Grill Me logo

Grill Me

Community
belos-street
grill-me

Iteratively grill users to clarify vague requirements via layered questioning. Use when requirements are ambiguous, incomplete, or need refinement before implementation.

Overview

Publisherbelos-street
Repositorystock-analytics-agent
Skill namegrill-me
Stars
57
Forks
9
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by belos-street 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/belos-street/stock-analytics-agent/tree/main/.agents/dev/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/belos-street/stock-analytics-agent.git /tmp/stock-analytics-agent
mkdir -p .claude/skills
cp -r /tmp/stock-analytics-agent/.agents/dev/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

Iteratively grill users to clarify vague requirements before any implementation begins.

This skill defines two modes for requirement clarification:

  • /grill-me: Pure questioning flow — no file writes, chat-only, outputs a structured summary at the end.
  • /grill-with-docs: Full questioning flow + automatically creates/incrementally updates a root CONTEXT.md file to persist business rules, terminology, and requirement boundaries.

Both modes follow the same systematic layered questioning approach covering business goals, input/output specs, edge cases, and hard constraints.

When to Apply

Reference these guidelines when:

  • Requirements are vague, incomplete, or self-contradictory
  • A feature request lacks clear acceptance criteria
  • Multiple interpretations of a requirement exist
  • Building a feature that touches multiple systems or stakeholders
  • Before writing any code to ensure shared understanding

Modes

ModeDescriptionReference
/grill-mePure questioning, no file writes, structured summary outputgrill-me
/grill-with-docsFull grill + auto-create incremental CONTEXT.md persistencegrill-with-docs

Core Methodology

Four-Layer Questioning

The questioning follows a strict layered sequence:

LayerFocusKey Questions
1. Business GoalCore problem, end users, usage scenariosWhat core problem? Who are the users?
2. Input & OutputData format, parameters, display/storageWhat inputs/outputs? Format constraints?
3. Edge & ExceptionEmpty data, errors, conflicts, failuresHow to handle edge cases? Fallback logic?
4. Hard ConstraintsTech stack, performance, security, acceptanceWhat are the limits? Acceptance criteria?

Termination Rule

  • Continue layered questioning until the user explicitly states "all details are clear"
  • Do NOT stop based on your own judgment of completeness
  • After termination, output a structured Requirement Clarification Summary

Self-Check Before Summary

Before presenting the Requirement Clarification Summary, verify all checklist items are resolved:

  • Business Goal answered — core problem, target users, main scenario
  • Input/Output specified — data format, parameters, display/storage
  • Edge cases addressed — empty data, errors, conflicts, failures
  • Tech constraints documented — stack, performance, security
  • Acceptance criteria defined — verifiable, testable standards
  • Terminology aligned — no ambiguous or inconsistent terms

If any item is unchecked, continue questioning. Do NOT proceed to summary until all are resolved.

Hard Rules

  1. Never provide code, interface design, database schema, or architecture plans during the entire grill process.
  2. Do not make assumptions to fill ambiguous descriptions — keep asking.
  3. Do not read or modify project files unless using /grill-with-docs mode.

Output: Requirement Clarification Summary

After the user confirms "all details are clear" and self-check passes, output the summary using this exact template:

markdown
## Requirement Clarification Summary

**Feature:** [feature name]

### 1. Business Goal

- **Core problem:** [what problem does this solve]
- **Target users:** [who are the end users]
- **Main scenario:** [core user operation and usage scenario]

### 2. Data Spec

- **Inputs:** [parameters, formats, constraints]
- **Outputs:** [results, display location, storage]

### 3. Edge & Exception Handling

| Scenario | Behavior |
|----------|----------|
| Empty data | [fallback] |
| Network failure | [fallback] |
| Permission denied | [fallback] |
| Concurrent conflict | [fallback] |
| Other | [additional cases] |

### 4. Constraints

- **Tech stack:** [languages, frameworks, versions]
- **Performance:** [latency, throughput, scale targets]
- **Security:** [auth, data protection, compliance]
- **Browser/Platform:** [compatibility requirements]

### 5. Acceptance Criteria

- [ ] [criterion 1 — verifiable]
- [ ] [criterion 2 — verifiable]
- [ ] [criterion 3 — verifiable]

### 6. Terminology Dictionary

| Business Term | Code Naming | Description |
|---------------|-------------|-------------|

Transition Protocol

Once the summary is presented, propose the next step based on requirement maturity:

Requirement StateRecommended Next Step
Design exploration neededInvoke brainstorming
Requirements fully clear, multi-step taskInvoke writing-plans
Requirements simple, single-stepProceed directly to implementation

Transition message template:

"Requirements have been clarified and documented above. Based on the maturity of these requirements, I recommend: [next step]. Shall I proceed?"

Quick Reference

Key Principles

  • Question limit per round: 3-5 questions only
  • Layers must be followed in order: Business Goal → Input/Output → Edge/Exception → Constraints
  • Termination: Only when user says "all details are clear"
  • No code, no design, no architecture until grill is complete

CONTEXT.md Structure (grill-with-docs)

The persisted document follows 7 sections:

  1. Core Business Goal
  2. User Roles & Core Usage Scenarios
  3. Data Spec: Input / Output
  4. Edge & Exception Handling Rules
  5. Tech Constraints, Security & Performance Requirements
  6. Feature Acceptance Criteria
  7. Project Terminology Dictionary (Business Term → Unified Code Naming → Description)

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?

Iteratively grill users to clarify vague requirements via layered questioning. Use when requirements are ambiguous, incomplete, or need refinement before implementation.

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/belos-street/stock-analytics-agent/tree/main/.agents/dev/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 belos-street 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 👇