grilling

Files (2)

• SKILL.md
• openai.yaml · agents/

SKILL.md (first lines)

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>
```

When a question involves a workflow, branching decision, state transition, timeline, or set of interacting components, include a concise Mermaid diagram that makes the question easier to reason about. Place it with the question it clarifies. Use diagrams only when they materially improve understanding; they do not replace the numbered question, choices, or 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.

When the frontier is empty, present the shared understanding and ask the user to confirm or correct it. Use Mermaid diagrams to communicate any workflows, relationships, branches, or state changes in this final summary. Keep simple ideas in prose rather than forcing them into a diagram.

The session is done only after the user confirms the shared understanding: every branch of the design tree visited, nothing left silently assumed. Do not act on it before that confirmation.

From schneidenbach/skills, MIT.

More from schneidenbach/skills