AGENT SKILL

grilling

Interviews the user relentlessly about a plan, design, decision, or idea until every branch of the decision tree is resolved and nothing is silently assumed. Use when the user says "grill me" or wants to stress-test their thinking, before building something whose requirements are still fuzzy, and when another skill needs a structured interview.

License 许可
Apache-2.0
最近更新
2026-11-13
Stars
★ 0
Forks
1

01 前言 Front Matter

name
grilling
description
Interviews the user relentlessly about a plan, design, decision, or idea until every branch of the decision tree is resolved and nothing is silently assumed. Use when the user says "grill me" or wants to stress-test their thinking, before building something whose requirements are still fuzzy, and when another skill needs a structured interview.

02 资源文件 1

03 SKILL.md 正文

Grilling

Interview the user until you share an understanding of the plan. Map it as a design tree: each 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. Ask the whole frontier in one round, give your recommended answer for each, then wait. A question that depends on another question still open in this round belongs to a later round.

A round is done when every question in it has an answer, or the user has explicitly deferred it. Each round reshapes the tree: settled decisions push the frontier outward and unblock what depended on them. Recompute the frontier and ask the next round.

Facts are yours; decisions are the user's

When a frontier question needs a fact from the environment (the code, the docs, a config value, how a tool behaves), find it yourself, by reading or by dispatching a subagent. Only the questions downstream of a running lookup wait for it; ask the rest of the frontier now. Put every decision to the user and wait for their answer. An interview is the one place where asking is the work: the harness rule to ask only when necessary still holds for facts, never for the decisions themselves.

Asking a round

Claude Code: ask through AskUserQuestion. Each call takes up to 4 questions, each with a short header and 2-4 options, and the user can always type their own answer instead. Put your recommended answer first, labelled "(Recommended)", and make the other options genuinely different directions; when more than 4 candidates exist, offer the strongest 4. The call waits for the answers, so:

  • Write any question with no sensible preset answers (a name, a number, a free-form constraint) as plain text in the same message, before the call, and collect its answer alongside the picker's.
  • A round with more than 4 picker questions takes consecutive calls; ask the most consequential questions first.

If AskUserQuestion is unavailable (a headless run, a subagent, or the user declined it), use the plain-text format below.

Codex and other hosts: ask the round as numbered plain text:

Q1 — <question title>: <question, with the options if there are any>
   Recommended: <your answer and the one-clause reason>

Q2 — ...

Done

The session is done when the frontier is empty: every branch visited, and every assumption you are relying on has been stated to the user and confirmed or corrected. Summarize the decisions, and act on them only after the user confirms the summary matches their understanding.

04 同仓库更多 Skills

dougborg
dougborg/harness-kit

teach

Teach yourself a topic over several sessions, with lessons, references, and a record of what you've learned.

教师与教育
★ 0
dougborg
dougborg/harness-kit

svg-logo-designer

Generate SVG logos with multiple concepts, layouts, and color variations.

图像与多媒体
★ 0
dougborg
dougborg/harness-kit

documentation-writer

Writes and revises human-facing documentation — READMEs, contributor and setup guides, reference pages, architecture notes, CLAUDE.md, and changelog entries. Covers picking the right document type for the question being asked, structuring for skimming, writing examples that actually run, and keeping docs from going stale. Use when creating or rewriting docs, when a README has drifted from the code, or when deciding where a piece of information belongs. For SKILL.md and agent files, use /skill-writer instead.

内容创作者写作与文案
★ 0
dougborg
dougborg/harness-kit

adhd-mode

Shapes every response for a reader with ADHD: the next action first, numbered steps, progress restated each turn, tangents held back, concrete time estimates, wins made visible. Stays on for the rest of the session until the reader says "stop adhd mode". On Claude Code, the harness-kit:adhd output style does the same without invoking this skill.

★ 0
dougborg
dougborg/harness-kit

wait-what

That last message didn't land: re-explain it with the missing context.

★ 0
dougborg
dougborg/harness-kit

to-questionnaire

Turn a decision you can't make alone into a questionnaire for the one person who can answer it, filled in async or together in a meeting.

★ 0