# Lex

> Centralized 'Truth Engine' for cross-jurisdictional legal context (US, EU, CA) and contract scaffolding.

- Skill: `techwavedev/lex` (Agent Skill, multi-file: 7 files)
- Install (CLI): `npx skillmds@latest add techwavedev/lex`
- Raw SKILL.md: https://api.skillmd.com/api/skills/techwavedev/lex/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: techwavedev (https://skillmd.com/u/techwavedev)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/techwavedev/lex

---


# LEX: Legal-Entity-X-ref

## Overview

LEX is a structured truth engine designed to eliminate legal hallucinations by grounding agents in verified government references and legislation across 29+ jurisdictions. It provides deterministic context for business formation, employment, and contract drafting.

## When to Use This Skill

- Use when you need to cross-reference or compare legal requirements between different territories, such as verifying the compliance gap between an **EU SARL** and a **US LLC**.
- Use when working with foundational business or employment documents that require specific, jurisdiction-compliant clauses to be inserted into a professional scaffold.
- Use when the user asks about the specific regulatory nuances, formation steps, or "truth-based" definitions of legal entities within the **29 supported jurisdictions** (USA, Canada, and the EU).

## How It Works

### Step 1: Identify Jurisdiction
Before drafting, determine if the user's entity or contract target is in the **USA, Canada, or the EU**.

### Step 2: Search & Fetch Context
Use the CLI shortcuts to find the relevant legal patterns and templates.
- Run `lex search <query>` to find matching templates.
- Run `lex get <path>` to read the granular metadata and requirements.

### Step 3: Scaffold Drafting
Generate foundation-level documents using `lex draft <description>`. This ensures that all drafts include the mandatory AI-generated content disclaimer.

### Step 4: Verify Authority
Always include a "Verified Sources" section in your output by running `lex verify`, which fetches official government links for the retrieved context.

## Examples

### Example 1: Comparing Employment Laws
```bash
# Get the workforce template to compare US vs EU notice periods
lex get templates/02_employment_workforce.md
```

### Example 2: Drafting a Czech Contract
```bash
# Create a house sale contract scaffold in Czech language
lex draft "Czech house sale contract"
```

## Best Practices

- ✅ **Trust but Verify**: Always include the links provided by `lex verify` in your output.
- ✅ **Table Formatting**: Use tables when comparing results across multiple jurisdictions.
- ❌ **No Guessing**: If a jurisdiction is outside the US/EU/CA scope, state that it is outside the LEX "Truth Engine" coverage.
- ❌ **No Anecdotal Advice**: Stick strictly to the findings in the templates or verified government domains.

## Common Pitfalls

- **Problem:** Legal hallucination regarding specific EU notice periods.
  **Solution:** Run `lex get templates/02_employment_workforce.md` to see the restrictive covenant comparison table.

## Related Skills

- `@employment-contract-templates` - For more specific HR policy phrasing.
- `@legal-advisor` - For general legal framework architecture.
- `@security-auditor` - For reviewing the final repository security.

---

<!-- AGI-INTEGRATION-START -->

## AGI Framework Integration

> **Adapted for [@techwavedev/agi-agent-kit](https://www.npmjs.com/package/@techwavedev/agi-agent-kit)**
> Original source: [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills)

### Memory-First Protocol

Retrieve prior decisions and patterns to avoid re-discovering solutions. Cache results for instant retrieval in future sessions.

```bash
# Check for prior development context before starting
python3 execution/memory_manager.py auto --query "prior work and patterns related to Lex"
```

### Storing Results

After completing work, store development decisions for future sessions:

```bash
python3 execution/memory_manager.py store \
  --content "Completed task with key insights documented for future reference" \
  --type decision --project <project> \
  --tags lex default
```

### Multi-Agent Collaboration

Share outcomes with other agents so the team stays aligned and avoids duplicate work.

```bash
python3 execution/cross_agent_context.py store \
  --agent "<your-agent>" \
  --action "Task completed — results documented and shared with team" \
  --project <project>
```

<!-- AGI-INTEGRATION-END -->