Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

legalby lawve-ai

/oral-argument — Tribunal Prep, the Katyal/Harvey Way

lawve-ai/oral-argument

Source lawve-ai/awesome-legal-skills ↗License NOASSERTION

Prepare a lawyer for an adversarial proceeding the way Neal Katyal's "Harvey" prepared him for the SCOTUS tariffs argument: profile the tribunal from their prior opinions and questions, predict the specific questions you will face, map narrow "escape routes" each judge can walk through without abandoning prior commitments, and spar adversarially until only the strongest answers survive. The model is the sparring partner. The human still wins the case.

SkillScore77Maintained

Automatic

Legal & Contracts pack

Last verified 8/16/2026

What it changes

Passed 17 of 22 test cases with the skill, and 13 of 22 without it.

Without skill59%

With skill77%

Checks it passed that the model alone missed

Keeps the entire index card content strictly under 150 words.
Includes the exact phrase 'I get to' to reframe anxiety as a privilege.
Instructs the lawyer to pause briefly and listen to the underlying worry before answering.

and 2 more in the full report

4 fixed13 passed either way5 still failing0 broke

Pass-rate lift: +18 pp
Tokens: +72%
Agent turns: 0%
Response time: -22%

Model gemini-3.6-flashMeasured 8/16/2026v117 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/lawve-ai-oral-argument/SKILL.md https://app.decimal.ai/s/lawve-ai-oral-argument/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add lawve-ai-oral-argument, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/lawve-ai-oral-argument/ and pins it in .decimal/skills.lock

decimalai skills add lawve-ai-oral-argument

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/lawve-ai-oral-argument/SKILL.md https://app.decimal.ai/s/lawve-ai-oral-argument/SKILL.md

Raw file: /s/lawve-ai-oral-argument/SKILL.md ↗ · machine-readable summary at /s/lawve-ai-oral-argument.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 4

Prompt

Generate the single index card of podium cues to close out our tribunal prep session for an upcoming state supreme court argument on breach of fiduciary duty.

What was checked, without and with the skill
Checked	Without skill	With skill
Keeps the entire index card content strictly under 150 words.	Missed	Passed

case-21 · gemini-3.6-flash · 8/16/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md151 linessingle file

/oral-argument — Tribunal Prep, the Katyal/Harvey Way

You are preparing a lawyer for an adversarial proceeding in front of one or more known decision-makers (justices, judges, arbitrators, opposing counsel in deposition). Your job is sparring partner, not oracle. The human delivers the argument. You sharpen it.

The architecture comes from Neal Katyal's Nov 2025 SCOTUS tariffs argument, where his AI ("Harvey") was trained on every question every justice had asked in 25 years and every opinion they had written. It predicted the bench near-verbatim and mapped the narrow door the Chief Justice walked through.

Operating principles (read before every session)

Predictability is integrity, not weakness. A judge who returns to the same principles case after case has character. Do not frame predictions as "gotchas." Frame them as respect for the judge's stated commitments.
No parroting. If the lawyer steps to the podium and recites your output, they lose. Your output is raw material — angles, phrases, doctrinal hooks — that the lawyer must absorb and re-deliver in their own voice while actually listening to what the judge asks.
Find the door, don't push the judge through it. The strongest move is to identify the narrowest ground a skeptical judge could rule your way while staying consistent with everything they've ever said. Hand them the door open. They walk through.
Adversarial by default. Treat every argument the lawyer makes as wrong until it survives the worst question on the bench. Read the 200th case the same way you read the first.
End with the human. Always close a session by reminding the lawyer what only they can do at the podium: listen, connect, adjust tone, see the actual worry behind the question.

Phase 1 — Profile the tribunal

Build a profile for each named decision-maker. Ask the user for what they have, then fill gaps from public sources.

For each judge / justice / arbitrator gather:

Doctrinal commitments. What principles do they return to? (textualism,

Track record

Benchmark

17 / 22

test cases passed, vs 13 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

lawve-ai / awesome-legal-skills

skills/oral-argument-stephane-boghossian/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

/oral-argument — Tribunal Prep, the Katyal/Harvey Way

Operating principles (read before every session)

Phase 1 — Profile the tribunal

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills