Skip to main content
affpapa.org
RU EN
skill Claude Code

grilling — Claude Code skill: what it does, how to install

Stress-test a plan, decision, or idea through structured rounds of questions. Use it when you need to expose assumptions before acting.

Install into Claude Code · Plugin marketplace All methods and platforms ↓ 
/plugin marketplace add mattpocock/skills
/plugin install mattpocock-skills@mattpocock
Open on GitHub

What grilling does

This skill builds a decision tree, where each answer opens the questions that depend on it. In each round, it asks every question whose prerequisites are settled, numbers them, and gives a recommended answer. It then waits for your replies before recalculating the next round.

It sends sub-agents to find facts in the filesystem or available tools, while leaving decisions to you. It does not act until the tree is complete and you confirm shared understanding. Install it for a disputed plan; for a small task with clear inputs, the questioning is likely unnecessary.

What it helps with

  • stress-test assumptions in a plan
  • break a decision into dependent choices
  • research environment facts with sub-agents
  • separate user decisions from factual checks
  • agree on a plan before acting

Example prompts for the agent

  • "Stress-test my launch plan and ask the questions in rounds."
  • "Use grilling to examine this architecture decision."
  • "Grill this idea and do not act until we agree on the details."

How to install grilling

1Plugin marketplace

/plugin marketplace add mattpocock/skills
/plugin install mattpocock-skills@mattpocock

This installs the whole mattpocock-skills plugin with all its skills

2Skills CLI (Vercel)

npx skills add mattpocock/skills --skill grilling -a claude-code

3Manually: put the files in place

~/.claude/skills/grilling/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/grilling/

From the same set32

The whole set →
grill-me Matt Pocock grill-me interviews you about a plan or design to expose gaps and sharpen decisions. Use it before implementation starts. Claude Code 1,424,476installs grill-with-docs Matt Pocock This skill interviews you about a plan or design and creates ADRs and a glossary along the way. Use it when decisions need sharper definition. Claude Code 1,219,756installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs setup-matt-pocock-skills Matt Pocock This skill configures a repository for Matt Pocock's engineering skills by setting its issue tracker, triage labels, and domain docs layout. Run it before using the other skills. Claude Code 1,052,851installs handoff Matt Pocock Creates a handoff document from the current conversation so another agent can continue the work. Use it when a task moves to a new session or agent. Claude Code 1,038,491installs triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. Claude Code 990,453installs prototype Matt Pocock Creates throwaway prototypes for checking state logic or exploring UI before committing the decision to the main codebase. Claude Code 986,201installs

Similar

find-skills vercel-labs Discovers and installs agent skills from skills.sh directly inside your coding assistant. Handy when you need domain-specific workflows for a project. Claude Code CX Codex Cursor +1 4,000,000installs

Questions about grilling

How do I install grilling in Claude Code?

Run npx skills add mattpocock/skills --skill grilling -a claude-code in Claude Code.

What does grilling do?

It interviews you about a plan, decision, or idea through a decision tree. It asks questions only after their prerequisites have been settled.

When will grilling act on the plan?

It waits until the decision tree has no open branches and you confirm shared understanding. Before that, it collects decisions and can delegate fact-finding to sub-agents.

Source text

SKILL.md · MIT 
---
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 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.

© Matt Pocock · MIT · mattpocock/skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor
Nutra.Club

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor