对用户的计划、决策或想法进行层层盘问。当用户想要压力测试自己的思考，或使用任何 'grill' 触发短语时使用。
The English summary is being prepared. Showing the original description.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
持续盘问用户，直到你们达成共识。将讨论映射为一棵设计树（design tree）：每个决策都会分支出一系列依赖它的子决策。
以**轮次（rounds）**推进这棵树。**前沿（frontier）**是所有前提已确定的决策：即你现在可以问的问题，无需猜测尚未听到的答案。每一轮问完整个前沿：为每个问题编号，并给出你的推荐答案。然后等待用户的回答，再进行下一轮。
每个问题格式如下：
❓ **Q1** - **<问题标题>**：<问题正文，可以是多段，包括多个选项>
➡️ <你的推荐答案>
---
❓ **Q2** - **<问题标题>**：<问题正文，可以是多段，包括多个选项>
➡️ <你的推荐答案>
每一轮用户的回答都会重塑这棵树：已确定的决策把前沿向外推，解锁依赖它们的问题。重新计算前沿，进入下一轮。某个问题的答案依赖本轮中另一个仍未回答的问题时，它属于更晚的轮次，而不是本轮。
寻找事实是你的工作，永远不是用户的。当前沿问题需要来自环境的事实（文件系统、工具等）时，派一个子代理去查；不要问用户任何你自己能查到的东西。不要阻塞等待：正在进行的探查是一个未解决的前提，只有它下游的问题需要等子代理回报；现在就把前沿其余部分问完。决策是用户的：把每个决策摆给他们，然后等待。
当前沿为空时，会话结束：设计树的每条分支都已遍历，没有任何东西被默默假设。在用户确认你们达成共识之前，不要付诸行动。
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
从固定点（commit、branch、tag 或 merge-base）开始，沿两条轴线审查变更——规范（代码是否遵循仓库文档化的编码规范？）和规格（代码是否与原始 issue/PRD 的要求一致？）。两条审查线在并行子 agent 中运行，并以并排方式报告结果。当用户想审查一个分支、PR、进行中的变更，或要求"从 X 开始审查"时使用。
The English summary is being prepared. Showing the original description.
一场无休止的盘问，用来打磨你的计划或设计。
The English summary is being prepared. Showing the original description.
Define backend API contract standards for FastAPI services. Use when adding or refactoring HTTP/WebSocket endpoints in app/api, designing request/response schemas in app/models/schema.py, standardizing status/error contracts, and maintaining backward compatibility for clients.
The English summary is being prepared. Showing the original description.
Use when an AUTO-MAS PR is red in CI, when reproducing a dev-PR gate locally before pushing, when a workflow needs a skip-changelog or changelog-maintenance label, or when editing .github/workflows, .github/actions, scripts/changelog.py or scripts/check_reverts.py. Covers every gate that runs on a PR to dev and the exact local command for each.
The English summary is being prepared. Showing the original description.
Use when implementing, fixing, refactoring, or reviewing non-generated AUTO-MAS code, or when preparing code-style guidance, comments, docstrings, version notes, or Conventional Commit wording. Skip read-only diagnosis, explanation, exploration, and planning unless code conventions are requested.
The English summary is being prepared. Showing the original description.
Define backend data modeling standards for Python services. Use when designing or refactoring models in app/models (schema/config/task), normalizing shared fields, choosing types/defaults/validation strategy, and evolving model contracts with backward compatibility.
The English summary is being prepared. Showing the original description.