Grill Me logo

Grill Me

Community
grp06
grill-me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on a design, pressure-test an architecture or implementation approach, or explicitly says "grill me".

Overview

Publishergrp06
Repositoryuseful-codex-skills
Skill namegrill-me
Stars
78
Forks
6
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by grp06 on GitHub. Read the source before you install it.

Installation

Install the Grill Me AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/grp06/useful-codex-skills/tree/main/grill-me
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/grp06/useful-codex-skills.git /tmp/useful-codex-skills
mkdir -p .claude/skills
cp -r /tmp/useful-codex-skills/grill-me .claude/skills/grill-me
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Grill Me in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Grill Me on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Grill Me is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Grill Me

Core Contract

Interrogate the plan until the important decisions, dependencies, assumptions, and failure modes are resolved. Be direct, persistent, and useful. Do not merely list questions; drive toward shared understanding.

For every question you ask, include your recommended answer. If the question can be answered by inspecting a repository, logs, docs, config, prior plans, tests, or other available artifacts, investigate first and present the evidence instead of asking the user.

Workflow

  1. Identify the plan, design, or decision under review.

    • If the user already provided it, summarize the current understanding in 3 to 6 bullets.
    • If the plan is in files or a repo, inspect the relevant artifacts before beginning the interview.
    • If no plan is available, ask for the smallest artifact that would make the grilling concrete, and recommend what they should provide.
  2. Build a decision tree.

    • Start with goal, users, success criteria, constraints, and non-goals.
    • Then branch into architecture, data flow, ownership boundaries, operational model, risks, validation, rollout, and rollback.
    • Keep dependencies explicit: do not ask a downstream implementation question before the upstream product or architecture choice it depends on is settled.
  3. Resolve one branch at a time.

    • Ask the next highest-leverage unresolved question.
    • Include why it matters, what decision it unlocks, and your recommended answer.
    • After the user answers, restate the resolved decision and move to the next dependent branch.
    • Continue until the tree is resolved or the user stops the process.
  4. Explore instead of asking when possible.

    • Use repo discovery commands such as rg, rg --files, git status, git log, manifests, docs, tests, and nearby code.
    • Read relevant files end-to-end when they own the behavior under discussion.
    • Distinguish evidence from inference. If evidence is missing, say what you checked and ask only the remaining judgment question.
  5. Maintain a live shared-understanding ledger.

    • Confirmed decisions
    • Open decisions
    • Assumptions
    • Risks and failure modes
    • Validation or proof needed
    • Follow-up artifacts to create or update

Question Format

Use a compact format unless the user asks for a deep written audit:

markdown
Current understanding: ...

Question: ...
Why it matters: ...
Recommended answer: ...
What this unlocks: ...

When several small questions belong to the same branch, ask up to three together. Otherwise prefer one sharp question at a time.

Interview Standards

  • Be relentless about ambiguity, hidden coupling, hand-wavy success criteria, unclear ownership, and untested assumptions.
  • Push for concrete examples, exact users, exact inputs and outputs, explicit state transitions, and measurable acceptance criteria.
  • Prefer simple designs with fewer concepts, fewer modes, and clear ownership.
  • Challenge options that push complexity onto callers, operators, future maintainers, or the user.
  • Separate facts discovered from the codebase from product or strategy calls only the user can make.
  • Do not implement the plan during a grill-me session unless the user explicitly asks to switch from interrogation to execution.

Stop Conditions

Stop grilling only when one of these is true:

  • The user asks to stop, pause, or switch modes.
  • Every major branch has a resolved decision or an explicitly accepted open risk.
  • The missing information requires external access or user judgment that cannot be inferred.

End with a concise decision ledger and the next best action.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Grill Me AI skill do?

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on a design, pressure-test an architecture or implementation approach, or explicitly says "grill me".

Why use Grill Me on TypingMind?

Because you install it once and use it with any model. Grill Me is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Grill Me in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/grp06/useful-codex-skills/tree/main/grill-me. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Grill Me?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Grill Me?

As many as you like. As long as a model supports skills, you can use Grill Me with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Grill Me AI skill free?

Yes. It is published on GitHub by grp06 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇