Oral Argument — Development skill for Claude Code
Claude Code skill that prepares a lawyer for an adversarial proceeding the way Neal Katyal's Harvey prepared him for SCOTUS: profile the tribunal, predict the bench, map escape routes, spar adversaria.
How to install Oral Argument
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open sboghossian/oral-argument and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Oral Argument does
Claude Code skill that prepares a lawyer for an adversarial proceeding the way Neal Katyal's Harvey prepared him for SCOTUS: profile the tribunal, predict the bench, map escape routes, spar adversarially. AGPL-3.0.
Alternatives in Development
- PaperSpine — PaperSpine is a motivation-driven skill for learning from strong academic papers, building a paper’s central a 5k ★
- Predict Issues — Predictive Code Analysis 2.8k ★
- Academic Pptx Skill — A Claude Skill for creating academic presentations (conference talks, seminar slides, thesis defenses, grant b 811 ★
README
oral-argument
A Claude skill that prepares a lawyer for an adversarial proceeding the way Neal Katyal's prep team prepared him for a SCOTUS argument.
Profile the tribunal from prior opinions and questions. Predict the specific questions you will face. Map narrow "escape routes" each judge can walk through without abandoning their commitments. Spar adversarially until only the strongest answers survive.
The model is the sparring partner. The human still wins the case.
Why this exists
In November 2025 Neal Katyal argued the SCOTUS tariffs case. His prep partner, "Harvey," was trained on every question every justice had asked in 25 years and every opinion they had written. Harvey predicted the bench near-verbatim and surfaced the narrow door the Chief Justice walked through.
The technique is reproducible. The skill encodes it.
What it does
You give Claude a hearing context: case, posture, the named tribunal members, the lawyer's draft brief or theory of the case. The skill runs five phases:
- Profile the tribunal. One-page bullet profile per decision-maker — doctrinal commitments, recurring questions, tells in concurrences, institutional concerns, coalition behavior, phrasing tics.
- Predict the bench. 3–7 questions per judge, each annotated with the doctrinal hook, the worry behind the question, and an attack-rank.
- Map escape routes. For each plausibly hostile judge, find the narrow holding they could sign onto without abandoning a prior commitment. Hand them the door open.
- Spar adversarially. Round-trip the lawyer's draft answers against the worst question on the bench. Iterate until the answer survives.
- End with the human. Close every session by reminding the lawyer what only they can do at the podium: listen, connect, adjust tone, see the worry behind the question.
See [examples/example-bench.md](examples/example-bench.md) for the canonical output.
When to use
- Appellate oral argument prep
- Motion hearing pr
Related Skills
Academic Taste Skill
Claude Code skill that distills a research field's academic taste by contrasting top-venue papers (oral vs. po
Tribunal
Convene the blind tribunal on the current diff — cross-family jurors, one lens each, author-redacted envelope,
Spar
Make the models argue before you build — Codex attacks the plan in bounded read-only rounds, then one builds a
Handler
You are Harvey, responding to replies from prospects. Every reply is an opportunity, but some replies are a st
Writer
You are Harvey, writing cold outreach emails for {{persona_company}}.
Claude Cretan Cat
Manousos, a pixel-art Cretan cat above your Claude Code prompt. Clawd tells him what to do; he answers in mant
Related Agents
Ff Nav
Flapforge navigation and integration engineer: hub sections, screen routing, the back/escape path and the way
Way Of Working Compliance Reviewer
Reviews only the prepared compliance payload against its captured project instructions and returns a terse, ci
Klein Data Auditor
Gate 1 (DATA) worker for Klein Auto Research — profiles the PREPARED dataset and writes data_card.md with rank