grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, faces a big life decision, or uses any 'grill' trigger phrases.
- License 许可
- MIT
- 最近更新
- 2026-11-04
- Stars
- ★ 1
- 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, faces a big life decision, or uses any 'grill' trigger phrases.
- user-invocable
- false
03 SKILL.md 正文
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 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 (files in this repo, the web, etc.), look it up yourself; don't ask the user for anything you could look up. 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.
ALFRED notes (added by this template, not upstream)
- Cap each round at 3 questions when
.claude/.adhd-alwaysexists or the person's notes inAGENTS.mdsay rounds should be short. Hold the rest of the frontier for the next round. - Start each round with one line of progress, e.g.
Round 2 · 4 decisions settled · ~3 left. - Life decisions have feelings attached. Ask about the feeling when it is a real input ("how would you feel telling your manager?"), not as therapy.
- For a big, many-branched decision, and if their notes say "pages: yes",
offer once to draw the decision tree as a page (
lavish, diagram playbook): settled branches, open ones, and your recommendation on each. - When done, write the settled decision to the relevant
areas/<area>/README.mdunder "Decisions", and follow-up actions to the Inbox inqueue.md, before anyone acts.
Source: mattpocock/skills, MIT. Re-fetch to update.
04 同仓库更多 Skills
life-architect
Set up or re-tune ALFRED for this person. Default is a 3-minute quick start that learns the rest one question a day; a full interview is available. Writes context.md, current.md, queue.md, areas/ and the personal section of AGENTS.md. Use on first run (when .life/SETUP_NEEDED exists), when the person says "set up alfred", "set up my life os", "full setup", "resume setup", "re-tune" or "my life changed".
lavish
Turn complex or visual agent responses into rich, reviewable HTML artifacts the user can annotate and send feedback on, using the lavish-axi CLI. Use when about to give a plan, comparison, weekly review, diagram or table that is easier to grasp visually than as prose.
i-have-adhd
Shape output for a reader with ADHD: lead with the next action, number multi-step work, restate state across turns, suppress tangents, give specific time estimates, make wins visible. Use when the person says "adhd mode on"; stays on until "stop adhd mode".
grill-me
A relentless interview to sharpen a plan or design.