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.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
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.
Each question should be formatted like so:
Question **Q1** - **<question title>**: <question body, might be multiple paragraphs, including multiple choices>
Recommended: <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.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Create and maintain AGENTS.md files for project onboarding and grounding. Use when initialized in a new project, when project structure changes significantly, or when creating subfolder-level AGENTS.md files for complex monorepos.
日本語の概要は準備中です。原文の説明を表示しています。
Audit and update an arbitrary codebase to follow the Code.mil federal open-source licensing model (MIT with 17 U.S.C. Section 105 disclaimers and INTENT.md), including CRAN/R package DESCRIPTION setup.
日本語の概要は準備中です。原文の説明を表示しています。
Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".
日本語の概要は準備中です。原文の説明を表示しています。
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes - Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
日本語の概要は準備中です。原文の説明を表示しています。
Reads Copilot conversation history and extracts executive-ready success stories. Use when the user asks to study prior Copilot sessions, summarize what was done before, mine evidence, or quantify time, cost, risk, and priority alignment from GitHub Copilot history in any workspace or repository.
日本語の概要は準備中です。原文の説明を表示しています。
Comprehensive investigation of complex multi-domain narratives (technology, theology, policy, finance). Systematically decouples factual claims from speculation through iterative verification, multi-source comparison, and contradiction resolution. Use for investigations requiring institutional knowledge, historical context, and handling of conflicting incentives.
日本語の概要は準備中です。原文の説明を表示しています。