@wentorai/research-plugins 1.0.0 → 1.1.0

package/skills/domains/humanities/political-history-guide/SKILL.md

@@ -0,0 +1,241 @@
+---
+name: political-history-guide
+description: "Chinese and European political struggle history and comparative analysis"
+metadata:
+  openclaw:
+    emoji: "🗳️"
+    category: "domains"
+    subcategory: "humanities"
+    keywords: ["political history", "comparative politics", "Chinese history", "European history", "state formation", "revolution"]
+    source: "https://plato.stanford.edu/entries/political-history/"
+---
+
+# Political History Guide
+
+## Overview
+
+Political history examines the struggle for power, the formation of states, the dynamics of revolution and reform, and the evolution of political ideas across time and space. This guide focuses on comparative political history, drawing on Chinese and European traditions to illuminate how different civilizations have organized political authority, managed conflict, and theorized the relationship between rulers and ruled.
+
+Comparing Chinese and European political development is one of the most productive exercises in historical social science. Both civilizations produced sophisticated state systems, bureaucratic administrations, and political philosophies -- but through radically different paths. Understanding these divergences helps researchers avoid Eurocentric assumptions and develop more robust theories of political change.
+
+This guide covers key periods and themes in both traditions, methods for comparative historical analysis, and the theoretical frameworks that scholars use to explain political transformation. It is designed for researchers working on political history, comparative politics, historical sociology, or area studies who need to engage with both traditions.
+
+## Chinese Political History: Key Periods
+
+### Imperial State Formation
+
+| Period | Key Development | Significance |
+|--------|----------------|--------------|
+| Warring States (475-221 BCE) | Competing state systems, Legalism | Earliest bureaucratic experiments |
+| Qin Unification (221-206 BCE) | Centralized empire, standardization | Template for imperial governance |
+| Han Dynasty (206 BCE-220 CE) | Confucian-Legalist synthesis, civil service | "Confucianization" of the state |
+| Tang Dynasty (618-907) | Imperial examination system, cosmopolitan empire | Meritocratic bureaucracy matured |
+| Song Dynasty (960-1279) | Neo-Confucianism, commercial revolution | Civilian-military tension, reform debates |
+| Ming Dynasty (1368-1644) | Autocratic centralization, eunuch politics | Limits of centralization |
+| Qing Dynasty (1644-1912) | Multi-ethnic empire, late reform crisis | Confrontation with modernity |
+
+### Political Struggle in Late Imperial China
+
+```
+The Wang Anshi Reforms (1069-1076) -- Paradigmatic reform struggle:
+
+REFORMERS (New Policies faction):
+- Wang Anshi, chief architect
+- Goal: Strengthen the state against Jurchen/Liao military threat
+- Policies: State loans to farmers, militia system, merchant taxes,
+  reform of examination content
+
+CONSERVATIVES (Old Policies faction):
+- Sima Guang, Su Shi, Ouyang Xiu
+- Goal: Preserve Confucian moral governance, limit state intervention
+- Argument: State activism corrupts both officials and people
+
+DYNAMICS:
+1. Emperor Shenzong backs Wang Anshi (1069)
+2. Conservatives purged from court
+3. Policies implemented with mixed results
+4. Emperor dies (1085), conservatives recalled
+5. Reform faction returns (1094), purges conservatives
+6. Cycle of factional purges weakens Northern Song
+
+ANALYTICAL FRAMEWORK:
+- Not simply "progressive vs. conservative"
+- Two competing visions of state-society relations
+- Both grounded in Confucian political philosophy
+- Structural issue: factional competition without institutional checks
+```
+
+## European Political History: Key Periods
+
+### State Formation and Political Struggle
+
+| Period | Key Development | Significance |
+|--------|----------------|--------------|
+| Athenian democracy (5th c. BCE) | Direct democracy, citizen participation | Foundational political model |
+| Roman Republic/Empire | Republican institutions, imperial autocracy | Mixed constitution theory |
+| Feudalism (9th-15th c.) | Decentralized authority, vassal obligations | Fragmented sovereignty |
+| Magna Carta (1215) | Limited royal authority | Constitutional principle |
+| Protestant Reformation (16th c.) | Religious wars, cuius regio | Sovereignty and conscience |
+| English Civil War (1642-1651) | Parliamentary sovereignty | Constitutionalism vs. absolutism |
+| French Revolution (1789) | Popular sovereignty, rights of man | Democratic revolution template |
+| 1848 Revolutions | Liberal nationalism, class conflict | Limits of liberal revolution |
+| Welfare state (20th c.) | Social rights, managed capitalism | State-market-society bargain |
+
+### The French Revolution: Anatomy of Political Struggle
+
+```
+Phases of revolutionary escalation:
+
+1. FISCAL CRISIS (1787-1789)
+   - State bankruptcy from war debts
+   - Estates-General convened (first since 1614)
+   - Third Estate declares National Assembly
+
+2. LIBERAL REVOLUTION (1789-1791)
+   - Declaration of the Rights of Man
+   - Constitutional monarchy
+   - Abolition of feudal privileges
+
+3. RADICALIZATION (1792-1794)
+   - War with Austria and Prussia
+   - Republic declared, king executed
+   - Committee of Public Safety, Terror
+   - Factional struggle: Girondins vs. Jacobins vs. sans-culottes
+
+4. THERMIDORIAN REACTION (1794-1799)
+   - Fall of Robespierre
+   - Conservative republic (Directory)
+   - Military coup by Napoleon (1799)
+
+ANALYTICAL TAKEAWAYS:
+- Revolutions rarely achieve their initial goals
+- Radicalization driven by external war + internal factional competition
+- "Revolutionary devouring its children" pattern
+- Fiscal crisis as trigger, but ideology shapes trajectory
+```
+
+## Comparative Analysis
+
+### Divergence in State Formation
+
+```
+Why did China centralize early while Europe remained fragmented?
+
+CHINESE CENTRALIZATION:
+- Geographic: North China Plain enabled large-scale agriculture and armies
+- Ideological: Mandate of Heaven legitimized universal rule
+- Administrative: Examination system created loyalist bureaucracy
+- Economic: State monopolies (salt, iron) funded centralization
+
+EUROPEAN FRAGMENTATION:
+- Geographic: Mountains, seas, rivers created defensible boundaries
+- Ideological: Church vs. state dual authority
+- Administrative: Feudal loyalties vs. centralized bureaucracy
+- Economic: Commercial city-states resisted centralization
+
+COMPARATIVE INSIGHT:
+Neither path is "superior" -- each produced distinctive political capacities:
+- China: Administrative efficiency, cultural unity, but brittle to dynastic collapse
+- Europe: Innovation through competition, but chronic warfare and instability
+```
+
+### Comparative Methods
+
+| Method | Description | Example |
+|--------|-------------|---------|
+| Mill's Method of Difference | Same outcome, different conditions | Why revolution in France but not England? |
+| Mill's Method of Agreement | Different contexts, same outcome | Revolutions in France, Russia, China |
+| Process tracing | Causal mechanisms within a case | How fiscal crisis led to revolution |
+| Path dependence | Early choices constrain later options | Examination system locks in bureaucratic model |
+| Critical junctures | Moments of structural contingency | 1911: Qing collapse opens multiple paths |
+| Counterfactual analysis | "What if" reasoning | What if Wang Anshi reforms had succeeded? |
+
+### Comparative Political Concepts
+
+```
+Concepts that translate across traditions (with caution):
+
+LEGITIMACY
+- Chinese: Mandate of Heaven (tianming 天命) -- cosmic-moral authority
+- European: Social contract -- consent of the governed
+- Both: Performance-based (good governance sustains legitimacy)
+- Divergence: Hereditary vs. meritocratic principles
+
+BUREAUCRACY
+- Chinese: Scholar-officials selected by examination
+- European: Patrimonial officeholders → Weberian rational bureaucracy
+- Both: Tension between expertise and political loyalty
+- Key difference: China 1000+ years earlier
+
+POLITICAL OPPOSITION
+- Chinese: Remonstrance (jian 谏) -- loyal criticism within the system
+- European: Institutionalized opposition (parliament, parties)
+- Both: Risk of punishment for dissent
+- Key difference: Legitimate organized opposition vs. individual moral courage
+
+REVOLUTION
+- Chinese: Dynastic cycle (geming 革命 = change of mandate)
+- European: Progressive transformation (revolution as social rupture)
+- Both: Violence as mechanism of political change
+- Key difference: Cyclical vs. linear models of change
+```
+
+## Research Methods for Political History
+
+### Archival Sources for Political History
+
+```
+Chinese political history sources:
+- Veritable Records (shilu 实录): Official court records
+- Standard Histories (zhengshi 正史): 24 dynastic histories
+- Memorials (zouzhe 奏折): Official communications to the emperor
+- Local gazetteers (difangzhi 地方志): Provincial/county records
+- Private collections (wenji 文集): Literati writings and correspondence
+
+European political history sources:
+- Parliamentary records (Hansard, Archives parlementaires)
+- Diplomatic correspondence (state papers, foreign office files)
+- Police and intelligence reports
+- Pamphlets and political press
+- Personal papers of political actors
+- Constitutional and legal documents
+```
+
+## Writing Comparative Political History
+
+```
+Structure for a comparative article:
+
+1. INTRODUCTION: Present the comparison and why it matters
+2. THEORETICAL FRAMEWORK: State your analytical categories
+3. CASE 1: Detailed analysis (e.g., Chinese reform)
+4. CASE 2: Detailed analysis (e.g., European reform)
+5. COMPARATIVE ANALYSIS: Systematic comparison
+   - Similarities explained
+   - Differences explained
+   - Theoretical implications
+6. CONCLUSION: What does the comparison teach us?
+
+Common pitfalls:
+- Treating one case as the "norm" and the other as "deviant"
+- Superficial comparison (listing similarities without analysis)
+- Ignoring the internal diversity within each case
+- Anachronism: applying modern concepts to pre-modern societies
+```
+
+## Best Practices
+
+- **Learn the languages.** Serious comparative work requires reading sources in the original.
+- **Avoid teleology.** Do not explain the past as inevitably leading to the present.
+- **Historicize your categories.** "State," "class," "revolution" meant different things in different times and places.
+- **Engage with area studies scholarship.** Comparativists must respect the depth of specialist knowledge.
+- **Be explicit about your units of comparison.** What exactly is being compared, and at what level?
+- **Acknowledge asymmetries.** Chinese and European archives have different biases, gaps, and preservation histories.
+
+## References
+
+- Skocpol, T. (1979). States and Social Revolutions. Cambridge UP.
+- Tilly, C. (1992). Coercion, Capital, and European States. Wiley-Blackwell.
+- Zhao, D. (2015). The Confucian-Legalist State: A New Theory of Chinese History. Oxford UP.
+- Fukuyama, F. (2011). The Origins of Political Order. Farrar, Straus and Giroux.
+- [Cambridge History of China](https://www.cambridge.org/core/series/cambridge-history-of-china/) -- Standard reference

package/skills/domains/law/legal-nlp-guide/SKILL.md

@@ -0,0 +1,236 @@
+---
+name: legal-nlp-guide
+description: "NLP techniques for legal text analysis, case law mining, and contracts"
+metadata:
+  openclaw:
+    emoji: "balance-scale"
+    category: "domains"
+    subcategory: "law"
+    keywords: ["legal-nlp", "text-mining", "case-law", "contract-analysis", "named-entity", "classification"]
+    source: "wentor"
+---
+
+# Legal NLP Guide
+
+A skill for applying natural language processing techniques to legal texts. Covers legal document classification, named entity recognition for legal entities, contract clause extraction, case law similarity search, and court opinion summarization using modern NLP tools.
+
+## Legal Text Characteristics
+
+Legal language presents unique NLP challenges:
+
+- **Long documents**: Court opinions average 5,000-20,000 tokens; contracts can exceed 50,000
+- **Domain-specific vocabulary**: Terms of art with precise legal meanings (e.g., "consideration", "estoppel")
+- **Complex syntax**: Multi-clause sentences with nested qualifications and cross-references
+- **Citation networks**: Dense cross-referencing between cases, statutes, and regulations
+- **Temporal reasoning**: Effective dates, amendments, and retroactivity
+
+## Legal Text Classification
+
+### Document Type Classification
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+# Legal-BERT: domain-adapted BERT for legal text
+model_name = "nlpaueb/legal-bert-base-uncased"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSequenceClassification.from_pretrained(
+    model_name, num_labels=5
+)
+
+# Legal document categories
+labels = ["contract", "court_opinion", "statute", "regulation", "brief"]
+
+def classify_legal_document(text: str, max_length: int = 512) -> dict:
+    """
+    Classify a legal document into predefined categories.
+    For long documents, use the first 512 tokens (typically the
+    preamble/introduction which contains strong classification signals).
+    """
+    inputs = tokenizer(
+        text, return_tensors="pt",
+        max_length=max_length, truncation=True, padding=True
+    )
+    with torch.no_grad():
+        logits = model(**inputs).logits
+    probs = torch.softmax(logits, dim=-1).squeeze()
+    predicted = labels[probs.argmax().item()]
+    return {
+        "predicted_class": predicted,
+        "confidence": probs.max().item(),
+        "all_scores": {l: p.item() for l, p in zip(labels, probs)},
+    }
+```
+
+### Topic Classification for Case Law
+
+Common topic taxonomies for legal research:
+
+| Category | Examples |
+|----------|---------|
+| Constitutional Law | Due process, equal protection, First Amendment |
+| Criminal Law | Sentencing, evidence, plea bargaining |
+| Contract Law | Breach, formation, damages |
+| Tort Law | Negligence, product liability, defamation |
+| Property Law | Real property, intellectual property, zoning |
+| Administrative Law | Agency rulemaking, judicial review |
+
+## Named Entity Recognition
+
+### Legal NER Categories
+
+Legal NER extends standard NER with domain-specific entity types:
+
+```python
+import spacy
+
+# Load a legal NER model (e.g., trained on the LegalNERo dataset)
+# or fine-tune spaCy on legal annotations
+nlp = spacy.load("en_legal_ner")
+
+legal_entity_types = {
+    "COURT": "Court or tribunal name",
+    "JUDGE": "Judge or justice name",
+    "PARTY": "Plaintiff, defendant, petitioner, respondent",
+    "STATUTE": "Statute or regulation citation",
+    "CASE_CITATION": "Case name and reporter citation",
+    "DATE": "Dates of decisions, filings, events",
+    "JURISDICTION": "Geographic or subject matter jurisdiction",
+    "PROVISION": "Specific section or clause reference",
+}
+
+def extract_legal_entities(text: str) -> list[dict]:
+    """Extract legal named entities from text."""
+    doc = nlp(text)
+    entities = []
+    for ent in doc.ents:
+        entities.append({
+            "text": ent.text,
+            "label": ent.label_,
+            "start": ent.start_char,
+            "end": ent.end_char,
+            "description": legal_entity_types.get(ent.label_, ""),
+        })
+    return entities
+```
+
+### Citation Extraction and Parsing
+
+```python
+import re
+
+# US case citation patterns (simplified)
+CASE_CITE_PATTERN = re.compile(
+    r"(?P<volume>\d+)\s+"
+    r"(?P<reporter>U\.S\.|S\.\s?Ct\.|F\.\s?\d[dthsr]+|"
+    r"F\.\s?Supp\.\s?\d*[dthsr]*)\s+"
+    r"(?P<page>\d+)"
+    r"(?:\s*,\s*(?P<pinpoint>\d+))?"
+    r"(?:\s*\((?P<year>\d{4})\))?"
+)
+
+def parse_citations(text: str) -> list[dict]:
+    """Extract and parse legal citations from text."""
+    citations = []
+    for match in CASE_CITE_PATTERN.finditer(text):
+        citations.append({
+            "full_match": match.group(),
+            "volume": match.group("volume"),
+            "reporter": match.group("reporter"),
+            "page": match.group("page"),
+            "pinpoint": match.group("pinpoint"),
+            "year": match.group("year"),
+        })
+    return citations
+```
+
+## Contract Analysis
+
+### Clause Extraction and Classification
+
+```python
+def segment_contract_clauses(text: str) -> list[dict]:
+    """
+    Segment a contract into numbered clauses and classify them.
+    Uses section numbering patterns as primary segmentation cues.
+    """
+    # Split on section/article numbering patterns
+    section_pattern = re.compile(
+        r"\n\s*(?:Section|Article|Clause|\d+\.)\s+\d+[\.\d]*\s*[:\.\-]?\s*",
+        re.IGNORECASE,
+    )
+    sections = section_pattern.split(text)
+    headers = section_pattern.findall(text)
+
+    clause_types = {
+        "indemnification": ["indemnif", "hold harmless", "defend and indemnify"],
+        "termination": ["terminat", "cancel", "expir"],
+        "confidentiality": ["confidential", "non-disclosure", "proprietary"],
+        "limitation_of_liability": ["limit of liabilit", "limitation of liabilit",
+                                     "aggregate liability", "consequential damages"],
+        "governing_law": ["governing law", "governed by", "jurisdiction"],
+        "force_majeure": ["force majeure", "act of god", "beyond reasonable control"],
+        "assignment": ["assign", "transfer", "delegate"],
+    }
+
+    clauses = []
+    for i, section in enumerate(sections[1:], 1):
+        detected_type = "general"
+        section_lower = section.lower()
+        for ctype, keywords in clause_types.items():
+            if any(kw in section_lower for kw in keywords):
+                detected_type = ctype
+                break
+        clauses.append({
+            "index": i,
+            "header": headers[i - 1].strip() if i <= len(headers) else "",
+            "type": detected_type,
+            "text": section.strip()[:500],
+        })
+    return clauses
+```
+
+## Case Similarity and Legal Search
+
+### Embedding-Based Case Retrieval
+
+```python
+from sentence_transformers import SentenceTransformer
+import numpy as np
+
+# Legal domain sentence embeddings
+encoder = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+
+def build_case_index(case_summaries: list[str]) -> np.ndarray:
+    """Encode case summaries into dense vector representations."""
+    embeddings = encoder.encode(case_summaries, show_progress_bar=True)
+    # L2 normalize for cosine similarity via dot product
+    norms = np.linalg.norm(embeddings, axis=1, keepdims=True)
+    return embeddings / norms
+
+def search_similar_cases(query: str, index: np.ndarray,
+                         case_ids: list[str], top_k: int = 10) -> list:
+    """Find the most similar cases to a query."""
+    query_vec = encoder.encode([query])
+    query_vec = query_vec / np.linalg.norm(query_vec)
+    scores = (index @ query_vec.T).squeeze()
+    top_indices = np.argsort(scores)[::-1][:top_k]
+    return [(case_ids[i], scores[i]) for i in top_indices]
+```
+
+## Legal Datasets and Benchmarks
+
+- **CaseHOLD**: Multiple-choice QA from case law holdings (Harvard)
+- **LEDGAR**: 100,000 contract provisions labeled with 12 clause types
+- **ECtHR dataset**: European Court of Human Rights case texts with violation labels
+- **LegalBench**: Multi-task benchmark for legal reasoning (Stanford)
+- **CUAD (Contract Understanding Atticus Dataset)**: 510 contracts with 41 clause type annotations
+
+## Tools and Resources
+
+- **Legal-BERT / CaseLaw-BERT**: Domain-adapted transformer models
+- **spaCy + Blackstone**: Legal NER and text processing for UK law
+- **Haystack**: Open-source framework for legal document search and QA
+- **CourtListener / RECAP**: Free US case law and PACER document archive
+- **LexNLP (ContraxSuite)**: Python library for legal text extraction