ssci-subagent-skills 1.0.0

package/skills/field-expert/modules/habitus_analysis.py

@@ -0,0 +1,306 @@
+"""
+场域习性分析模块
+此模块提供分析社会场域中行动者习性模式的功能
+"""
+
+from typing import Dict, List, Any
+import json
+
+
+def field_habitus_analysis(data: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    分析社会场域中行动者的习性模式
+    
+    Args:
+        data: 包含场域相关信息的字典
+    
+    Returns:
+        包含习性分析结果的字典
+    """
+    # 从数据中提取相关信息
+    actors = data.get('actors', [])
+    practices = data.get('practices', [])
+    field_structure = data.get('field_structure', {})
+    social_conditions = data.get('social_conditions', {})
+    
+    # 执行习性分析
+    disposition_analysis = analyze_dispositions(actors)
+    embodied_knowledge_analysis = analyze_embodied_knowledge(actors)
+    practice_logic_analysis = analyze_practice_logic(practices)
+    structure_agency_analysis = analyze_structure_agency_relationship(actors, field_structure)
+    practice_enablers_constraints = analyze_practice_enablers_constraints(actors)
+    habitus_formation_analysis = analyze_habitus_formation(social_conditions)
+    correspondence_analysis = assess_correspondence(actors, field_structure)
+    change_adaptation_analysis = analyze_change_adaptation(actors)
+    
+    return {
+        "disposition_analysis": disposition_analysis,
+        "embodied_knowledge": embodied_knowledge_analysis,
+        "practice_logic": practice_logic_analysis,
+        "structure_agency_relationship": structure_agency_analysis,
+        "practice_enablers_constraints": practice_enablers_constraints,
+        "habitus_formation": habitus_formation_analysis,
+        "correspondence_assessment": correspondence_analysis,
+        "change_adaptation": change_adaptation_analysis
+    }
+
+
+def analyze_dispositions(actors: List[Dict[str, Any]]) -> Dict[str, Any]:
+    """
+    分析行动倾向
+    
+    Args:
+        actors: 行动者列表
+    
+    Returns:
+        行动倾向分析结果
+    """
+    disposition_analysis = {
+        "durable_transposable_dispositions": [],
+        "generative_schemes": [],
+        "cognitive_structures": [],
+        "motivating_structures": [],
+        "embodied_tendencies": []
+    }
+    
+    for actor in actors:
+        if 'dispositions' in actor:
+            dispositions = actor['dispositions']
+            disposition_analysis["durable_transposable_dispositions"].extend(dispositions.get('durable', []))
+            disposition_analysis["generative_schemes"].extend(dispositions.get('generative', []))
+            disposition_analysis["cognitive_structures"].extend(dispositions.get('cognitive', []))
+            disposition_analysis["motivating_structures"].extend(dispositions.get('motivating', []))
+            disposition_analysis["embodied_tendencies"].extend(dispositions.get('embodied', []))
+    
+    return disposition_analysis
+
+
+def analyze_embodied_knowledge(actors: List[Dict[str, Any]]) -> Dict[str, Any]:
+    """
+    分析具身体现的知识
+    
+    Args:
+        actors: 行动者列表
+    
+    Returns:
+        具身体现知识分析结果
+    """
+    embodied_knowledge_analysis = {
+        "tacit_knowledge": [],
+        "practical_mastery": [],
+        "intuitive_understanding": [],
+        "bodily_techniques": [],
+        "non_verbal_aspects": []
+    }
+    
+    for actor in actors:
+        if 'embodied_knowledge' in actor:
+            knowledge = actor['embodied_knowledge']
+            embodied_knowledge_analysis["tacit_knowledge"].extend(knowledge.get('tacit', []))
+            embodied_knowledge_analysis["practical_mastery"].extend(knowledge.get('practical_mastery', []))
+            embodied_knowledge_analysis["intuitive_understanding"].extend(knowledge.get('intuitive', []))
+            embodied_knowledge_analysis["bodily_techniques"].extend(knowledge.get('bodily_techniques', []))
+            embodied_knowledge_analysis["non_verbal_aspects"].extend(knowledge.get('non_verbal', []))
+    
+    return embodied_knowledge_analysis
+
+
+def analyze_practice_logic(practices: List[Dict[str, Any]]) -> Dict[str, Any]:
+    """
+    分析实践逻辑
+    
+    Args:
+        practices: 实践列表
+    
+    Returns:
+        实践逻辑分析结果
+    """
+    practice_logic_analysis = {
+        "logic_transcending_rules": [],
+        "creative_improvisational_aspects": [],
+        "economy_of_practice": [],
+        "past_present_relationship": [],
+        "temporal_situational_aspects": []
+    }
+    
+    for practice in practices:
+        logic = practice.get('logic', {})
+        practice_logic_analysis["logic_transcending_rules"].append(logic.get('transcends_rules', 'unknown'))
+        practice_logic_analysis["creative_improvisational_aspects"].append(logic.get('creative', 'unknown'))
+        practice_logic_analysis["economy_of_practice"].append(logic.get('economy', 'unknown'))
+        practice_logic_analysis["past_present_relationship"].append(logic.get('past_present', 'unknown'))
+        practice_logic_analysis["temporal_situational_aspects"].append(logic.get('temporal', 'unknown'))
+    
+    return practice_logic_analysis
+
+
+def analyze_structure_agency_relationship(actors: List[Dict[str, Any]], field_structure: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    分析结构-能动性关系
+    
+    Args:
+        actors: 行动者列表
+        field_structure: 场域结构
+    
+    Returns:
+        结构-能动性关系分析结果
+    """
+    structure_agency_analysis = {
+        "habitus_incorporates_field_structure": {},
+        "correspondence_between_habitus_field": {},
+        "objective_conditions_subjective_dispositions": {},
+        "habitus_reproduces_transforms_structure": {},
+        "dialectical_relationship": {}
+    }
+    
+    for actor in actors:
+        actor_id = actor.get('id', actor.get('name', 'unknown'))
+        # 简化的对应关系分析
+        structure_agency_analysis["habitus_incorporates_field_structure"][actor_id] = True
+        structure_agency_analysis["correspondence_between_habitus_field"][actor_id] = "high"  # 示例值
+        structure_agency_analysis["objective_conditions_subjective_dispositions"][actor_id] = "matched"  # 示例值
+    
+    return structure_agency_analysis
+
+
+def analyze_practice_enablers_constraints(actors: List[Dict[str, Any]]) -> Dict[str, Any]:
+    """
+    分析实践的使能和约束因素
+    
+    Args:
+        actors: 行动者列表
+    
+    Returns:
+        实践使能和约束分析结果
+    """
+    enablers_constraints_analysis = {
+        "practice_enablers": {},
+        "practice_constraints": {},
+        "selective_perception": {},
+        "range_of_possible_actions": {},
+        "creative_potential": {}
+    }
+    
+    for actor in actors:
+        actor_id = actor.get('id', actor.get('name', 'unknown'))
+        # 简化的使能和约束分析
+        enablers_constraints_analysis["practice_enablers"][actor_id] = actor.get('enablers', [])
+        enablers_constraints_analysis["practice_constraints"][actor_id] = actor.get('constraints', [])
+        enablers_constraints_analysis["range_of_possible_actions"][actor_id] = actor.get('action_range', 'broad')
+        enablers_constraints_analysis["creative_potential"][actor_id] = actor.get('creative_potential', 'high')
+    
+    return enablers_constraints_analysis
+
+
+def analyze_habitus_formation(social_conditions: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    分析习性形成过程
+    
+    Args:
+        social_conditions: 社会条件
+    
+    Returns:
+        习性形成分析结果
+    """
+    habitus_formation_analysis = {
+        "social_origins": social_conditions.get('origins', []),
+        "socialization_processes": social_conditions.get('socialization', []),
+        "internalization_processes": social_conditions.get('internalization', []),
+        "role_of_family_school_peers": social_conditions.get('influences', {}),
+        "social_trajectory_relationship": social_conditions.get('trajectory', {}),
+        "critical_life_experiences": social_conditions.get('critical_experiences', [])
+    }
+    
+    return habitus_formation_analysis
+
+
+def assess_correspondence(actors: List[Dict[str, Any]], field_structure: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    评估对应关系
+    
+    Args:
+        actors: 行动者列表
+        field_structure: 场域结构
+    
+    Returns:
+        对应关系评估结果
+    """
+    correspondence_analysis = {
+        "fit_between_habitus_field": {},
+        "correspondence_between_dispositions_opportunities": {},
+        "selection_adaptation_processes": {},
+        "habitus_field_position_relationship": {},
+        "implications_for_success": {}
+    }
+    
+    for actor in actors:
+        actor_id = actor.get('id', actor.get('name', 'unknown'))
+        # 简化的对应关系评估
+        correspondence_analysis["fit_between_habitus_field"][actor_id] = actor.get('fit_level', 'medium')
+        correspondence_analysis["implications_for_success"][actor_id] = actor.get('success_implications', 'moderate')
+    
+    return correspondence_analysis
+
+
+def analyze_change_adaptation(actors: List[Dict[str, Any]]) -> Dict[str, Any]:
+    """
+    分析变化和适应
+    
+    Args:
+        actors: 行动者列表
+    
+    Returns:
+        变化和适应分析结果
+    """
+    change_adaptation_analysis = {
+        "habitus_transformation_processes": [],
+        "impact_of_field_changes": [],
+        "adaptation_mechanisms": [],
+        "resistance_to_change": [],
+        "modification_conditions": []
+    }
+    
+    for actor in actors:
+        transformations = actor.get('habitus_changes', [])
+        change_adaptation_analysis["habitus_transformation_processes"].extend(transformations)
+        
+        resistance = actor.get('resistance_to_change', [])
+        change_adaptation_analysis["resistance_to_change"].extend(resistance)
+    
+    return change_adaptation_analysis
+
+
+def analyze_symbolic_violence(data: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    分析象征暴力
+    
+    Args:
+        data: 包含场域信息的字典
+    
+    Returns:
+        象征暴力分析结果
+    """
+    return {
+        "mechanisms_of_symbolic_violence": data.get('symbolic_violence_mechanisms', []),
+        "misrecognition_processes": data.get('misrecognition_processes', []),
+        "power_inequality_perpetuation": data.get('power_inequality_perpetuation', []),
+        "internalization_of_dominance": data.get('internalization_of_dominance', [])
+    }
+
+
+def analyze_cross_field_analysis(data: Dict[str, Any]) -> Dict[str, Any]:
+    """
+    分析跨场域分析
+    
+    Args:
+        data: 包含场域信息的字典
+    
+    Returns:
+        跨场域分析结果
+    """
+    return {
+        "habitus_transfer_between_fields": data.get('habitus_transfer', []),
+        "field_boundary_crossings": data.get('field_boundary_crossings', []),
+        "habitus_adaptation_new_fields": data.get('habitus_adaptation_new_fields', []),
+        "competence_variations_fields": data.get('competence_variations_fields', [])
+    }

package/skills/field-expert/prompts/boundary_analysis.txt

@@ -0,0 +1,56 @@
+## 场域边界识别提示词（精简版）
+
+你是布迪厄场域理论专家。请基于以下西游记文本分析数据，识别主要场域及其边界。
+
+### 输入摘要
+{context}
+
+### 分析任务
+
+请识别以下5个核心场域：**佛界、天庭、人间、妖界、取经团队**
+
+对每个场域分析：
+1. **核心行动者** - 3-5个主要参与者
+2. **边界标识** - 什么标识这个场域的边界
+3. **进入条件** - 如何进入这个场域
+4. **排斥机制** - 谁被排斥在外
+
+### 输出格式（严格JSON）
+
+```json
+{
+  "fields": [
+    {
+      "name": "佛界",
+      "core_actors": ["如来佛祖", "观音菩萨", "弥勒佛"],
+      "boundary_markers": ["佛法经书", "佛门仪式", "灵山"],
+      "entry_conditions": ["出家修行", "功德圆满", "如来认可"],
+      "exclusion_mechanisms": ["妖魔鬼怪", "凡人", "不信佛者"]
+    }
+  ],
+  "gatekeepers": [
+    {
+      "actor": "观音菩萨",
+      "fields": ["佛界", "取经团队"],
+      "role": "取经项目总协调",
+      "gatekeeping_power": "如来授权"
+    }
+  ],
+  "boundary_dynamics": {
+    "stability": "稳定",
+    "permeability": "中",
+    "change_triggers": ["取经任务完成"]
+  },
+  "field_relations": {
+    "dominance": [
+      {"dominant": "佛界", "dominated": "天庭", "mechanism": "安天大会确立主导地位"},
+      {"dominant": "佛界", "dominated": "妖界", "mechanism": "取经收编妖怪"}
+    ],
+    "autonomy": [
+      {"field": "天庭", "autonomy_level": "低", "external_influences": ["佛界干预"]}
+    ]
+  }
+}
+```
+
+**必须返回严格JSON，直接输出，不要任何其他文字。**

package/skills/field-expert/prompts/boundary_analysis_simple.txt

@@ -0,0 +1,17 @@
+你是布迪厄场域理论专家。
+
+西游记有5个主要场域：
+1. 佛界 - 如来佛祖、观音菩萨、弥勒佛
+2. 天庭 - 玉皇大帝、太上老君、托塔李天王
+3. 人间 - 唐太宗、唐僧、李世民
+4. 妖界 - 牛魔王、白骨精、金角大王
+5. 取经团队 - 唐僧、孙悟空、猪八戒、沙僧
+
+请为每个场域写出2个核心行动者，用中文回答。
+
+回答格式（只要中文部分）：
+佛界：如来佛祖、观音菩萨
+天庭：玉皇大帝、太上老君
+人间：唐太宗、唐僧
+妖界：牛魔王、白骨精
+取经团队：唐僧、孙悟空

package/skills/field-expert/prompts/capital_analysis.txt

@@ -0,0 +1,87 @@
+## 资本分布分析提示词
+
+你是布迪厄场域理论专家。请基于以下扎根理论分析数据，分析各场域中的资本类型与分布。
+
+### 输入数据
+{context}
+
+### 分析任务
+
+请从以下四个维度进行资本分布分析：
+
+#### 1. 资本类型识别
+识别分析文本中出现的各类资本：
+- **经济资本**：物质财富、收入、资产等
+- **社会资本**：关系网络、社会声望、社会资源等
+- **文化资本**：学历、知识、技能、教育背景等
+- **符号资本**：称号、荣誉、合法性、权威等
+
+#### 2. 资本分布分析
+分析各类资本在不同行动者/场域间的分布：
+- 资本持有量排名
+- 资本分布的不平等程度
+- 资本占有的合法性来源
+
+#### 3. 资本转换路径
+分析资本之间的转换关系：
+- 经济资本→社会资本
+- 社会资本→文化资本
+- 文化资本→符号资本
+- 转换的条件和代价
+
+#### 4. 资本与位置关系
+分析资本占有与场域位置的关系：
+- 资本多寡如何决定场域位置
+- 位置如何影响资本获取
+- 资本策略与位置保持/跃迁
+
+### 输出格式
+
+请以JSON格式输出分析结果：
+
+```json
+{
+  "capital_types": {
+    "economic": {
+      "description": "经济资本描述",
+      "manifestations": ["表现形式1", "表现形式2"],
+      "key_actors": [{"actor": "行动者", "amount": "持有量"}]
+    },
+    "social": {
+      "description": "社会资本描述",
+      "manifestations": ["表现形式1", "表现形式2"],
+      "key_actors": [{"actor": "行动者", "network": "网络规模"}]
+    },
+    "cultural": {
+      "description": "文化资本描述",
+      "manifestations": ["表现形式1", "表现形式2"],
+      "key_actors": [{"actor": "行动者", "credentials": ["资质1", "资质2"]}]
+    },
+    "symbolic": {
+      "description": "符号资本描述",
+      "manifestations": ["表现形式1", "表现形式2"],
+      "key_actors": [{"actor": "行动者", "titles": ["称号1", "称号2"]}]
+    }
+  },
+  "capital_distribution": {
+    "ranking": [{"rank": 1, "actor": "行动者A", "total_capital": "资本总量", "dominant_type": "主导资本类型"}],
+    "inequality_level": "高/中/低",
+    "legitimacy_sources": ["来源1", "来源2"]
+  },
+  "conversion_paths": [
+    {
+      "from": "经济资本",
+      "to": "社会资本",
+      "conditions": ["条件1", "条件2"],
+      "cost": "转换代价",
+      "examples": [{"from": "财富", "to": "人脉", "example": "具体例子"}]
+    }
+  ],
+  "capital_position_relationship": {
+    "position_determinants": ["决定因素1", "决定因素2"],
+    "capital_strategies": ["策略1", "策略2"]
+  }
+}
+```
+
+请基于输入数据，生成详细的资本分布分析结果。

package/skills/field-expert/prompts/dynamics_analysis.txt

@@ -0,0 +1,89 @@
+## 场域动力学分析提示词
+
+你是布迪厄场域理论专家。请基于以下前期分析结果，进行场域动力学分析。
+
+### 输入数据
+{context}
+
+### 分析任务
+
+请从以下四个维度进行场域动力学分析：
+
+#### 1. 场域竞争分析
+分析场域内的竞争格局：
+- 竞争主体（主要竞争者及其实力对比）
+- 竞争资源（竞争的核心资源与利益）
+- 竞争策略（各主体的竞争策略与手段）
+- 竞争结果（竞争格局的变化趋势）
+
+#### 2. 权力关系分析
+分析场域内的权力结构与运作：
+- 权力来源（权力的基础与合法性来源）
+- 权力结构（权力的层级分布与网络结构）
+- 权力运作（权力的行使方式与机制）
+- 权力抵抗（抵抗权力的形式与效果）
+
+#### 3. 场域演变趋势
+分析场域的历史演变与未来趋势：
+- 发展阶段（场域发展的阶段划分）
+- 演变动力（推动场域变化的主要动力）
+- 演变阻力（阻碍场域变化的主要阻力）
+- 未来趋势（场域可能的发展方向）
+
+#### 4. 综合理论建构
+基于以上分析，提炼理论命题：
+- 核心发现（最关键的分析发现）
+- 理论命题（1-3个可检验的命题）
+- 研究启示（对相关研究的启示）
+
+### 输出格式
+
+请以JSON格式输出分析结果：
+
+```json
+{
+  "competition_analysis": {
+    "competitors": [
+      {
+        "actor": "竞争者名称",
+        "position": "场域位置",
+        "capital_advantage": "资本优势",
+        "strategy": "竞争策略"
+      }
+    ],
+    "competed_resources": ["资源1", "资源2"],
+    "competition_patterns": ["模式1", "模式2"],
+    "competition_trends": "竞争格局趋势"
+  },
+  "power_relations": {
+    "power_sources": [{"source": "来源", "holders": ["持有者1", "持有者2"]}],
+    "power_structure": {
+      "hierarchy": "层级结构描述",
+      "network": "网络结构描述"
+    },
+    "power_mechanisms": ["机制1", "机制2"],
+    "resistance_forms": ["形式1", "形式2"]
+  },
+  "field_evolution": {
+    "development_stages": [
+      {"stage": 1, "period": "时期", "characteristics": ["特征1", "特征2"]}
+    ],
+    "driving_forces": ["动力1", "动力2"],
+    "resistance_forces": ["阻力1", "阻力2"],
+    "future_trends": ["趋势1", "趋势2"]
+  },
+  "theory_construction": {
+    "core_findings": ["发现1", "发现2"],
+    "theoretical_propositions": [
+      {
+        "proposition": "命题内容",
+        "evidence": "支撑证据",
+        "testability": "可检验性"
+      }
+    ],
+    "research_implications": ["启示1", "启示2"]
+  }
+}
+```
+
+请基于输入数据，生成详细的场域动力学分析结果。

package/skills/field-expert/prompts/habitus_analysis.txt

@@ -0,0 +1,87 @@
+## 习性模式分析提示词
+
+你是布迪厄场域理论专家。请基于以下扎根理论分析数据，分析各场域行动者的习性模式。
+
+### 输入数据
+{context}
+
+### 分析任务
+
+请从以下四个维度进行习性模式分析：
+
+#### 1. 行动者习性识别
+识别各主要行动者的习性特征：
+- 行为模式（日常行为、消费选择、社交方式等）
+- 认知结构（价值观、思维方式、判断标准等）
+- 实践倾向（风险偏好、创新保守、合作竞争等）
+
+#### 2. 习性与场域关系
+分析习性如何与场域结构相互作用：
+- 场域如何塑造习性
+- 习性如何影响场域实践
+- 习性-场域的契合与错位
+
+#### 3. 符号暴力机制
+分析场域中的符号暴力：
+- 支配者实施的符号暴力形式
+- 被支配者的接受与内化
+- 符号暴力的再生产机制
+
+#### 4. 跨场域分析
+分析习性的跨场域作用：
+- 场域转换时的习性调适
+- 跨场域策略
+- 场域间习性冲突与协调
+
+### 输出格式
+
+请以JSON格式输出分析结果：
+
+```json
+{
+  "actors_habitus": [
+    {
+      "actor": "行动者名称",
+      "behavior_patterns": {
+        "daily_behavior": ["行为1", "行为2"],
+        "consumption_choice": ["选择1", "选择2"],
+        "social_style": ["风格1", "风格2"]
+      },
+      "cognitive_structure": {
+        "core_values": ["价值1", "价值2"],
+        "thinking_mode": "思维方式",
+        "judgment_criteria": ["标准1", "标准2"]
+      },
+      "practical_dispositions": {
+        "risk_preference": "偏好描述",
+        "innovation_tendency": "倾向描述",
+        "cooperation_competition": "倾向描述"
+      }
+    }
+  ],
+  "habitus_field_relationship": {
+    "field_shaping_habitus": ["塑造机制1", "塑造机制2"],
+    "habitus_influencing_practice": ["影响机制1", "影响机制2"],
+    "fit_misfit": [{"habitus": "习性类型", "field": "场域名称", "fit_level": "契合程度", "misfit_examples": ["错位例子1"]}]
+  },
+  "symbolic_violence": {
+    "dominant_violence": [{"form": "暴力形式", "mechanism": "机制描述", "victims": ["受害者1", "受害者2"]}],
+    "victim_acceptance": ["接受方式1", "接受方式2"],
+    "reproduction_mechanism": "再生产机制描述"
+  },
+  "cross_field_analysis": {
+    "field_transitions": [
+      {
+        "actor": "行动者",
+        "from_field": "场域A",
+        "to_field": "场域B",
+        "adaptation": "调适方式",
+        "conflict": "冲突表现"
+      }
+    ],
+    "cross_field_strategies": ["策略1", "策略2"]
+  }
+}
+```
+
+请基于输入数据，生成详细的习性模式分析结果。

package/skills/field-expert/pyproject.toml

@@ -0,0 +1,27 @@
+[tool.poetry]
+name = "field-expert"
+version = "1.0.0"
+description = "布迪厄场域理论专家分析技能，整合场域边界识别、资本分析和习性分析功能"
+authors = ["chinese-social-sciences-subagents"]
+license = "MIT"
+
+[tool.poetry.dependencies]
+python = "^3.8"
+pandas = {version = "^1.3.0", optional = true}
+numpy = {version = "^1.21.0", optional = true}
+networkx = {version = "^2.6.0", optional = true}
+matplotlib = {version = "^3.4.0", optional = true}
+seaborn = {version = "^0.11.0", optional = true}
+scipy = {version = "^1.7.0", optional = true}
+statsmodels = {version = "^0.13.0", optional = true}
+pingouin = {version = "^0.5.0", optional = true}
+
+[tool.poetry.extras]
+analysis = ["pandas", "numpy", "networkx", "matplotlib", "seaborn", "scipy", "statsmodels", "pingouin"]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.poetry.scripts]
+field-expert-analyzer = "scripts.field_expert_analyzer:main"

package/skills/field-expert/scripts/debug_output.txt

@@ -0,0 +1,4 @@
+{"name":"场域名", "actors":"[角色1", 角色2]}
+
+示例格式：
+[{"name":"佛界", "actors":"[如来佛祖", 观音菩萨]}, {"name":"天庭", "actors":"[玉皇大帝", 太上老君]}