# Grilling

> Grills the user to stress-test a plan. Use on any grill trigger phrase.

- Skill: `forgeyclap/grilling` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx get-skill add forgeyclap/grilling`
- Raw SKILL.md: https://api.skillmd.com/api/skills/forgeyclap/grilling/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: MIT
- Author: ForgeyClap (https://skillmd.com/u/forgeyclap)
- Updated: 2026-11-14
- Page: https://skillmd.com/skills/forgeyclap/grilling

---


<!--
  Source: https://github.com/mattpocock/skills
  Pinned commit: c55ee46073ed923f86ce59a5eb3b6d895095d1b7
  Upstream path: skills/productivity/grilling/
  License: MIT (c) 2026 Matt Pocock -- full text in LICENSE next to this file
  Forge vendor note: frontmatter license: MIT key and this provenance block added; agents/openai.yaml (Codex UI metadata, no function in Claude Code) not shipped; everything else verbatim.
  Reviewed for prompt-injection patterns, hidden/zero-width/bidi/control unicode, network use and deletes by build-boss, 2026-09-24 -- clean; every upstream file sha256-verified against the pinned-commit manifest before copying.
-->

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>
```

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.

