Grilling

Community

devton

grilling

Deep Socratic grilling and interrogation protocol to stress-test assumptions, clarify non-functional requirements, and resolve edge cases before design.

Overview

Publisher	devton
Repository	`agentic-workflow-blueprint`
Skill name	`grilling`
Stars	73
Forks	4
Bundled files	Instructions only
Links	Skill source Repository

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.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by devton on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/devton/agentic-workflow-blueprint/tree/main/workflows/mattpocock/grilling
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/devton/agentic-workflow-blueprint/tree/main/workflows/mattpocock/grilling

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/devton/agentic-workflow-blueprint.git /tmp/agentic-workflow-blueprint
mkdir -p .claude/skills
cp -r /tmp/agentic-workflow-blueprint/workflows/mattpocock/grilling .claude/skills/grilling

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Grilling 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 Grilling 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 Grilling 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.

agentic-workflows-blueprint.workflow.mattpocock.grilling

Goal

Systematically interrogate assumptions, edge cases, trade-offs, and operational boundaries through intensive Socratic questioning before domain modeling or code implementation.

Scope

Applies to: Feature requirement clarification, ambiguous requests, architectural trade-offs, and high-impact changes.
Does not cover: Direct code implementation or initial codebase mapping (use /wayfinder).

Triggers

"/grilling"
"Grill user on feature details"
"Challenge feature assumptions"
"Socratic grilling session"

Inputs

wayfinderBrief or userPrompt: Orientation brief or initial feature request.
existingRootDoc: Main project instruction document (AGENTS.md, CLAUDE.md).

Invariants (Guardrails)

Mandatory Socratic Interrogation Gate: Present 3–7 strategic questions covering Scope, Edge Cases, Data Integrity, Security, and Operational Constraints. Do NOT proceed without explicit user responses.
Option-Driven Questioning: Present questions with clear trade-offs (Pros, Cons, Default Option) so choices are actionable.
Strict UUIDv7 Ordering Invariant: Enforce time-sortable UUIDv7 for resource identifiers in data model decisions.
Binding Decision Log: Record all user answers and trade-off resolutions into a binding decision log to govern domain modeling and spec creation.

Procedure

1) Analyze Wayfinder & Request Context

Review the orientation brief (wayfinder.md) and original request to extract ambiguous requirements, boundary decisions, and risk areas.
Identify implicit assumptions that must be explicitly confirmed.

2) Formulate Categorized Grilling Questions

Formulate 3 to 7 targeted questions across key dimensions:

Category A: Scope & Boundary Limits — What is strictly in vs. out of scope for this iteration?
Category B: Edge Cases & Failure Modes — How to handle network timeouts, concurrency conflicts, invalid payloads, or missing data?
Category C: Data Contracts & Invariants — Permitted mutations, state transition guards, UUIDv7 identity rules, and audit logging.
Category D: Performance & Security Constraints — Rate limiting, RBAC permissions, zero-downtime deployment requirements, and migration strategy.

Format each question with:

Context & Problem Statement
Option 1 (Pros / Cons)
Option 2 (Pros / Cons)
Recommended Default Option

3) Present Grilling Interview

Present the formatted questions clearly to the user.
Wait for explicit user answers. Do NOT proceed to domain modeling or spec writing until grilling responses are recorded.

4) Synthesize Binding Decision Log

Summarize user choices and confirmed trade-offs into a binding Decision Log.
Store decision log in conversation context and append to walkthrough.md.

Outputs

Binding decision-log.md stored in conversation context and walkthrough.md.

Review gate

At least 3 to 7 targeted grilling questions presented with trade-offs.
Explicit user responses received and recorded.
UUIDv7 identity standard confirmed for resource data models.
Binding decision log generated to govern domain modeling and specification.

References

../../../SKILL.md
../wayfinder/SKILL.md
../domain-modeling/SKILL.md
../../embed-aihero-radioactive/SKILL.md

Frequently asked questions

What does the Grilling AI skill do?

Deep Socratic grilling and interrogation protocol to stress-test assumptions, clarify non-functional requirements, and resolve edge cases before design.

Why use Grilling on TypingMind?

Because you install it once and use it with any model. Grilling 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 Grilling in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/devton/agentic-workflow-blueprint/tree/main/workflows/mattpocock/grilling. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Grilling?

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 Grilling?

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

Is the Grilling AI skill free?

It is published on GitHub by devton. Check the repository for licensing terms. 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

Doc Coauthoring

anthropics

OrganizationPopular

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This…

Authoring Skills

How to create and maintain agent skills in .agents/skills/. Use when creating a new SKILL.md, writing skill descriptions, choosing frontmatter fields, or deciding what content belongs in a skill vs…

Dce Edge

DCE-safe require() patterns and edge runtime constraints. Use when writing conditional require() calls, guarding Node-only imports (node:stream etc.), or editing define-env-plugin.ts / app-render /…

Gh Stack

Manages stacked PRs and splits multi-part work into reviewable branches with gh-stack. Use for stack creation, viewing, edits, push, submit, sync, rebase, merge, or checkout; when asked to split or…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

agentic-workflows-blueprint.workflow.mattpocock.grilling

Goal

Scope

Triggers

Inputs

Invariants (Guardrails)

Procedure

1) Analyze Wayfinder & Request Context

2) Formulate Categorized Grilling Questions

3) Present Grilling Interview

4) Synthesize Binding Decision Log

Outputs

Review gate

References

Frequently asked questions

Related AI Skills

Set up your own AI workspace now