court
Put an idea on trial in front of a jury of 12 Claudes.
Skill by Alex Chen (@nocodealex)
Chalk Labs
Need help deploying court?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/angeldelbiondo-court
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/court
What's inside
- Skill name
court- Description
- Put an idea on trial in front of a jury of 12 Claudes. A prosecutor Claude argues it fails, a defense Claude argues it works, they rebut each other, 12 juror Claudes with different backgrounds vote on their own, and a judge Claude reads the verdict and the conditions that would flip it. Use when the user wants honest pushback instead of agreement, says Claude just agrees with everything, asks "is this a good idea", wants an idea, plan, pitch or claim stress-tested, or says "court" or "put it on trial". Spanish triggers: "tribunal", "juicio", "llévalo a juicio", "¿es buena idea?", "critícame esto", "abogado del diablo", "dame contras honestos", or brainstorming an idea to decide on it.
- License
- MIT
- Metadata
- author: Alex Chen (@nocodealex) · source: https://github.com/alexyc9381/court-skill · version: 1.0.0 · homepage: https://chen.media · local-patch: 2026-10-17 (Angel): python instead of python3 (Windows), Spanish output, explicit premises section
- Instructions
- 107 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (4)
- LICENSE
- SKILL.md
- court.py
- jurors.json
SKILL.md (first lines)
# 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`: `$ARGUMENTS`
If that is blank, or still reads like a placeholder, take the case from the conversation: the idea,
plan or claim the user most recently wanted an opinion on.
## The tool
Every piece of bookkeeping goes through `court.py` in this skill's folder:
```bash
python "${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`.
## Step 1: size it
Read the flags out of the request. Everything that is not a flag is the case.
| flag | meaning |
| --- | --- |
| `--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.
## Step 2: write the case file
**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.
- (local patch) A `## Premisas` section listing what the case takes for granted, one per line, so the
prosecution can attack the premises and not only the conclusion. A panel inherits the premises of
whoever frames it (rule in Angel's global CLAUDE.md).
- (local patch) Write the case file in Spanish and end it with the line: `Responde en español.` Every
sub-agent reads this file, so the statements, votes and judgment come back in Spanish.
## Step 3: open the trial
```bash
COURT init --case-file .court/case.md [--jury N | --quick] [--seed S]
```
## Step 4: the trial
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.
## Step 5: the verdict
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.From angeldelbiondo/claude-config, MIT.
More from angeldelbiondo/claude-config
- 0.567score
diagram-design
angeldelbiondo
Diagramas con estilo editorial en HTML/SVG/PNG para mostrar a otros: arquitectura, flujo, secuencia, ER, línea de tiempo, Gantt, Sankey, journey y más.
SkillAFreshness: AClaude Code +9 - 0.565score
design-motion
LottieFiles
Aplica principios de motion design para crear animaciones y transiciones técnicamente sólidas y con carga emocional.
SkillAFreshness: AClaude Code +9 - 0.565score
design-dna
angeldelbiondo
Extrae, define y aplica el ADN de diseno en tres dimensiones: sistema de diseno (tokens), estilo de diseno (sensacion cualitativa) y efectos visuales (Canvas…
SkillAFreshness: AClaude Code +9 - 0.561score
humanizer
angeldelbiondo
Reescribe texto que suena a IA para que suene a quien lo escribe, sin cambiar lo que dice.
SkillAFreshness: AClaude Code +9 - 0.556score
decidir
angeldelbiondo
Pensamiento crítico antes de decidir.
SkillAFreshness: AClaude Code +9 - 0.556score
doc-coauthoring
angeldelbiondo
Flujo para coescribir documentos largos (propuestas, specs, documentos de decisión, informes): recoger contexto, armar la estructura e iterar por secciones.
SkillAFreshness: AClaude Code +9 - 0.556score
doubt-driven-development
angeldelbiondo
Revisión adversarial en contexto limpio de cada decisión no trivial antes de seguir.
SkillAFreshness: AClaude Code +9 - 0.556score
interview-me
angeldelbiondo
Entrevista de a una pregunta hasta entender qué quiere Angel de verdad.
SkillAFreshness: AClaude Code +9 - 0.556score
discernment-nudge
angeldelbiondo
Después de una respuesta sustantiva que Angel va a ejecutar (recomendación, plan, números, análisis, afirmaciones), agrega 2-3 preguntas cortas para verificar…
SkillAFreshness: AClaude Code +9 - 0.556score
construir
angeldelbiondo
Escribir código o armar algo que funcione.
SkillAFreshness: AClaude Code +9 - 0.556score
datos
angeldelbiondo
Trabajar con datos y números.
SkillAFreshness: AClaude Code +9 - 0.551score
escribir
angeldelbiondo
Producir textos y documentos.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 22, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- MIT
- Repository
- github.com/angeldelbiondo/claude-config
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get court running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
court skill. Agent Mart. https://agentmart.dev/skills/angeldelbiondo-court (last updated 2026-10-24)