⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
court
>-
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
The court skill
When Claude agrees with everything you say, put your idea on trial in front of a jury of 12 Claudes. One Claude Code skill. Free, MIT, no signup, no API key, nothing to connect.
Made by Alex Chen (@nocodealex), an AI creator who builds free Claude Code skills. Step-by-step guide at chen.media.
Ask Claude "is this a good idea?" and it usually says yes. /court takes the same idea and runs a
trial instead:
- A prosecutor Claude builds the strongest honest case that your idea fails as described.
- A defense Claude builds the strongest honest case that it works.
- Each side answers the other's points.
- 12 jurors read the record and vote GUILTY or NOT GUILTY on their own. Each one sees the case through different eyes: an accountant, a first-time customer, a competitor, a retired judge, a teenager, an engineer, a small-business owner, a statistician, a parent, an investor, a designer and a lawyer. No juror sees another's vote, so nobody can just go along with the room.
- A judge Claude reads the verdict, the charges that stuck, what the defense got right, and the conditions for acquittal: the specific changes that would flip the most votes.
What comes back is VERDICT.md: the vote (for example GUILTY, 9 to 3), every juror's one-line reason,
and what to change before you try again.
It never touches your files. Everything is written inside .court/ in the folder you run it in.
Install
Paste this into Claude:
https://github.com/alexyc9381/court-skill
Install this skill, then confirm /court works.
Or copy the folder yourself, in Claude Code:
git clone https://github.com/alexyc9381/court-skill
cp -r court-skill/skills/court ~/.claude/skills/
Or with the skills CLI:
npx skills add alexyc9381/court-skill
Or as a plugin:
/plugin marketplace add alexyc9381/court-skill
/plugin install court-skill@court-skill
Installed as a plugin, it shows up as /court-skill:court.
Use
/court Quit my job to sell candles on Etsy full time. I have $8,000 saved and 40 sales so far.
| flag | meaning |
|---|---|
--jury N | 3 to 12 jurors. Default 12. |
--quick | 6 jurors. |
--seed S | Fixes which jurors sit on a smaller jury. |
A full trial is 17 sub-agent calls (2 openings, 2 rebuttals, 12 jurors, 1 judge); --quick is 11.
Every sub-agent counts toward your Claude plan's usage, so start with --quick if you are near your
limit. Turn on accept-edits mode (Shift+Tab) first so you are not asked to approve every file.
See examples/candles/VERDICT.md for a real (3-juror) trial: "Quit my job as a nurse to sell
handmade candles on Etsy full time" came back GUILTY, 3 to 0, with the conditions that would flip it.
How it works
skills/court/court.py does the bookkeeping: it opens the trial, writes one brief per sub-agent, checks
that every output exists, counts the votes and renders the verdict. Claude only orchestrates: it never
argues a side, never votes and never edits the verdict. The jurors are in skills/court/jurors.json.
python3 -m unittest discover -s tests
Making a video or post about this?
Go ahead. Credit it like this, in your caption or description:
/court skill by Alex Chen (@nocodealex): github.com/alexyc9381/court-skill
Tag @nocodealex so I can see it. Every verdict the skill writes already ends with the same credit, so leave it in the shot.
Writing about it or citing it in a paper? Use Cite this repository in the sidebar on GitHub.
Uninstall
rm -rf ~/.claude/skills/court
Not made by Anthropic. The jury is made of language models, so treat the verdict as a structured second opinion, not legal, financial or professional advice.
// HOW IT'S BUILT
KEY FILES