grilling

Files (2)

• SKILL.md
• openai.yaml · agents/

SKILL.md (first lines)

> **框架本地化技能**：以上游 `skills/skills/productivity/grilling` 为基础，由 cg-work 维护本地调整；不逐字节同步上游，也不登记为原始镜像。上游变更需评估后再合并。

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.

## Visible preflight

Before starting the first grilling round, show the user a decision preflight brief. It must state the risk (`low`, `medium`, `high`, and `irreversible` when applicable), the assumptions already made, the recommended path, meaningful alternatives, and whether their confirmation is required. This is the Agent's recommendation, not a user decision.

Do not silently invoke grilling for a high-risk decision. If the preflight is `high` or `irreversible`, stop after the brief and wait for explicit confirmation to begin the interview. A `low` or reversible `medium` preflight may proceed after the brief when grilling was already requested or the workflow explicitly selected 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.

From GFigting/carry-god, MIT.

More from GFigting/carry-god