Skills mattpocock skills Engineering workflow
grilling
- Use it when:
- You have a plan, design or decision you haven't fully thought through.
- It does:
- Asks every question it can in numbered rounds, each with its recommended answer.
- You get:
- A shared understanding, with nothing left assumed, before any work starts.
- Also called:
- grill-me, a shortcut you call by name.
Skill 5 of 24 in the Engineering workflow bundle, after grill-me and before domain-modeling.
TL;DR
The agent treats your plan as a tree of decisions, where each decision opens further ones. Each round, it asks every question whose prerequisites are already settled: numbered, each with the answer it recommends, and worded so that "yes" accepts it. Your answers settle those branches and unlock the next round. Facts it can find in your files or tools, it looks up itself, with a subagent if needed, instead of asking you; the decisions stay yours. It ends when every branch has been visited, and doesn't act on the plan until you confirm you're aligned.
Summarizes the skill at 5beb35b. Its SKILL.md has changed by 5 words since.
npx skills add https://github.com/mattpocock/skills --skill grilling skills.sh pageSource on GitHubAll skills from mattpocock/skills
- Total Downloads
- 1,075,383 on skills.sh, Nov 9, 2026
- Repo stars
- 318,714 mattpocock/skills
- First seen
- Jun 4, 2026 on skills.sh
Weekly values
| Week to | Installs |
|---|---|
| Sep 21 | 49,789 |
| Sep 28 | 44,480 |
| Oct 5 | 46,132 |
| Oct 12 | 61,775 |
| Oct 19 | 52,706 |
| Oct 26 | 47,202 |
| Nov 2 | 46,289 |
| Nov 9 | 40,707 |
| Category |
Make the agent question you and write the plan down before it writes code. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills. |
|---|---|
| Type |
A multi-step process the agent follows: interview, debug, run a TDD loop, review. |
| Effect |
Adds no side effects of its own. It shapes how the agent thinks, writes or reviews. Guidelines and routers are always effect:none, even when the task they support edits code. |
| Needs |
Instructions only. Works in any agent that supports skills. |
| Publisher |
Everyone else. Unverified vendor claims default to community. |
| Topics |
SKILL.md
From mattpocock/skills at a496f55. Checked daily, last changed Oct 30, 2026.
Frontmatter
name: grilling
description: Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.Interview the user relentlessly until you reach a shared understanding. Map this as a design tree: every decision branches into the decisions that hang off it.
Work the tree in rounds. The frontier is every decision whose prerequisites are already settled: the questions you can ask now without guessing at answers you haven't heard yet. Ask the whole frontier in one round: number each question and give your recommended answer. Then wait for the user's answers before the next round.
Format a round like so:
❓ **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
---
❓ **Q2** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
➡️ <your recommended answer>
Word each question so "yes" accepts your recommended answer.
Each round the user answers reshapes the tree: settled decisions push the frontier outward and unblock questions that depended on them. Recompute the frontier and ask the next round. A question whose answer depends on another question still open in this round belongs to a later round, not this one.
Finding facts is your job, never the user's. When a frontier question needs a fact from the environment (filesystem, tools, etc.), dispatch a sub-agent with a fresh context window to find it; don't ask the user for anything you could look up yourself. Don't block on it: a running exploration is an unsettled prerequisite, so only the questions downstream of it wait for the sub-agent to report; ask the rest of the frontier now. The decisions are the user's: put each to them and wait.
The session is done when the frontier is empty: every branch of the design tree visited, nothing left silently assumed. Do not act on it until the user confirms you have reached a shared understanding.