Grilling a plan
Questions the user about a plan or decision in rounds of numbered questions with recommended answers, looks facts up itself through subagents and stops only when no decision is left assumed. Use when a plan needs stress-testing before work starts.
grilling- Author
- Matt Pocock
- Source
- mattpocock/skills/skills/productivity/grilling @ abeeaf9
- License
- MIT · Copyright (c) 2026 Matt Pocock
About this skill
What it does
The agent questions you about a plan, decision or idea until you both understand it the same way. It keeps decisions as a design tree, where each answer opens the ones that depend on it. Questions come in rounds: the whole frontier, every question whose prerequisites are settled, numbered, each with the agent's recommended answer and worded so that "yes" accepts it. A question that depends on one still open waits for the next round.
Facts are the agent's job, decisions are yours. If a question needs something from the code or the environment, the agent sends a subagent with a fresh context to find it and asks the rest of the round meanwhile. It ends when the frontier is empty, and the agent acts on nothing until you confirm agreement.
The skill is one short SKILL.md; agents/openai.yaml holds the name and short description for Codex.
When to use it, and when not
Use it before work with several linked decisions (a feature, a migration, a data model) or to stress-test your reasoning.
Skip it for small, clear tasks and unattended runs: the agent waits for your answers after every round. It writes no document; ask for a summary if needed.
How to run it
The install command below puts the whole folder in place. The agent picks the skill up by its description, for example on "grill me"; to call it yourself:
- Claude Code:
/grilling, or ask for the skill by name. - Codex:
$grilling. - Cursor: type
/in the Agent chat and pickgrilling.
Example: /grilling I want to move user sessions from Redis to Postgres. Grill me before any code.
improve-codebase-architecture, triage and wayfinder from the same pack call grilling as a step; install it alongside them.
How it differs from similar skills
Interview me also attaches a guess to each question, but asks one at a time and stops at about 95% confidence. Grilling asks a whole round at once, looks facts up itself and runs until no branch is left. Interview me also reacts to "grill me", so with both installed call the one you want by name. Brainstorming before you build goes on to approaches and a design doc; Spec-first kickoff asks up to five questions and writes a one-page spec. When someone else holds the answers, Decision questionnaire writes the questions up for them. Idea refinement and Doubt-driven development also respond to a request to stress-test a plan: the first generates variations and ends with a one-pager, the second hands the plan to a fresh-context reviewer instead of questioning you.
Install
Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.
curl -fsSL --create-dirs -o ~/.claude/skills/grilling/SKILL.md https://anymodel.org/en/skills/matt-pocock/grilling/SKILL.md -o ~/.claude/skills/grilling/LICENSE https://anymodel.org/en/skills/matt-pocock/grilling/LICENSE -o ~/.claude/skills/grilling/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/grilling/agents/openai.yaml
curl -fsSL --create-dirs -o ~/.agents/skills/grilling/SKILL.md https://anymodel.org/en/skills/matt-pocock/grilling/SKILL.md -o ~/.agents/skills/grilling/LICENSE https://anymodel.org/en/skills/matt-pocock/grilling/LICENSE -o ~/.agents/skills/grilling/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/grilling/agents/openai.yaml
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml') { $p = Join-Path "$HOME\.claude\skills\grilling" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/grilling/$f" -UseBasicParsing -OutFile $p }foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml') { $p = Join-Path "$HOME\.agents\skills\grilling" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/grilling/$f" -UseBasicParsing -OutFile $p }Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/matt-pocock/grilling/SKILL.md
SKILL.md
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.
Connect through AnyModel API
This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.
AnyModel