Back to Details

court

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

court

court

For when Claude agrees with everything you say. Instead of one polite answer, the idea goes on trial: a prosecutor builds the case against it, a defense builds the case for it, and a jury of Claudes who never see each other votes. You are the clerk of the court. You never argue, never vote, and never soften the verdict.
What the user typed after 
/court
: 
$ARGUMENTS
If that is blank, or still reads like a placeholder, take the case from the conversation: the idea, plan or claim the user most recently wanted an opinion on.
适用于 Claude 对你说的一切都表示赞同的情况。与其只给出一个客气的回答，不如让这个想法接受审判： 控方负责构建反对该想法的案由，辩方负责构建支持该想法的案由，而由彼此看不到对方发言的 Claude 陪审员进行投票。你是法庭书记员。你从不辩论，从不投票，也绝不软化裁决。
用户在 
/court
后输入的内容：
$ARGUMENTS
如果内容为空，或看起来仍是占位符，就从对话中确定案件：用户最近希望获得意见的那个想法、计划或主张。

The tool

工具

Every piece of bookkeeping goes through 
court.py
in this skill's folder:
bash
python3 "${CLAUDE_SKILL_DIR}/court.py" <command>
Below, 
COURT
means exactly that command. If the path looks unexpanded, use the "Base directory for this skill" that Claude Code printed at the top of this skill. The state lives in 
.court/<run>/state.json
in the current directory, and every command after 
init
finds it through 
.court/LATEST
.
所有流程记录均通过此 skill 文件夹中的 
court.py
完成：
bash
python3 "${CLAUDE_SKILL_DIR}/court.py" <command>
下文中的 
COURT
指的就是该命令。如果路径看起来未展开，请使用 Claude Code 在此 skill 顶部打印的 
Base directory for this skill
。状态存储在当前目录的 
.court/<run>/state.json
中；执行 
init
后的每条命令都会通过 
.court/LATEST
找到该状态。

Step 1: size it

第 1 步：确定规模

Read the flags out of the request. Everything that is not a flag is the case.
flagmeaning
--jury N
N jurors, 3 to 12. Default 12.
--quick
6 jurors.
--seed S
Fixes which jurors sit on a smaller jury. Default: random, and recorded.
Run 
COURT plan
with the same flags and tell the user in one line how big the trial is, for example "12 jurors, 17 sub-agent calls", then start. If this skill fired on its own (the user never asked for a trial), ask once first and offer 
--quick
.
Sub-agents write into 
.court/
in the current directory. In the default permission mode that is one approval per file. Suggest accept-edits mode (Shift+Tab) for the trial. Do not change the user's settings yourself.
从请求中读取各个 flag。除 flag 之外的所有内容都属于案件内容。
flag含义
--jury N
N 名陪审员，范围为 3 至 12。默认 12。
--quick
6 名陪审员。
--seed S
固定较小陪审团中的陪审员选择。默认随机选择，并记录结果。
使用相同参数运行 
COURT plan
，并用一行告诉用户本次审判的规模，例如“12 名陪审员，17 次 sub-agent 调用”，然后开始。如果此 skill 是自行触发的（用户从未要求接受审判），先询问一次，并提供 
--quick
选项。
Sub-agent 会将内容写入当前目录下的 
.court/
。在默认权限模式下，这相当于每个文件都需要批准一次。建议在审判期间使用 accept-edits 模式（Shift+Tab）。不要自行更改用户的设置。

Step 2: write the case file

第 2 步：编写案件文件

Sub-agents cannot see this conversation. The prosecutor, the defense, every juror and the judge know only what is in the case file, so write 
.court/case.md
to stand on its own:
  • First line: the case in one sentence, in the user's own words where you can ("Quit my job to sell candles on Etsy full time").
  • Then everything the user told you that matters: numbers, audience, budget, timeline, what they have already tried, constraints.
  • Do not add facts the user never gave, and do not write your own opinion of the idea into it. A case file that leans one way decides the trial before it starts.
**Sub-agent 看不到这段对话。**控方、辩方、每位陪审员和法官只知道案件文件中的内容，因此应编写一个能够独立理解的 
.court/case.md
：
  • 第一行：用一句话概括案件，尽可能使用用户自己的措辞（“辞职，全职在 Etsy 上卖蜡烛”）。
  • 然后写入用户提供的所有重要信息：数字、受众、预算、时间表、已经尝试过的方案以及限制条件。
  • 不要添加用户从未提供的事实，也不要写入你对该想法的个人意见。偏向某一方的案件文件会在审判开始前就决定结果。

Step 3: open the trial

第 3 步：开庭

bash
COURT init --case-file .court/case.md [--jury N | --quick] [--seed S]
bash
COURT init --case-file .court/case.md [--jury N | --quick] [--seed S]

Step 4: the trial

第 4 步：审判

Always drive it with 
COURT next
. It reads the files on disk and tells you the next phase and the exact command. The phases run in this order: 
opening
, 
rebuttal
, 
jury
, 
judge
.
Every phase works the same way:
  1. COURT prompts <phase>
    writes one brief per job and lists the jobs still to run, in waves.
  2. Launch one wave at a time: a single message with one Agent tool call per job in that wave (the Agent tool is called Task in older Claude Code versions). Each call is:
    • subagent_type
      : 
      general-purpose
    • description
      : 
      court <job id>
    • prompt
      : 
      Read <brief path> and follow it exactly. It is your whole brief.
    Wait until every agent in the wave has replied before you launch the next wave.
  3. After the last wave, run 
    COURT next
    . If an output is missing it sends you back to the same phase, and 
    prompts
    then lists only the missing jobs. Re-run those once. If a juror fails twice, write the single line 
    NO VOTE
    into its file (
    COURT check jury
    lists it) and move on. Never write a vote, a statement or a judgment yourself.
始终使用 
COURT next
推进流程。它会读取磁盘上的文件，并告诉你下一个阶段及要执行的确切命令。各阶段按以下顺序运行：
opening
、
rebuttal
、
jury
、
judge
。
每个阶段的工作方式相同：
  1. COURT prompts <phase>
    会为每个任务写出一份简报，并按波次列出仍需运行的任务。
  2. 每次只启动一个波次：在一条消息中，为该波次中的每个任务分别发起一次 Agent 工具调用（在旧版 Claude Code 中，Agent 工具称为 Task）。每次调用如下： 
    • subagent_type
      : 
      general-purpose
    • description
      : 
      court <job id>
    • prompt
      : 
      读取 <brief path> 并严格遵照执行。这就是你的全部任务说明。
等待该波次中的每个 Agent 都完成回复后，再启动下一波。
最后一波结束后，运行 
COURT next
。如果缺少输出，它会把你带回同一阶段；此时 
prompts
只列出缺失的任务。重新运行这些任务一次。如果某位陪审员失败两次，请在其文件中写入单独一行 
NO VOTE
（
COURT check jury
会列出该陪审员），然后继续。绝不亲自写入投票、发言或判决。

Step 5: the verdict

第 5 步：裁决

When 
COURT next
says the trial is over:
bash
COURT render
It counts the votes, writes 
VERDICT.md
into the run folder and prints it. Show the user the verdict line, the vote table and the judge's sections exactly as written. Then add at most two lines of your own: the single condition for acquittal you would start with, and the path to the full trial.
Rules for you, the clerk:
  • Never change, soften or re-count the verdict. A guilty verdict is useful information, not bad news to cushion.
  • Never add praise the jury did not give.
  • If the user disagrees with the verdict, offer a retrial with the changes from "Conditions for acquittal" written into a new case file. Do not argue for either side yourself.
当 
COURT next
表示审判结束时：
bash
COURT render
它会统计票数，将 
VERDICT.md
写入运行目录并打印出来。向用户原样展示裁决结论行、投票表和法官的各个部分。然后最多补充你自己的两行：你首先会采用的那一个无罪条件，以及通往完整审判的路径。
你作为书记员必须遵守以下规则：
  • 绝不更改、软化或重新统计裁决结果。有罪裁决是有价值的信息，而不是需要粉饰的坏消息。
  • 绝不添加陪审团没有给予的赞扬。
  • 如果用户不同意裁决结果，提供一次重审机会，将“无罪条件”中的修改写入新的案件文件。不要亲自替任何一方辩论。