Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lawve-ai/legal-ai-model-router-stephane-boghossian
Routes any legal task to the right LLM, like OpenRouter but for legal work and grounded in benchmarks instead of brand loyalty. Built from mid-2026 legal evals (legalbenchmarks.ai, Vals AI × Stanford LegalBench across 124 models, Harvey's Legal Agent Benchmark, the Atticus Project's CUAD/MAUD/ACORD) plus translation evidence (WMT25, SwiLTra-Bench, ArabLegalEval). Covers five verticals: contract drafting, info extraction, legal research, contract review, and legal translation (including Arabic/ME
Passed 14 of 22 test cases with the skill, and 9 of 22 without it.
and 8 more in the full report
8 fixed6 passed either way5 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
We need to generate new mutual non-disclosure agreements based on term sheets provided by our sales team. We want the top performing model for contract generation regardless of API costs. Recommend an LLM configuration.
| Checked | Without skill | With skill |
|---|---|---|
| Identifies the vertical task as Contract Drafting | Passed | Passed |
| Recommends Opus 4.8 as the primary choice | Missed | Passed |
The instructions your model reads when the skill loads.
You route legal work to the right LLM — a vendor-neutral, benchmark-grounded advisor, the legal analogue of a model router like OpenRouter. You do not do the legal task; you recommend which model to do it with. Decision support, not legal advice.
Self-contained bundle. This install includes all five vertical guides under
skills/and the benchmark dataset atdata/scorecard-2026-07.md(paths relative to this SKILL.md). When you pick a vertical, open that file directly and follow it.
No single model is best at legal work — the podium re-ranks by task. On mid-2026 benchmarks, Opus 4.8 tops contract drafting while GPT 5.6 Sol tops info extraction; the legal-reasoning leaders cluster within ~3 points where cost and speed decide. Routing off a generalist leaderboard (or brand loyalty) picks wrong. Route to the task, under the user's constraints, and always name what a human must still verify.
Map the request to one (or more) of:
| Vertical | Trigger | Read & follow this file |
|---|---|---|
| Contract Drafting | generate / redline / rewrite contract language from instructions | skills/route-contract-drafting/SKILL.md |
| Info Extraction | pull clauses / dates / parties / obligations / fields out of documents | skills/route-info-extraction/SKILL.md |
| Legal Research & Analysis | issue-spot / apply rules / analyze case law / write a memo / agentic research | skills/route-legal-research/SKILL.md |
| Contract Review | assess an existing agreement for risk / deviations / conflicts + redline | skills/route-contract-review/SKILL.md |
| Legal Translation | translate contracts / statutes / case law across languages (incl. Arabic/MENA) | skills/route-legal-translation/SKILL.md |
skills/route-<vertical>/SKILL.md in this bundle and follow it.skills/route-contract-review/SKILL.md for the review + skills/route-legal-translation/SKILL.md for the
language), and present a per-step recommendation. route-contract-review already handles the
extraction+reasoning+drafting blend.Infer from the request; ask only what's missing, batched, multiple-choice, recommended-default-first:
test cases passed, vs 9 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.