│├─ DB schema for sessions/tokens?│ └─ Once decided → ask: cleanup/revocation strategy?│├─ Rate limiting & brute force?│ └─ Once decided → ask: lockout duration vs. progressive delay?```Only ask dependent questions after parent is resolved.## Stopping**User says**: "stop grill", "that's enough", "I'm confident now" **You decide**: "We've resolved the full decision tree and reached agreement."---**Status**: Ready for design reviews, plan stress-testing, and decision validation **Best for**: Complex features, architectural decisions, security-critical design, high-risk plans

Frequently asked questions