Legal Research GuideSAFE

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库,覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文,并支持用户上传 Skills。-- Maintained by CoPaper.AI from Stanford REAP.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: legal-research-guide
description: "Legal research methods, case law analysis, and compliance tools"
metadata:
  openclaw:
    emoji: "⚖️"
    category: "domains"
    subcategory: "law"
    keywords: ["law", "jurisprudence", "case law", "compliance analysis"]
    source: "wentor-research-plugins"
---

# Legal Research Guide

Conduct systematic legal research across jurisdictions, analyze case law, navigate statutory frameworks, and use computational legal tools for academic and practice-oriented research.

## Legal Research Frameworks

### IRAC Method

The standard analytical framework for legal reasoning:

| Step | Description | Example |
|------|-------------|---------|
| **Issue** | Identify the legal question | "Does web scraping of public data constitute a CFAA violation?" |
| **Rule** | State the applicable legal rule | "The CFAA prohibits accessing a computer 'without authorization' or 'exceeding authorized access'" |
| **Application** | Apply the rule to the facts | "In hiQ v. LinkedIn, the 9th Circuit held that scraping publicly available data does not violate the CFAA..." |
| **Conclusion** | State the legal conclusion | "Therefore, scraping publicly available academic data likely does not violate the CFAA, though terms-of-service issues remain." |

### CREAC Method (For Academic Legal Writing)

```
C - Conclusion (state your thesis)
R - Rule (present the legal rule with authority)
E - Explanation (analyze how courts have interpreted the rule)
A - Application (apply the rule to your specific scenario)
C - Conclusion (restate and refine conclusion)
```

## Legal Research Databases

### Primary Sources

| Database | Coverage | Cost | Best For |
|----------|----------|------|----------|
| Westlaw (Thomson Reuters) | US, UK, EU, international | Subscription | Comprehensive case law, KeyCite citator |
| LexisNexis | US, UK, international | Subscription | News integration, Shepard's citator |
| Google Scholar (Case Law) | US federal and state courts | Free | Quick case lookup, citation tracking |
| Casetext / CoCounsel | US courts | Subscription | AI-powered legal research |
| CourtListener | US federal courts | Free | PACER alternative, bulk data |
| EUR-Lex | EU law | Free | EU legislation, CJEU case law |
| BAILII | UK, Ireland | Free | UK case law and legislation |
| Justia | US law | Free | US case law, statutes, regulations |
| HeinOnline | Historical legal materials | Subscription | Law journals, treaties, legislative history |

### Secondary Sources

| Source | Content | Use |
|--------|---------|-----|
| Law reviews / journals | Scholarly analysis | Academic research, policy arguments |
| Restatements | ALI compilations of common law | Authoritative secondary source |
| Treatises | Comprehensive subject coverage | Deep dive into specific areas |
| Legal encyclopedias (AmJur, CJS) | Broad legal summaries | Starting point for unfamiliar areas |
| Practice guides | Practical how-to | Practitioner-oriented research |

## Citation Systems

### Bluebook (US Standard)

```
# Case citation
Marbury v. Madison, 5 U.S. (1 Cranch) 137 (1803).
Brown v. Board of Education, 347 U.S. 483, 495 (1954).

# Statute citation
42 U.S.C. Section 1983 (2018).
Cal. Civ. Code Section 1798.100 (West 2020).  # California statute

# Law review article
Jane Smith, The Future of AI Regulation, 120 Harv. L. Rev. 456 (2024).

# Book
Richard Posner, Economic Analysis of Law 25 (9th ed. 2014).

# Short form citations (after first full citation)
Brown, 347 U.S. at 495.
Smith, supra note 12, at 460.
Id. at 462.  # Same source as immediately preceding citation
```

### OSCOLA (UK/Oxford Standard)

```
# Case citation
Donoghue v Stevenson [1932] AC 562 (HL).
R v Brown [1994] 1 AC 212, 237 (HL).

# Statute citation
Human Rights Act 1998, s 3.
Data Protection Act 2018, s 170(1).

# Journal article
Jane Smith, 'The Future of AI Regulation' (2024) 120 Modern Law Review 456.

# Book
Richard Posner, Economic Analysis of Law (9th edn, Aspen 2014) 25.
```

## Computational Legal Research

### Case Law Analysis with Python

```python
import requests
import json

# Using the CourtListener API (free, open-source)
BASE_URL = "https://www.courtlistener.com/api/rest/v3"

def search_opinions(query, court="scotus", page_size=20):
    """Search case opinions via CourtListener API."""
    response = requests.get(
        f"{BASE_URL}/search/",
        params={
            "q": query,
            "type": "o",  # opinions
            "court": court,
            "page_size": page_size,
            "order_by": "score desc"
        },
        headers={"Authorization": "Token YOUR_API_TOKEN"}
    )
    results = response.json()
    for case in results.get("results", []):
        print(f"[{case.get('dateFiled', 'N/A')}] {case.get('caseName', 'N/A')}")
        print(f"  Court: {case.get('court', 'N/A')}")
        print(f"  Citation: {case.get('citation', ['N/A'])[0] if case.get('citation') else 'N/A'}")
        print(f"  URL: https://www.courtlistener.com{case.get('absolute_url', '')}")
    return results

# Search for AI-related Supreme Court cases
results = search_opinions("artificial intelligence", court="scotus")
```

### Citation Network Analysis

```python
import networkx as nx

def build_citation_network(seed_case_ids, depth=2):
    """Build a citation network starting from seed cases."""
    G = nx.DiGraph()
    visited = set()
    queue = [(cid, 0) for cid in seed_case_ids]

    while queue:
        case_id, level = queue.pop(0)
        if case_id in visited or level > depth:
            continue
        visited.add(case_id)

        # Get case metadata and citations
        resp = requests.get(f"{BASE_URL}/opinions/{case_id}/",
                           headers={"Authorization": "Token YOUR_API_TOKEN"})
        if resp.status_code != 200:
            continue

        case = resp.json()
        case_name = case.get("case_name", f"Case {case_id}")
        G.add_node(case_id, name=case_name, date=case.get("date_filed"))

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.