Agent skill

Route Contract Drafting

by lawve-ai in lawve-ai/awesome-legal-skills

Pick the right LLM for CONTRACT DRAFTING — generating, redlining, or rewriting contract language from instructions.

AGPL-3.0-or-laterAuto-check passedLegal & Compliance

Install Route Contract Drafting

skills CLI
$ npx skills add lawve-ai/awesome-legal-skills --skill route-contract-drafting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lawve-ai/awesome-legal-skills route-contract-drafting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lawve-ai/awesome-legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/legal-ai-model-router-stephane-boghossian/skills/route-contract-drafting .claude/skills/route-contract-drafting && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
route-contract-drafting
GitHub stars
847
Token cost
~1.6k tokens
SKILL.md length
609 words
Files
2 (incl. references)
Skills in repo
154
Repo updated
First seen
Licence
AGPL-3.0-or-later

At a glance

Pick the right LLM for CONTRACT DRAFTING — generating, redlining, or rewriting contract language from instructions.

  • Works in 3 steps: Infer, then ask only what's missing → Route using the scorecard → Output (use this exact shape)
  • Someone asks which model should I use to draft this clause/agreement
  • SKILL.md covers When this applies, Step 1 — Infer, then ask only…, Step 2 — Route using the… and Step 3 — Output (use this…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Route Contract Drafting is an agent skill from lawve-ai/awesome-legal-skills. Pick the right LLM for CONTRACT DRAFTING — generating, redlining, or rewriting contract language from instructions. Vendor-neutral routing grounded in mid-2026 legal benchmarks (legalbenchmarks.ai Contract Drafting). Asks up to 4 quick questions (cost, speed, accuracy/ stakes, privacy/jurisdiction/language), then recommends a primary model + fallback + what to avoid + what a human must verify. Use when someone asks "which model should I use to draft this clause/agreement", "best AI for drafting contracts", "route…

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/scorecard.md`).

It sits in Legal & Compliance, covering Contract review. The repository describes itself as: A curated list of awesome Agent Skills for automating legal work. The licence is AGPL-3.0-or-later.

When your agent uses it

  • Someone asks which model should I use to draft this clause/agreement
  • Best AI for drafting contracts
  • Route this drafting task
  • Is about to generate/redline contract text and hasnt fixed a model

Example prompts

  • “which model should I use to draft this clause/agreement”
  • “best AI for drafting contracts”
  • “route this drafting task”
  • “/route-contract-drafting”

Requirements

  • Pre-approved tools (allowed-tools): AskUserQuestion, Read

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Infer, then ask only what's missing
  2. Route using the scorecard
  3. Output (use this exact shape)

What it can do on your machine

Read from SKILL.md and the folder at commit 045f738. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • AskUserQuestion
    • Read

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • legalbenchmarks.ai

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Route Contract Drafting loads about 1.6k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 159 tokens; SKILL.md has 609 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~159
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from lawve-ai/awesome-legal-skills at commit 045f738, republished under its AGPL-3.0-or-later licence (© lawve-ai). 609 words, ~1,562 tokens.

Download SKILL.mdSave it as .claude/skills/route-contract-drafting/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
route-contract-drafting
description
Pick the right LLM for CONTRACT DRAFTING — generating, redlining, or rewriting contract language from instructions. Vendor-neutral routing grounded in mid-2026 legal benchmarks (legalbenchmarks.ai Contract Drafting). Asks up to 4 quick questions (cost, speed, accuracy/ stakes, privacy/jurisdiction/language), then recommends a primary model + fallback + what to avoid + what a human must verify. Use when someone asks "which model should I use to draft this clause/agreement", "best AI for drafting contracts", "route this drafting task", or is about to generate/redline contract text and hasn't fixed a model.
allowed-tools
AskUserQuestion, Read
version
0.1.0
triggers
which model should I use to draft this clause or agreement, best AI for drafting contracts, route this drafting task, which LLM to redline this contract
license
AGPL-3.0-or-later

Route: Contract Drafting

You are a model-routing advisor for contract drafting — generating new clauses/agreements, redlining, or rewriting language from a set of instructions. You do not draft the contract here; you recommend which model to draft it with, and why, grounded in benchmark evidence + the user's constraints. This is decision support, not legal advice.

When this applies

Drafting a clause or full agreement from a brief · redlining to protect a party · rewriting language · turning a term sheet into contract text. (If the task is mainly reading a contract to pull facts, use route-info-extraction. If it's assessing an existing contract, use route-contract-review.)

Step 1 — Infer, then ask only what's missing

Read the request and infer the four routing axes. Ask the user only the axes you cannot infer, and ask them batched, multiple-choice, with a recommended default first (never one-by-one):

  1. Stakes / accuracy — Recommended: High for anything a client or counterparty will sign. Back-of-envelope draft · Working draft (internal review) · High — will be signed/filed.
  2. Cost sensitivity — Don't care · Balanced (default) · Minimize $/task.
  3. Speed — Batch/overnight fine · Interactive (default) · Real-time, latency-critical.
  4. Privacy / jurisdiction / language — US/UK English, cloud OK (default) · Non-English or non-US law · Client-privileged → needs self-hostable/on-prem.

If the user says "just pick," assume: High stakes, Balanced cost, Interactive speed, US/UK English cloud.

Step 2 — Route using the scorecard

Contract Drafting scorecard (legalbenchmarks.ai, 34 tasks, data as of 2026-07) Reliability = % of tasks passed fully on a lawyer checklist (one miss fails the task). Cost = $/task.

ModelReliabilityUsefulnessCost/taskRoute it for…
Claude Opus 4.867.6%2.67~$0.29Default & high-stakes. Best drafter; also flags contradictory instructions.
Claude Fable 561.8%2.66~$0.63Ties Opus on quality but ~2.2× cost — pick Opus instead unless already in a Fable pipeline.
Grok 4.558.8%2.61~$0.19Best value. Best non-Anthropic drafter; leaves already-sound language untouched.
Gemini 3.5 Flash55.9%2.60~$0.08Cheapest/fastest sane option for lower-stakes or high-volume drafting.
Claude Sonnet 4.650.0%2.63$0.13Mid-tier balanced; fine for working drafts.
Gemini 3.1 Pro50.0%2.69$0.07Cheap, decent usefulness; verify obligations coverage.
GPT 5.6 Sol44.1%2.75~$0.19⚠️ Trap. Most polished prose but misses ≥1 instruction in >50% of drafts.
Qwen 3.7 Max44.1%2.67~$0.03Strongest cheap/multilingual option, but reliability is low — heavy human review.
GPT-5.5 / DeepSeek V4 Pro / GPT-5.4-mini26–41%—$0.01–0.15Low-stakes triage only.
Show full SKILL.md (227 more words)Show less

Decision rules

  • High stakes (default) → Opus 4.8. It has the top reliability and is the one model that flags contradictory instructions rather than silently drafting through them — exactly what you want on signable text.
  • Minimize cost, stakes still real → Grok 4.5 (~$0.19, 58.8%): the best quality-per-dollar in the top tier.
  • High volume / lower stakes / speed-critical → Gemini 3.5 Flash (~$0.08, fast, 55.9%).
  • Never route drafting on "usefulness"/readability alone. GPT 5.6 Sol tops usefulness (2.75) but misses an instruction in >50% of drafts. Polished ≠ correct. Avoid it for drafting.
  • Privacy / on-prem → no open-weight model is a strong drafter. Best self-hostable is Qwen 3.7 Max (44.1%) — usable only with heavy human review. State the reliability cost explicitly.
  • Non-English / non-US law → this benchmark is English + US/UK only. Do not treat these ranks as valid; hand off to route-legal-translation for language and add a jurisdiction-qualified human reviewer.

Step 3 — Output (use this exact shape)

PRIMARY:    <model> — <one line tying the pick to the user's axes + the scorecard>
FALLBACK:   <model> — <when to switch to it>
ESCALATE IF: <trigger, e.g. "counterparty markup / signable"> → <stronger model>
AVOID:      <model> — <why, for THIS task>
CONFIDENCE: low | med | high  (top drafting cluster is close; say so)
VERIFY:     Contradiction check + every instruction represented (all-pass — a draft missing 1 of N
            obligations is not 90% done, it's incomplete). Human sign-off for signable text.

If stakes are High, append: "Benchmarks drift monthly — re-check https://www.legalbenchmarks.ai/leaderboard before betting a filing on this."

Non-negotiables

  • Capability ≠ controllability. A top score doesn't mean the model stays in scope or won't invent a clause.
  • All-pass grading is the honest bar for drafting: one missed obligation fails the draft.
  • Extended per-model notes, methodology, and caveats: references/scorecard.md. Full cross-vertical data + live sources: repo data/scorecard-2026-07.md.
  • This routes models; it does not give legal advice. A qualified lawyer owns the final document.

© lawve-ai, AGPL-3.0-or-later. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/legal-ai-model-router-stephane-boghossian/skills/route-contract-drafting of lawve-ai/awesome-legal-skills.

  • SKILL.md
  • references/scorecard.md

Open the folder on GitHubat commit 045f738

Compare with similar skills

Route Contract Drafting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Route Contract Drafting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Route Contract Drafting this skilllawve-ai/awesome-legal-skills847—~1.6kAutomated safety check: PassAGPL-3.0-or-later
Contract Reviewevolsb/claude-legal-skill4641 repos~3.6kAutomated safety check: PassMIT
Commercial Legal Plapiotrowski-afk/commercial-legal-pl1761 repos~4.1kAutomated safety check: PassApache-2.0
Hand Drawnthreerocks/hand-drawn-styles2.2k—~398Automated safety check: PassMIT
Tabular Document Reviewanthropics/claude-for-legal9.6k3 repos~4.3kAutomated safety check: PassApache-2.0
Tw Formal WritingImbad0202/tw-formal-writing179—~1kAutomated safety check: PassMIT

Similar skills

  • Contract Review

    evolsb/claude-legal-skill

    Review legal contracts, NDAs, employment agreements, SaaS terms, and M&A documents.

    464 GitHub starsUsed in 1 repo~3.6k tokens
    Legal & ComplianceAuto-check passed
  • Commercial Legal Pl

    apiotrowski-afk/commercial-legal-pl

    Skill do analizy i tworzenia umów według polskiego prawa, ze szczególnym uwzględnieniem umów B2B, IP i IT (body leasing, NDA, wdrożenia, SaaS, przeniesienie praw autorskich, ugody).

    176 GitHub starsUsed in 1 repo~4.1k tokens
    Legal & ComplianceAuto-check passed
  • Hand Drawn

    threerocks/hand-drawn-styles

    A skill your agent uses when users ask for a hand-drawn or illustrated image prompt, name one of the repository's 20 numbered styles or the 3.1 stable variant, or mention triggers such as…

    2.2k GitHub stars~398 tokensUpdated yesterday
    Legal & ComplianceAuto-check passed
  • Tabular Document Review

    anthropics/claude-for-legal

    Official

    Builds a review grid with one row per document and one column per data point, each cell cited to a verbatim quote, built for M&A diligence and other batch reviews.

    9.6k GitHub starsUsed in 3 repos~4.3k tokens
    Legal & ComplianceAuto-check passed
  • Tw Formal Writing

    Imbad0202/tw-formal-writing

    台灣正式文件撰寫助手 — 涵蓋政府公文、政府機關其他文件、法律文件、人民對政府文書四類中文正式文件的撰寫(不含學術論文、商業文書、私人書信等,見下方排除清單)。

    179 GitHub stars~1k tokensUpdated 15 days ago
    Legal & ComplianceAuto-check passed
  • Contract Review Pro

    CSlawyer1985/contract-review-pro

    专业合同审核 Skill:7步工作流(含立场声明、框架审阅、类型路由)、5类通用门禁+16个专项门禁、终稿三件套+HTML可视化报告、8维度风险评分、修订5分类路由。完全自包含,零外部依赖。

    277 GitHub stars~2.3k tokensUpdated 1 mo ago
    Legal & ComplianceAuto-check passed

More from lawve-ai/awesome-legal-skills

All 154 skills in this repo
  • Customs Trade Law Onur Kafkas

    lawve-ai/awesome-legal-skills

    U.S. An agent skill from lawve-ai/awesome-legal-skills.

    847 GitHub stars~4.1k tokensUpdated 8 days ago
    Auto-check passed
  • Eu Data Act Oliver Schmidt Prietz

    lawve-ai/awesome-legal-skills

    Practitioner skill for advising on EU Regulation 2023/2854 (Data Act).

    847 GitHub stars~3.9k tokensUpdated 8 days ago
    Auto-check passed
  • Litigation Deadline Calendar

    lawve-ai/awesome-legal-skills

    Calendar litigation and arbitration deadlines from a scheduling order.

    847 GitHub stars~4.3k tokensUpdated 8 days ago
    Auto-check passed
  • Outlook Emails Lawvable

    lawve-ai/awesome-legal-skills

    Read, search, and download emails and attachments from Microsoft Outlook via OAuth2.

    847 GitHub stars~672 tokensUpdated 8 days ago
    Auto-check passed
  • Ambiguity Report

    lawve-ai/awesome-legal-skills

    Turn an interpretive-ambiguity audit of a legal text — contract, statute, regulation, or judicial opinion — into a polished deliverable.

    847 GitHub stars~4.6k tokensUpdated 8 days ago
    Auto-check passed
  • Az Eu Website Privacy Audit

    lawve-ai/awesome-legal-skills

    Audits a website for compliance with Azerbaijan's Law on Personal Data No.

    847 GitHub stars~3.8k tokensUpdated 8 days ago
    Auto-check passed

Questions about Route Contract Drafting

What does Route Contract Drafting do?

Pick the right LLM for CONTRACT DRAFTING — generating, redlining, or rewriting contract language from instructions. Route Contract Drafting is an agent skill from lawve-ai/awesome-legal-skills. Pick the right LLM for CONTRACT DRAFTING — generating, redlining, or rewriting contract language from instructions.

When should I use Route Contract Drafting?

Route Contract Drafting fits situations like: someone asks which model should I use to draft this clause/agreement; best AI for drafting contracts; route this drafting task; is about to generate/redline contract text and hasnt fixed a model.

How do I install Route Contract Drafting in Claude Code?

Run `npx skills add lawve-ai/awesome-legal-skills --skill route-contract-drafting -a claude-code`. Or copy the skill folder (skills/legal-ai-model-router-stephane-boghossian/skills/route-contract-drafting in lawve-ai/awesome-legal-skills) into .claude/skills/route-contract-drafting in your project. Claude Code loads it when a task matches its description.

How do I install Route Contract Drafting in Codex?

Run `npx skills add lawve-ai/awesome-legal-skills --skill route-contract-drafting -a codex`. Or copy the skill folder (skills/legal-ai-model-router-stephane-boghossian/skills/route-contract-drafting in lawve-ai/awesome-legal-skills) into .agents/skills/route-contract-drafting in your project. Codex loads it when a task matches its description.

Can I use Route Contract Drafting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lawve-ai/awesome-legal-skills --skill route-contract-drafting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/route-contract-drafting, .gemini/skills/route-contract-drafting, .github/skills/route-contract-drafting and .opencode/skills/route-contract-drafting in your project.

What does Route Contract Drafting need to run?

SKILL.md names no scripts, command-line tools or credentials: Route Contract Drafting is instructions for the agent only. Its frontmatter pre-approves these tools: AskUserQuestion, Read.

Does Route Contract Drafting access the network?

SKILL.md names 1 domain. As links in the text: legalbenchmarks.ai. This is read from the text; nothing was executed.

Is Route Contract Drafting safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Route Contract Drafting use?

Route Contract Drafting is published under the AGPL-3.0-or-later licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Route Contract Drafting use?

About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.2k tokens, read only when the agent opens those files.

What are the alternatives to Route Contract Drafting?

Skills that share tags, products or a category with Route Contract Drafting: Contract Review (evolsb/claude-legal-skill, 464 stars), Commercial Legal Pl (apiotrowski-afk/commercial-legal-pl, 176 stars), Hand Drawn (threerocks/hand-drawn-styles, 2.2k stars) and Tabular Document Review (anthropics/claude-for-legal, 9.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Route Contract Drafting?

lawve-ai (a GitHub organization) maintains it in lawve-ai/awesome-legal-skills, which has 847 GitHub stars. The repository holds 154 skills in this directory. The repository was last updated on October 2, 2026.

Source: lawve-ai/awesome-legal-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.