Business operationsPublic skills

Legal Research

Global legal intelligence for AI agents — case law, legislation, regulations, and sanctions screening across US, UK, EU, Africa, Canada, and Australia.

Open the skill source Read the official guide ↗

What this skill teaches

A reusable playbook for a specific kind of work.

An MCP server tells an agent which actions are available. A skill adds the judgment around those actions: how to recognize the job, which sequence to follow, what to avoid, and how to decide that the result is complete.

Orchestrate legal research — search case law, legislation, and regulations across US, UK, EU, Africa, Canada, and Australia. Screen entities against sanctions lists. Use when researching case law, finding legislation, checking regulations, screening for sanctions, or verifying legal compliance across jurisdictions.

Architecture

How Legal Research guides an ADK-Rust agent.

The skill stays readable and portable because it contains instructions rather than service credentials or business data. ADK-Rust supplies it to the agent, the agent chooses from its reviewed tool boundary, and the connected MCP server performs the authenticated operation.

User request

The agent receives a goal expressed in ordinary language.

→

Legal Research skill

Matches intent, supplies the decision guide, and narrows the tool boundary.

→

ADK-Rust agent

Plans the workflow and streams each meaningful step through the runtime.

→

mcp-legal

Executes authenticated operations against the system that owns the capability.

→

Verified result

The skill's completion rules shape the evidence returned to the user.

Portable instructions: SKILL.md · Capability boundary: mcp-legal · Allowed tools: 14

Decision guide

How the agent turns a request into the right action.

These routes come directly from the skill instructions. They help the model recognize intent and select a focused tool or workflow instead of improvising across the entire capability surface.

"case", "ruling", "precedent", "court"?

search_cases / get_case

"law", "legislation", "act", "statute"?

search_uk/eu_legislation / search_federal_register

"sanctions", "screen", "blocked", "restricted"?

screen_entity / search_sanctions

"regulation", "rule", "federal register"?

search_federal_register

"jurisdiction", "coverage"?

list_supported_jurisdictions

Proven workflows

Repeatable sequences for useful outcomes.

A workflow joins several tool calls into a task the user actually recognizes. The skill explains the sequence and the intended result while ADK-Rust streams the agent's progress through the shared runtime.

012 calls

Case Law Research

Find precedents by topic/jurisdiction

022 calls

Legislation Lookup

Find and read statutes (UK, EU, US)

031-2 calls

Sanctions Screening

Screen entities against OFAC/EU/UN lists

Tool boundary

The skill may use 14 documented tools.

This allowlist is declared by the skill. It keeps the agent focused on the actions needed for this job while mcp-legal retains responsibility for authentication, validation, and the connected system.

search_cases

get_case

search_uk_legislation

get_uk_legislation

search_eu_legislation

get_eu_document

search_federal_register

get_federal_register_document

screen_entity

search_sanctions

get_sanctions_record

list_supported_jurisdictions

list_supported_sources

get_coverage_status

Working rules

What the agent should do.

Follow the decision guide, use the declared tool boundary, and verify the result before responding.

Operating boundaries

What the agent should avoid.

Review the complete SKILL.md before enabling this skill for production work.

Install and connect

Add the skill beside the capability it expects.

Install the repository where your ADK-Rust skill loader can discover it, connect mcp-legal, and confirm the declared tools are available before asking the agent to use the workflow.

Install the skill

git clone https://github.com/zavora-ai/skill-legal-research.git ~/.skills/skills/legal-research

ADK-Rust loading shape

let skills = SkillLoader::from_dir("~/.skills/skills").await?;
let skill = skills.load("legal-research").await?;

let agent = LlmAgentBuilder::new("agent")
    .instruction(skill.instructions())
    .tools(skill.allowed_tools(toolset)?)
    .build()?;

The repository's compatibility statement: Requires mcp-legal server connected (free public legal databases).

Official documentation

Read the complete skill package.

The repository remains authoritative for its exact instructions, examples, helper scripts, assets, MCP requirements, license, and later updates.

Overview ↗README.md Skill instructions ↗SKILL.md Cross Mcp Workflows ↗references/cross-mcp-workflows.md Examples ↗references/examples.md Tool Sequences ↗references/tool-sequences.md Validate ↗scripts/validate.py Case Brief ↗assets/case-brief.md

Keep exploring

More in business operations.

Browse all skills →

Agriculture ManagementFarm operations for AI agents — field management, crop planning, weather intelligence, satellite monitoring (NDVI), commodity markets, IoT sensors, yield estimation, and pest/disease detection.34 allowed tools Banking OperationsReal-time banking intelligence for AI agents — account monitoring, transaction analysis, anomaly detection, and payment initiation across Plaid (US/EU), Mono (Africa), and Open Banking (UK/EU).15 allowed tools CRM Customer ManagementEnterprise CRM workflow orchestration for AI agents — customer 360 lookups, deal pipeline management, activity logging, and multi-MCP onboarding across Salesforce, HubSpot, Zoho CRM, and Pipedrive.27 allowed tools

Source record

Repository metadata for this skill entry.

View public repository ↗

License: Apache-2.0
Allowed tools: 14
References: 3
Revision: 8e45269193da
Updated: May 31, 2026