AGENT SKILL

grilling

Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

License 许可
AGPL-3.0
最近更新
2026-11-14
Stars
★ 0
Forks
0

01 前言 Front Matter

name
grilling
description
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.

02 资源文件 2

03 SKILL.md 正文

A prompt or brief naming this skill is its invocation.

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.

Read the contribution guide's Triage inference test and owner-question route before adding a question to the frontier. Reuse recorded answers with their dated sources, record qualifying inferences in the guide's named list, and investigate missing facts. When the guide is missing, use the fallback below.

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 frontier in rounds: number each question and give your recommended answer. Keep each round short: when the frontier holds more questions than the user can weigh at once, ask the ones that unblock the most and leave the rest for the next round. 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. Put the decisions the inference test leaves open to the user and wait for their answers.

The interview is done when the frontier is empty: each decision is recorded or listed as a qualifying inference, with no required owner answer missing under the guide's Triage rules. Reuse recorded approval. A composite skill can then continue to its publication step.

Without a contribution guide

Only when the guide is missing, use this inference boundary: cite the owner's approved goal, a recorded decision or wish, or the owner's quoted words, each with its date. Keep an inference reversible within the approved goal and scope; it adds no public name or breaking policy and chooses no persistent default, limit, timeout or fallback. List qualifying answers under Inferred, listed for the owner, with dated sources and owner veto. Ask the user directly about one-way doors and unchosen values, including every choice failing that test. Retain the owner's grill answers and plan approval as gates.

Reads

  • CONTRIBUTING.md, relative to the repository root: the Triage inference test and owner-question route. If missing, use Without a contribution guide.

04 同仓库更多 Skills