Relentless interviewing tool to validate plans and design decisions through guided Q&A.

Install

mkdir -p .claude/skills/grill-me-kgtdbx && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/11352" && unzip -o skill.zip -d .claude/skills/grill-me-kgtdbx && rm skill.zip

Installs to .claude/skills/grill-me-kgtdbx

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

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".
231 chars✓ has a “when” trigger
Intermediate

Key capabilities

  • Interview user
  • Stress-test designs
  • Resolve decision branches
  • Validate dependencies

How it works

It systematically asks questions to explore every branch of a design tree until shared understanding is reached.

Inputs & outputs

You give it
Project plan or design
You get back
Resolved decision tree

When to use grill-me

  • Stress-testing project designs
  • Validating plan dependencies
  • Exploring architectural edge cases
  • Ensuring team alignment

About this skill

Interview me relentlessly about every aspect of this plan until we reach a shared understanding. Walk down each branch of the design tree, resolving dependencies between decisions one-by-one. For each question, provide your recommended answer.

Ask the questions one at a time.

If a question can be answered by exploring the codebase, explore the codebase instead.

When not to use it

  • When the user wants a quick answer
  • When the plan is already fully validated

Limitations

  • Can be time-consuming

How it compares

It forces the user to clarify dependencies and edge cases through relentless questioning.

Compared to similar skills

grill-me side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
grill-me (this skill)03moNo flagsIntermediate
openspec-explore46moReviewBeginner
thought-patterns68moNo flagsAdvanced
gathering-requirements38moNo flagsIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

openspec-explore

studyzy

进入探索模式 - 一个用于探索想法、调查问题和澄清需求的思考伙伴。当用户想要在进行更改之前或期间深入思考某事时使用。

4117

thought-patterns

markpitt

Orchestrates comprehensive cognitive thinking patterns including sequential, systems, lateral, divergent/convergent, abductive, analogical, first-principles, double-loop learning, gestalt, metacognitive, and neurodivergent patterns (ADHD hyperfocus, autistic detail-orientation, dyslexic spatial reasoning). Analyzes tasks to select optimal pattern(s), chains multiple patterns when needed, and validates outputs before responding. Use for complex problem-solving, creative tasks, analytical challenges, or when diverse cognitive approaches enhance solution quality.

697

gathering-requirements

CaptainCrouton89

Systematically clarify user needs, preferences, and constraints before planning or implementation. Classifies work type, investigates existing systems, discovers edge cases and integration points, resolves assumptions, and creates detailed specifications. Use when building features, enhancements, or integrations where requirements need clarification.

31

the-fool

Jeffallan

Use when challenging ideas, plans, decisions, or proposals using structured critical reasoning. Invoke to play devil's advocate, run a pre-mortem, red team, or audit evidence and assumptions.

13

decision-critic

solatis

Invoke IMMEDIATELY via python script to stress-test decisions and reasoning. Do NOT analyze first - the script orchestrates the critique workflow.

11

tech-divergence

WellApp-ai

Evaluate technical options with scoring matrix, trigger Gate 4 for significant decisions

11

Search skills

Search the agent skills registry