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.

Vibe codingPack: Matt Pocock's skills30 linesgrilling
Author
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 pick grilling.

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.

Claude Code — macOS, Linux
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
Codex, Cursor — macOS, Linux
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
Claude Code — Windows PowerShell
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 $p }
Codex, Cursor — Windows PowerShell
foreach ($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

Raw

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.

More from the pack Matt Pocock's skills

Code review against standards and spec

Reviews the diff since a commit, branch or tag on two axes in parallel subagents: the repo's written standards plus a baseline of Fowler code smells, and the originating spec or issue. Use when a branch or PR needs checking against its spec.

Deep module design

Fixes a shared vocabulary for deep modules (interface, seam, adapter, depth, leverage), with the deletion test, dependency categories and a design-it-twice pattern on parallel subagents. Use when designing a module's interface or deciding where a seam goes.

Diagnosing hard bugs

Diagnoses hard bugs and slowdowns by first building a fast, deterministic command that reproduces the exact symptom, then minimising it, ranking falsifiable hypotheses and adding a regression test at a real seam. Use when something fails, throws or got slow.

Domain modeling

Sharpens a project's domain language during design: challenges fuzzy or conflicting terms, writes resolved ones to GLOSSARY.md at once and offers a short ADR only for hard-to-reverse trade-offs. Use when discussing terminology or recording an ADR.

Implement a spec

Implements a spec and its tickets on one integration branch: a fresh implementer subagent per ticket in its own worktree, run in parallel along the blocking graph, then a code review and one fix pass. Use when the tickets from to-tickets are ready.

Improve codebase architecture

Finds shallow modules worth deepening, starting from the code that changes most, shows the candidates in an HTML report with before/after diagrams and grills the chosen one with you. Use when a codebase has grown hard to test or navigate.

Throwaway prototype

Builds throwaway code to answer one design question: a single-file clickable HTML demo for a state model, or several structurally different UI variants on one route switched by a URL param. Use when checking whether logic holds or how a page should look.

Coding session retrospective

Reviews a finished coding session from its logs and proposes changes to the agent's environment: navigation pointers, lint rules, pre-commit and CI checks, reviewer standards, tool use. Use when an agent session went slowly or made avoidable mistakes.

TDD with integration tests

Drives test-first work through public interfaces: agrees the seams to test with the user, runs one red-green cycle per test, mocks only at system boundaries and leaves refactoring to review. Use when building a feature or fixing a bug test-first.

Conversation to spec

Turns the current conversation and codebase into a spec with user stories, implementation and testing decisions, and publishes it to the issue tracker as ready-for-agent, without interviewing the user. Use when a discussed feature needs writing up.

Spec to tickets

Splits a spec, plan or conversation into tracer-bullet tickets, vertical slices that each fit one agent session, with blocking edges, and publishes them as local files or tracker issues. Use when work is too big for one session and needs a task graph.

Issue and PR triage

Triages issues and external PRs on the tracker: gives each a category and a state, checks for existing code and past rejections, reproduces bugs and writes agent briefs for ready work. Use when a maintainer works through incoming issues and PRs.

Wayfinder for huge work

Charts work too big for one agent session as a map issue with child decision tickets on the tracker, then resolves one ticket per session until the route to the goal is clear. Use when a large effort has open questions that block a spec or plan.

Bash wizard for manual steps

Generates an interactive bash script that walks a person through manual steps such as dashboard setup, API keys and CI secrets, opening each URL and saving values to .env and GitHub secrets. Use when setup or a migration needs steps only a human can take.

Git guardrails for Claude Code

Installs a Claude Code PreToolUse hook that stops the usual forms of git push, reset --hard, clean -f, branch -D and checkout or restore of the whole tree, for one project or all, then tests it. Use when you want a safety net against an agent pushing or discarding work on its own.

Migrate tests to shoehorn

Replaces as and as unknown as casts in TypeScript tests with fromPartial and fromAny from @total-typescript/shoehorn, adds the imports and runs the type check. Use when tests fake whole objects or cast partial test data to satisfy the compiler.

Pre-commit hooks setup

Sets up Husky and lint-staged in a Node repo so each commit runs Prettier on staged files, then the typecheck and test scripts, matched to the lockfile, and makes the first commit through the hook. Use when a repo has no commit-time checks.

Teach me a topic

Runs a multi-session course in the current folder: a mission, trusted sources, short HTML lessons with quizzes, reference sheets and learning records that set the next lesson. Use when the user wants to learn a topic over time, not get one answer.

Decision questionnaire

Writes a Markdown questionnaire for someone who holds knowledge the user lacks, after asking only who it goes to and what answers are needed, with the most important questions first. Use when a decision depends on facts from another person.

Writing for agents

Gives the rules for writing text agents read: skill descriptions as context pointers, what to keep inline and what to move to a separate file, completion criteria, leading words and pruning. Use when creating or editing a skill, AGENTS.md or CLAUDE.md.