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
- MIT
- 最近更新
- 2026-11-04
- 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.
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 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.
04 同仓库更多 Skills
study
Build study material for a topic the developer wants to understand before writing about it — a guide in docs/study/<slug>/, tracked as a study task. Use when the developer asks to study a topic, to turn a blog candidate or a report topic into study material, or to prepare before writing a post. Never writes the post.
split-markdown
Split a Markdown file that reached the size limit (50 KiB) into a folder of its subjects — one file per top-level section, a README.md index, every inbound link updated — the way the rules prescribe. Use when check-md-size or the pre-commit hook refuses a file, or when the developer asks to split a Markdown file that grew too large. Shows the plan and writes nothing until the developer agrees.
review
End-of-day review with the developer — show each task worked today against its done criterion, and record the developer's acceptance or reopen it with what is missing. Use when the developer asks to review the day or close out today's work, or as the first part of the end-of-day block.
retro
The day's retrospective with the developer — report what was discovered, what surprised, what went wrong and what was decided without asking, take the developer's own "what I want to learn" line and elaborate on it, grounded in the day's work, and write the day's journal entry. Use after the review at the end of the day, or when the developer asks for the retro. Never skipped.
refine
Refinement with the developer — grill the next candidate items or a new idea, propose stories and tasks in the tracker, and agree or reject them on the developer's word, so tomorrow's planning has agreed tasks to pick. Use after the retro at the end of the day, or when the developer asks to refine or plan the next work.
project-report
A read-only report on the project — overview, decisions documented and implicit, critical areas, quality and tests, a study list by risk, and topics worth writing about — written to docs/REPORT.md, which git ignores. Use when the developer asks for a project report, an overview of the codebase, what to study, or what is worth writing about.