---
name: grill-me
description: Interview the user to stress-test a plan or decision, one independent set of questions at a time.
license: MIT
compatibility: TensorSharp or TensorAgent; workspace file tools required for saved artifacts and code changes.
metadata:
  source: mattpocock/skills
  revision: 49dd158d1076134a641b33efb035946536778336
---

# Plan interview

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.), use the available file tools to find it (delegate only if an agent tool is offered); 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.

## Host capabilities

Use only tools offered in this conversation. Read supplied workspace files with `read_file`; create artifacts with `write_file` and edit existing files with `apply_patch` when offered. Do not invent a `Skill` tool. After creating any file, include its exact Markdown download link from the tool result in your answer, even when the rest of your answer asks the user a decision question. Never replace that link with a filename or a claim that the file exists. If a required file, workspace, executable, or tool is unavailable, explain the limitation and do not claim it ran. A user's already-agreed scope and test interface count as agreement; do not ask the same question again. Apply the workflow directly after reading it; keep progress narration brief.