Agent skill · Content & Marketing

legal-translation-US

Translate legal documents from any language into English while preserving .docx formatting and translating track changes and headers/footers. Use this skill whenever the user asks to translate a legal document, contract, deed, agreement, or any formal legal text into English. Also trigger when the user mentions translating .docx files that contain legal content, or asks for a "format-preserving translation" of a legal document. This skill covers all legal SaaS and more. Even if the user just says "translate this contract" or "translate this into English", use this skill if the document is lega

lawve-aigithub.com/lawve-aiGitHub ↗
claude-codeships scriptsNOASSERTION
Install
npx skills add lawve-ai/awesome-legal-skills --skill en-us-legal-translation-wouter-van-den-berg --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 199
SKILL.md size: 56 KB
Bundled scripts: yes
Version: 2026-05-13
Declared author: Wouter van den Berg - wouter@monteclima.com - linkedin.com/in/wjvandenberg
Path: skills/en-us-legal-translation-wouter-van-den-berg/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 618
Language: Python

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

Translate legal documents from any language into publication-quality English while preserving all original .docx formatting (fonts, styles, headers, tables, numbering, etc.).

How it works

The skill directs the agent to process one document at a time, translating every paragraph from the source language to English and applying translations directly onto the original document without altering its structure. It preserves complex formatting, including headers/footers and table content, by matching paragraphs in the source and replacing only text runs, ensuring the final .docx retains exact layout. It enforces a hard 35-paragraph per batch limit, validates translations via per-batch checks, and requires en_runs population for definitions sections. It involves reading a sequence of step documents (setup, lexicons, translation, validation, apply, postprocess, and quality checks) before progressing, and uses the tool set specified (e.g., claude-code). The workflow emphasizes sequential processing: complete Steps 1 through 11 for a document before starting another, and translate into US English by default. It explicitly instructs to perform a full per-document pipeline and perform per-step validations prior to applying changes to the original document.

When to use it

Use when the user asks to translate a legal document, contract, deed, agreement, or any formal legal text into English, or mentions translating .docx files containing legal content or requests a "format-preserving translation" of a legal document. Trigger even if the user only says "translate this contract" or "translate this into English" if the content is legal in nature.

What it can touch

The skill uses Claude Code as its declared tool for translation tasks. It operates on .docx files and requires reading and applying translations to the original document while preserving formatting.

Caveats

The skill requires strict adherence to per-document, sequential workflow with a hard cap of 35 paragraphs per batch and mandatory per-definition en_runs population. It relies on a predefined set of step files (e.g., setup, lexicons, translation, apply, postprocess, quality) and internal gates to ensure validation before applying changes. No outcomes are promised beyond following the stated steps and validations; the description does not claim any specific accuracy guarantees beyond the described process.

From the SKILL.md

# Legal Document Translation Skill Translate legal documents from any language into publication-quality English while preserving all original .docx formatting (fonts, styles, headers, tables, numbering, etc.). ## Pre-step checkpoint — read this whole file before doing anything This skill's discipline depends on you actually reading SKILL.md, not just having it loaded in context. Before performing any step (Step 1 through Step 11), post a single short confirmation line in chat: **"Understanding of skill discipline is confirmed, now initiating translation process."** (use this exact wording). Do NOT print the technical details (Hard Rules location, validator names, step files) — the user does not want a wall of internal-state text. The act of writing the confirmation line is what proves you are at the right place; keep it terse. If, while you are about to type the line, you realize you cannot from memory name (a) where the Hard Rules block lives, (b) which validators auto-invoke from `apply_translations_textmatch.py` (there are four), or (c) the file containing the step you are about to perform — **STOP**, `Read('SKILL.md')` again slowly, then post the one-line confirmation. Internal

What's inside
Steps it walks through
  1. Pre-step checkpoint — read this whole file before doing anything
  2. Compaction-resume trigger — treat as session start
  3. Do not ask the user — these are absolute defaults
  4. Multi-document workflow
  5. IMPORTANT: Single-document workflow — no agent parallelization
  6. The golden rule: original-as-base with text matching
  7. Architecture overview
  8. Hard rules. Non-negotiable. Enforced by the skill's gates.
  9. Mandatory reading order
  10. Lexicon priority — cross-language reference wins on cross-language conventions
  11. Pipeline overview
  12. Anti-drift safeguards
  13. Why text matching matters
  14. Table-nested paragraphs (signature blocks, schedules, form fields)
Ships with 24 files
  • README.md
  • references/consumer-retail.md
  • references/corporate-ma-jv.md
  • references/employment.md
  • references/energy-infrastructure.md
  • references/finance-banking.md
  • references/general-legal.md
  • references/ip-it-technology.md
  • references/litigation-settlement.md
  • references/ndas-service-agreements.md
  • references/permitting-environmental.md
  • references/public-procurement.md
  • references/real-estate.md
  • references/taxes.md
  • references/trading-capital-markets.md
  • references/transport-and-insurance.md
  • scripts/apply_translations_textmatch.py
  • scripts/clean_conversion_artifacts.py
  • scripts/coalesce_fragmented_tcs.py
  • scripts/extract_paragraphs.py
  • scripts/lexicon_compliance.py
  • scripts/post_process.py
  • scripts/quality_check.py
  • scripts/reorder_definitions.py
first 24 of 199
Commands it runs
python <skill-path>/scripts/reorder_definitions.py \
More from awesome-legal-skills
All skills →
About this skill
What does the legal-translation-US skill do?

Translate legal documents from any language into English while preserving .docx formatting and translating track changes and headers/footers. Use this skill whenever the user asks to translate a legal document, contract, deed, agreement, or any formal legal text into English. Also trigger when the user mentions translating .docx files that contain legal content, or asks for a "format-preserving translation" of a legal document. This skill covers all legal SaaS and more. Even if the user just says "translate this contract" or "translate this into English", use this skill if the document is lega

How do I install it?

Run `npx skills add lawve-ai/awesome-legal-skills --skill en-us-legal-translation-wouter-van-den-berg --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From lawve-ai/awesome-legal-skills, a repository with 618 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going