ssci-subagent-skills 1.0.0

package/skills/alienation-analysis/scripts/workplace_satisfaction_analysis.py

@@ -0,0 +1,340 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+工作场所满意度分析器
+分析劳动者的工作满意度相关指标和数据
+"""
+
+import numpy as np
+import pandas as pd
+from typing import Dict, List, Tuple, Any
+from dataclasses import dataclass
+from datetime import datetime
+
+
+@dataclass
+class SatisfactionMetrics:
+    """满意度指标数据类"""
+    overall_satisfaction: float  # 总体满意度 (0-1)
+    job_security: float          # 工作安全感
+    work_environment: float      # 工作环境满意度
+    career_development: float    # 职业发展满意度
+    compensation: float          # 薪酬满意度
+    work_life_balance: float     # 工作生活平衡
+    management_satisfaction: float  # 管理满意度
+    autonomy: float              # 工作自主性
+    skill_utilization: float     # 技能运用程度
+    meaningful_work: float       # 工作意义感
+
+
+class WorkplaceSatisfactionAnalyzer:
+    """工作场所满意度分析器"""
+    
+    def __init__(self):
+        self.satisfaction_weights = {
+            'overall_satisfaction': 0.25,
+            'job_security': 0.15,
+            'work_environment': 0.10,
+            'career_development': 0.15,
+            'compensation': 0.10,
+            'work_life_balance': 0.10,
+            'management_satisfaction': 0.05,
+            'autonomy': 0.05,
+            'skill_utilization': 0.03,
+            'meaningful_work': 0.02
+        }
+        
+        self.satisfaction_thresholds = {
+            'high': 0.8,
+            'good': 0.6,
+            'moderate': 0.4,
+            'low': 0.2
+        }
+    
+    def analyze_workplace_satisfaction(self, satisfaction_data: Dict[str, float]) -> Dict[str, Any]:
+        """
+        分析工作场所满意度
+        
+        Args:
+            satisfaction_data: 满意度数据字典
+            
+        Returns:
+            分析结果字典
+        """
+        # 创建满意度指标对象
+        metrics = self._create_satisfaction_metrics(satisfaction_data)
+        
+        # 计算综合满意度
+        overall_satisfaction = self._calculate_weighted_satisfaction(metrics)
+        
+        # 分析满意度维度
+        dimension_analysis = self._analyze_satisfaction_dimensions(metrics)
+        
+        # 识别满意度问题
+        problem_areas = self._identify_satisfaction_problems(metrics)
+        
+        # 评估工作动机
+        motivation_assessment = self._assess_work_motivation(metrics)
+        
+        # 预测离职风险
+        turnover_risk = self._assess_turnover_risk(overall_satisfaction, dimension_analysis)
+        
+        return {
+            'overall_satisfaction': overall_satisfaction,
+            'satisfaction_level': self._determine_satisfaction_level(overall_satisfaction),
+            'dimension_analysis': dimension_analysis,
+            'problem_areas': problem_areas,
+            'motivation_assessment': motivation_assessment,
+            'turnover_risk': turnover_risk,
+            'improvement_priorities': self._prioritize_improvements(metrics),
+            'alienation_correlation': self._assess_alienation_correlation(metrics),
+            'analysis_timestamp': datetime.now().isoformat()
+        }
+    
+    def _create_satisfaction_metrics(self, data: Dict[str, float]) -> SatisfactionMetrics:
+        """创建满意度指标对象"""
+        # 设置默认值
+        default_values = {
+            'overall_satisfaction': 0.5,
+            'job_security': 0.5,
+            'work_environment': 0.5,
+            'career_development': 0.5,
+            'compensation': 0.5,
+            'work_life_balance': 0.5,
+            'management_satisfaction': 0.5,
+            'autonomy': 0.5,
+            'skill_utilization': 0.5,
+            'meaningful_work': 0.5
+        }
+        
+        # 合并数据
+        merged_data = {**default_values, **data}
+        
+        return SatisfactionMetrics(**merged_data)
+    
+    def _calculate_weighted_satisfaction(self, metrics: SatisfactionMetrics) -> float:
+        """计算加权满意度分数"""
+        weights = self.satisfaction_weights
+        values = [
+            metrics.overall_satisfaction * weights['overall_satisfaction'],
+            metrics.job_security * weights['job_security'],
+            metrics.work_environment * weights['work_environment'],
+            metrics.career_development * weights['career_development'],
+            metrics.compensation * weights['compensation'],
+            metrics.work_life_balance * weights['work_life_balance'],
+            metrics.management_satisfaction * weights['management_satisfaction'],
+            metrics.autonomy * weights['autonomy'],
+            metrics.skill_utilization * weights['skill_utilization'],
+            metrics.meaningful_work * weights['meaningful_work']
+        ]
+        
+        return sum(values)
+    
+    def _analyze_satisfaction_dimensions(self, metrics: SatisfactionMetrics) -> Dict[str, float]:
+        """分析各满意度维度"""
+        return {
+            'economic_satisfaction': (metrics.compensation + metrics.job_security) / 2,
+            'social_satisfaction': (metrics.work_environment + metrics.management_satisfaction) / 2,
+            'development_satisfaction': (metrics.career_development + metrics.skill_utilization) / 2,
+            'autonomy_satisfaction': (metrics.autonomy + metrics.meaningful_work) / 2,
+            'life_balance_satisfaction': metrics.work_life_balance
+        }
+    
+    def _identify_satisfaction_problems(self, metrics: SatisfactionMetrics) -> List[str]:
+        """识别满意度问题领域"""
+        problems = []
+        
+        if metrics.overall_satisfaction < self.satisfaction_thresholds['moderate']:
+            problems.append('总体工作满意度偏低')
+        if metrics.job_security < self.satisfaction_thresholds['moderate']:
+            problems.append('工作安全感不足')
+        if metrics.career_development < self.satisfaction_thresholds['moderate']:
+            problems.append('职业发展机会有限')
+        if metrics.compensation < self.satisfaction_thresholds['moderate']:
+            problems.append('薪酬满意度不足')
+        if metrics.work_life_balance < self.satisfaction_thresholds['moderate']:
+            problems.append('工作生活平衡失调')
+        if metrics.autonomy < self.satisfaction_thresholds['moderate']:
+            problems.append('工作自主性不足')
+        if metrics.meaningful_work < self.satisfaction_thresholds['moderate']:
+            problems.append('工作意义感缺失')
+        
+        return problems
+    
+    def _assess_work_motivation(self, metrics: SatisfactionMetrics) -> Dict[str, float]:
+        """评估工作动机"""
+        intrinsic_motivation = (
+            metrics.meaningful_work * 0.4 +
+            metrics.autonomy * 0.3 +
+            metrics.skill_utilization * 0.3
+        )
+        
+        extrinsic_motivation = (
+            metrics.compensation * 0.5 +
+            metrics.job_security * 0.3 +
+            metrics.career_development * 0.2
+        )
+        
+        return {
+            'intrinsic_motivation': intrinsic_motivation,
+            'extrinsic_motivation': extrinsic_motivation,
+            'motivation_balance': 1 - abs(intrinsic_motivation - extrinsic_motivation),
+            'motivation_health': (intrinsic_motivation + extrinsic_motivation) / 2
+        }
+    
+    def _assess_turnover_risk(self, overall_satisfaction: float, 
+                            dimension_analysis: Dict[str, float]) -> Dict[str, float]:
+        """评估离职风险"""
+        # 基于满意度计算离职风险
+        base_risk = 1 - overall_satisfaction
+        
+        # 考虑各个维度的影响
+        risk_factors = [
+            dimension_analysis.get('economic_satisfaction', 0.5),
+            dimension_analysis.get('development_satisfaction', 0.5),
+            dimension_analysis.get('autonomy_satisfaction', 0.5)
+        ]
+        
+        risk_adjustment = np.mean(risk_factors)
+        adjusted_risk = base_risk * (1 + (1 - risk_adjustment) * 0.5)
+        
+        return {
+            'overall_turnover_risk': min(1.0, adjusted_risk),
+            'risk_level': self._determine_risk_level(adjusted_risk),
+            'key_risk_factors': self._identify_risk_factors(dimension_analysis)
+        }
+    
+    def _determine_satisfaction_level(self, satisfaction: float) -> str:
+        """确定满意度等级"""
+        if satisfaction >= self.satisfaction_thresholds['high']:
+            return '高'
+        elif satisfaction >= self.satisfaction_thresholds['good']:
+            return '良好'
+        elif satisfaction >= self.satisfaction_thresholds['moderate']:
+            return '中等'
+        else:
+            return '低'
+    
+    def _determine_risk_level(self, risk: float) -> str:
+        """确定风险等级"""
+        if risk >= 0.8:
+            return '极高'
+        elif risk >= 0.6:
+            return '高'
+        elif risk >= 0.4:
+            return '中等'
+        else:
+            return '低'
+    
+    def _identify_risk_factors(self, dimension_analysis: Dict[str, float]) -> List[str]:
+        """识别风险因素"""
+        risk_factors = []
+        
+        for dimension, score in dimension_analysis.items():
+            if score < self.satisfaction_thresholds['moderate']:
+                risk_factors.append(f'{dimension}满意度低')
+        
+        return risk_factors
+    
+    def _prioritize_improvements(self, metrics: SatisfactionMetrics) -> List[Tuple[str, float]]:
+        """确定改进优先级"""
+        improvements = [
+            ('overall_satisfaction', metrics.overall_satisfaction),
+            ('job_security', metrics.job_security),
+            ('career_development', metrics.career_development),
+            ('compensation', metrics.compensation),
+            ('work_life_balance', metrics.work_life_balance),
+            ('work_environment', metrics.work_environment),
+            ('management_satisfaction', metrics.management_satisfaction),
+            ('autonomy', metrics.autonomy),
+            ('skill_utilization', metrics.skill_utilization),
+            ('meaningful_work', metrics.meaningful_work)
+        ]
+        
+        # 按满意度分数排序，分数越低优先级越高
+        improvements.sort(key=lambda x: x[1])
+        
+        return improvements[:5]  # 返回前5个优先级
+    
+    def _assess_alienation_correlation(self, metrics: SatisfactionMetrics) -> Dict[str, float]:
+        """评估与异化的相关性"""
+        # 工作满意度与劳动异化的负相关关系
+        labor_alienation_correlation = 1 - (
+            metrics.overall_satisfaction * 0.3 +
+            metrics.autonomy * 0.25 +
+            metrics.meaningful_work * 0.25 +
+            metrics.skill_utilization * 0.2
+        )
+        
+        return {
+            'labor_alienation_correlation': max(0, min(1, labor_alienation_correlation)),
+            'alienation_risk_level': self._determine_risk_level(labor_alienation_correlation),
+            'correlation_strength': self._determine_correlation_strength(labor_alienation_correlation)
+        }
+    
+    def _determine_correlation_strength(self, correlation: float) -> str:
+        """确定相关性强度"""
+        if correlation >= 0.8:
+            return '强'
+        elif correlation >= 0.6:
+            return '中等'
+        elif correlation >= 0.4:
+            return '弱'
+        else:
+            return '极弱'
+    
+    def batch_analyze_satisfaction(self, satisfaction_dataset: List[Dict[str, float]]) -> Dict[str, Any]:
+        """批量分析满意度数据"""
+        if not satisfaction_dataset:
+            return {'error': '数据为空'}
+        
+        results = []
+        for data in satisfaction_dataset:
+            result = self.analyze_workplace_satisfaction(data)
+            results.append(result)
+        
+        # 计算统计汇总
+        overall_satisfactions = [r['overall_satisfaction'] for r in results]
+        
+        return {
+            'individual_results': results,
+            'statistics': {
+                'mean_satisfaction': np.mean(overall_satisfactions),
+                'median_satisfaction': np.median(overall_satisfactions),
+                'std_satisfaction': np.std(overall_satisfactions),
+                'high_satisfaction_count': sum(1 for s in overall_satisfactions if s >= 0.8),
+                'low_satisfaction_count': sum(1 for s in overall_satisfactions if s < 0.4),
+                'total_respondents': len(satisfaction_dataset)
+            },
+            'analysis_timestamp': datetime.now().isoformat()
+        }
+
+
+def main():
+    """主函数 - 用于测试"""
+    analyzer = WorkplaceSatisfactionAnalyzer()
+    
+    # 测试数据
+    test_data = {
+        'overall_satisfaction': 0.6,
+        'job_security': 0.7,
+        'work_environment': 0.5,
+        'career_development': 0.4,
+        'compensation': 0.6,
+        'work_life_balance': 0.3,
+        'management_satisfaction': 0.7,
+        'autonomy': 0.4,
+        'skill_utilization': 0.5,
+        'meaningful_work': 0.3
+    }
+    
+    # 分析工作满意度
+    result = analyzer.analyze_workplace_satisfaction(test_data)
+    
+    # 打印结果
+    import json
+    print(json.dumps(result, ensure_ascii=False, indent=2))
+
+
+if __name__ == '__main__':
+    main()

package/skills/alienation_analysis/SKILL.md

@@ -0,0 +1,291 @@
+---
+name: alienation_analysis
+description: 鍩轰簬椹厠鎬濅富涔夊紓鍖栫悊璁猴紝瀵圭幇浠ｇぞ浼氫腑鐨勫姵鍔ㄥ紓鍖栥€佺ぞ浼氬叧绯诲紓鍖栥€佹秷璐瑰紓鍖栧拰鎶€鏈紓鍖栫幇璞¤繘琛屾繁搴﹀垎鏋愮殑鎶€鑳斤紝杩愮敤椹厠鎬濈殑鍥涢噸寮傚寲鐞嗚妗嗘灦锛岃瘎浼板紓鍖栫▼搴﹀苟鎻愬嚭瓒呰秺璺緞
+version: 2.0.0
+author: socienceAI.com
+license: MIT
+tags: [alienation-theory, marxist-analysis, labor-studies, social-phenomena, critical-theory]
+compatibility: Node.js environment
+metadata:
+  domain: social-sciences
+  methodology: marxist-critique
+  complexity: advanced
+  integration_type: analysis_tool
+  last_updated: "2025-12-26"
+allowed-tools: [node, bash, read_file, write_file]
+---
+
+# 寮傚寲鐜拌薄鍒嗘瀽鎶€鑳?(Alienation Analysis)
+
+## 姒傝堪
+
+寮傚寲鐜拌薄鍒嗘瀽鎶€鑳藉熀浜庨┈鍏嬫€濅富涔夊紓鍖栫悊璁猴紝瀵圭幇浠ｇぞ浼氫腑鐨勫姵鍔ㄥ紓鍖栥€佺ぞ浼氬叧绯诲紓鍖栥€佹秷璐瑰紓鍖栧拰鎶€鏈紓鍖栫幇璞¤繘琛屾繁搴﹀垎鏋愩€傝鎶€鑳借繍鐢ㄩ┈鍏嬫€濈殑鍥涢噸寮傚寲鐞嗚妗嗘灦锛堝姵鍔ㄨ€呬笌鍔冲姩浜у搧銆佸姵鍔ㄨ繃绋嬨€佺被鏈川浠ュ強浜轰笌浜轰箣闂村叧绯荤殑寮傚寲锛夛紝璇勪及寮傚寲绋嬪害骞舵彁鍑鸿秴瓒婂紓鍖栫殑瀹炶返璺緞銆?
+## 浣跨敤鏃舵満
+
+浣跨敤姝ゆ妧鑳藉綋鐢ㄦ埛璇锋眰锛?- 鍒嗘瀽鐜颁唬绀句細涓殑鍔冲姩寮傚寲鐜拌薄
+- 璇勪及鍔冲姩杩囩▼涓庡姵鍔ㄤ骇鍝佺殑鍒嗙绋嬪害
+- 鍒嗘瀽绀句細鍏崇郴鐨勫紓鍖栧拰浜洪檯鐤忕鐜拌薄
+- 璇勪及娑堣垂涓讳箟鏂囧寲涓殑寮傚寲鐜拌薄
+- 鍒嗘瀽鎶€鏈彂灞曞甫鏉ョ殑寮傚寲闂
+- 鐞嗚В骞冲彴缁忔祹涓殑鏂板瀷寮傚寲褰㈠紡
+
+## 蹇€熷紑濮?
+褰撶敤鎴疯姹傚紓鍖栫幇璞″垎鏋愭椂锛?1. **璇嗗埆**寮傚寲鐜拌薄鐨勭被鍨嬪拰琛ㄧ幇
+2. **搴旂敤**椹厠鎬濆洓閲嶅紓鍖栫悊璁烘鏋?3. **璇勪及**寮傚寲绋嬪害鍜屽奖鍝?4. **鍒嗘瀽**寮傚寲浜х敓鐨勬牴婧?5. **鎻愬嚭**瓒呰秺寮傚寲鐨勮矾寰?
+## 鏍稿績鍔熻兘
+
+### 1. 鍔冲姩寮傚寲涓撻」鍒嗘瀽
+- **鍔冲姩杩囩▼寮傚寲鍒嗘瀽**锛氬垎鏋愬姵鍔ㄨ€呬笌鍔冲姩杩囩▼銆佸姵鍔ㄤ骇鍝併€佸姵鍔ㄦ湰璐ㄧ殑鍒嗙绋嬪害
+- **鍔冲姩鏉′欢璇勪及**锛氳瘎浼板伐浣滅幆澧冦€佸姵鍔ㄥ己搴︺€佸姵鍔ㄤ繚鎶ょ殑寮傚寲姘村钩
+
+### 2. 绀句細鍏崇郴寮傚寲鍒嗘瀽
+- **浜洪檯浜ゅ線寮傚寲璇勪及**锛氬垎鏋愪汉涓庝汉涔嬮棿鐪熷疄鍏崇郴鐨勫紓鍖栫▼搴?- **绀句細鑱旂郴鐤忕搴?*锛氳瘎浼颁釜浣撲笌绀句細鐨勮仈绯绘柇瑁傜▼搴?
+### 3. 娑堣垂寮傚寲璇嗗埆
+- **娑堣垂琛屼负寮傚寲鍒嗘瀽**锛氬垎鏋愭秷璐硅涓虹殑鎰忎箟鍋忕绋嬪害
+- **鐗╂鑶ㄨ儉绋嬪害璇勪及**锛氳瘎浼扮墿璐ㄦ鏈涗笌鐪熷疄闇€瑕佺殑寮傚寲姘村钩
+
+### 4. 鎶€鏈紓鍖栬瘎浼?- **鎶€鏈緷璧栫▼搴﹁瘎浼?*锛氬垎鏋愪釜浣撳鎶€鏈殑杩囧害渚濊禆绋嬪害
+- **鎶€鏈帶鍒跺弽鍒跺垎鏋?*锛氬垎鏋愭妧鏈浣曟帶鍒朵汉绫昏涓哄拰鎬濈淮
+
+### 5. 寮傚寲鐩镐簰鍏崇郴鍒嗘瀽
+- **寮傚寲鐜拌薄鍏宠仈鎬?*锛氬垎鏋愪笉鍚屽紓鍖栫幇璞￠棿鐨勭浉浜掑叧绯?- **寮傚寲浼犲鏈哄埗**锛氬垎鏋愬紓鍖栫幇璞＄殑鐩镐簰褰卞搷鍜屼紶瀵艰矾寰?
+### 6. 寮傚寲瓒呰秺璺緞璁捐
+- **璁よ瘑瑙夐啋璺緞**锛氶€氳繃璁よ瘑瑙夐啋瓒呰秺寮傚寲
+- **瀹炶返鏀归€犺矾寰?*锛氶€氳繃绀句細瀹炶返鏀归€犲紓鍖栨潯浠?
+## 璇︾粏浣跨敤娴佺▼
+
+### 绗竴姝ワ細璇嗗埆寮傚寲鐜拌薄
+```javascript
+// 瀹氫箟闇€瑕佸垎鏋愮殑寮傚寲鐜拌薄
+const alienationPhenomenon = {
+  phenomenon: "骞冲彴缁忔祹涓殑鍔冲姩寮傚寲",
+  data: {
+    laborData: {
+      workingConditions: "绠楁硶鎺у埗涓嬬殑宸ヤ綔鏉′欢",
+      autonomyLevel: "浣庤嚜涓绘€?,
+      meaningfulness: "宸ヤ綔鎰忎箟鎰熺己澶?,
+      relationshipWithProducts: "涓庡姵鍔ㄦ垚鏋滅枏绂?
+    },
+    socialData: {
+      peerInteraction: "鍚屼簨闂寸己涔忕湡瀹炰簰鍔?,
+      communityConnection: "涓庣ぞ鍖鸿仈绯昏杽寮?,
+      socialIdentity: "閫氳繃骞冲彴韬唤瀹氫箟鑷垜"
+    },
+    consumptionData: {
+      consumptionPatterns: "閫氳繃娑堣垂鏋勫缓韬唤",
+      materialDesire: "杩囧害鐗╄川娆叉湜",
+      symbolicConsumption: "绗﹀彿娑堣垂涓诲"
+    },
+    technologyData: {
+      dependencyLevel: "瀵瑰钩鍙版妧鏈珮搴︿緷璧?,
+      algorithmControl: "绠楁硶椹卞姩鐨勮涓烘ā寮?,
+      digitalIsolation: "鏁板瓧鍖栧鑷寸殑绀句氦闅旂"
+    }
+  },
+  analysisType: "alienation_analysis",
+  focusAreas: ["labor", "social", "consumption", "technology"],
+  depthLevel: "comprehensive",
+  theoryFramework: "marxist_alienation_theory"
+};
+```
+
+**鍏抽敭瑕佺偣**锛?- 鏄庣‘寮傚寲鐜拌薄鐨勫叿浣撹〃鐜?- 鏀堕泦鐩稿叧鐨勭ぞ浼氥€佺粡娴庛€佹妧鏈暟鎹?- 纭畾鍒嗘瀽鐨勭悊璁烘鏋?
+### 绗簩姝ワ細搴旂敤椹厠鎬濆洓閲嶅紓鍖栫悊璁?```javascript
+// 搴旂敤鍥涢噸寮傚寲鐞嗚妗嗘灦杩涜鍒嗘瀽
+const fourFoldAlienationAnalysis = await alienationAnalysisSkill.execute({
+  phenomenonData: alienationPhenomenon,
+  theoreticalFramework: "four-fold-alienation"
+});
+```
+
+**鍒嗘瀽鍐呭**锛?- **涓庡姵鍔ㄤ骇鍝佺浉寮傚寲**锛氬垎鏋愬姵鍔ㄨ€呬笌鍔冲姩鎴愭灉鐨勫叧绯荤枏绂?- **涓庡姵鍔ㄨ繃绋嬬浉寮傚寲**锛氬垎鏋愬姵鍔ㄨ€呭湪鍔冲姩杩囩▼涓殑琚姩鐘舵€?- **涓庣被鏈川鐩稿紓鍖?*锛氬垎鏋愪汉鐨勫垱閫犳€ф湰璐ㄧ殑涓уけ
+- **涓庝粬浜虹浉寮傚寲**锛氬垎鏋愪汉涓庝汉涔嬮棿鐪熷疄鍏崇郴鐨勫紓鍖?
+### 绗笁姝ワ細璁捐寮傚寲瓒呰秺璺緞
+```javascript
+// 璁捐寮傚寲瓒呰秺璺緞
+const transcendencePath = await alienationAnalysisSkill.designTranscendencePath({
+  alienationAnalysis: {
+    labor: laborAlienationAssessment,
+    social: socialAlienationAnalysis,
+    consumption: consumptionAlienationAnalysis,
+    technology: technologyAlienationAnalysis,
+    interrelations: interrelationAnalysis
+  },
+  framework: "praxis-transformation-theory"
+});
+```
+
+**璁捐鍐呭**锛?- 璁よ瘑瑙夐啋璺緞
+- 瀹炶返鏀归€犺矾寰?- 鍒跺害鍙橀潻璺緞
+- 鏂囧寲閲嶅璺緞
+
+## 鎶€鏈疄鐜?
+### 鏋舵瀯璁捐
+- **鐞嗚椹卞姩**锛氫互椹厠鎬濅富涔夊紓鍖栫悊璁轰负鏍稿績妗嗘灦
+- **澶氱淮鍒嗘瀽**锛氫粠鍔冲姩銆佺ぞ浼氥€佹秷璐广€佹妧鏈瓑澶氫釜缁村害鍒嗘瀽寮傚寲
+- **閲忓寲璇勪及**锛氬寮傚寲绋嬪害杩涜閲忓寲璇勪及
+- **瀹炶返瀵煎悜**锛氭彁渚涘叿浣撶殑寮傚寲瓒呰秺璺緞
+
+### 鏁版嵁缁撴瀯
+```javascript
+// 杈撳叆鏁版嵁缁撴瀯
+{
+  phenomenon: "寮傚寲鐜拌薄鎻忚堪",
+  data: {
+    laborData: {
+      workingConditions: "宸ヤ綔鏉′欢",
+      autonomyLevel: "鑷富鎬ф按骞?,
+      meaningfulness: "鎰忎箟鎰熺▼搴?,
+      relationshipWithProducts: "涓庝骇鍝佸叧绯?
+    },
+    socialData: {
+      peerInteraction: "鍚屼即浜掑姩",
+      communityConnection: "绀惧尯鑱旂郴",
+      socialIdentity: "绀句細韬唤"
+    },
+    consumptionData: {
+      consumptionPatterns: "娑堣垂妯″紡",
+      materialDesire: "鐗╄川娆叉湜",
+      symbolicConsumption: "绗﹀彿娑堣垂"
+    },
+    technologyData: {
+      dependencyLevel: "渚濊禆绋嬪害",
+      algorithmControl: "绠楁硶鎺у埗",
+      digitalIsolation: "鏁板瓧闅旂"
+    }
+  },
+  analysisType: "alienation_analysis",
+  focusAreas: ["labor", "social", "consumption", "technology"],
+  depthLevel: "comprehensive",
+  theoryFramework: "marxist_alienation_theory"
+}
+
+// 杈撳嚭缁撴灉缁撴瀯
+{
+  analysisResult: {
+    laborAlienation: {
+      processAlienation: "鍔冲姩杩囩▼寮傚寲绋嬪害",
+      productAlienation: "鍔冲姩浜у搧寮傚寲绋嬪害",
+      speciesAlienation: "绫绘湰璐ㄥ紓鍖栫▼搴?,
+      socialAlienation: "绀句細鍏崇郴寮傚寲绋嬪害"
+    },
+    socialAlienation: "绀句細鍏崇郴寮傚寲鍒嗘瀽",
+    consumptionAlienation: "娑堣垂寮傚寲鍒嗘瀽",
+    technologyAlienation: "鎶€鏈紓鍖栧垎鏋?,
+    alienationInterrelations: "寮傚寲鐩镐簰鍏崇郴鍒嗘瀽",
+    transcendencePath: "瓒呰秺寮傚寲璺緞"
+  },
+  qualityMetrics: {
+    theoreticalAccuracy: 0.88,
+    analysisDepth: 0.82,
+    marxistAlignment: 0.91,
+    practicalGuidance: 0.85
+  },
+  interventionRecommendations: {
+    immediateActions: "鍗虫椂琛屽姩寤鸿",
+    mediumStrategies: "涓湡绛栫暐瑙勫垝",
+    longTermVision: "闀挎湡鎰挎櫙鐩爣"
+  }
+}
+```
+
+## 杈撳嚭鏍煎紡
+
+缁熶竴鐨勪笁灞侸SON鏍煎紡锛?
+```json
+{
+  "summary": {
+    "alienation_types_identified": ["labor", "social", "consumption"],
+    "alienation_severity_score": 78,
+    "primary_alienation_sources": ["algorithm_control", "market_pressures"],
+    "transcendence_readiness": 0.65
+  },
+  "details": {
+    "analysisResult": {
+      "laborAlienation": {
+        "processAlienation": "鍔冲姩杩囩▼寮傚寲绋嬪害楂橈紝宸ヤ汉缂轰箯鑷富鎬?,
+        "productAlienation": "涓庡姵鍔ㄦ垚鏋滅枏绂伙紝鏃犳硶浠庝骇鍝佷腑鑾峰緱鎴愬氨鎰?,
+        "speciesAlienation": "鍒涢€犳€ф湰璐ㄨ鍘嬫姂锛屾拨涓虹敓浜у伐鍏?,
+        "socialAlienation": "鍚屼簨闂村叧绯诲伐鍏峰寲锛岀己涔忕湡姝ｅ悎浣?
+      },
+      "socialAlienation": {
+        "interpersonalDisconnection": "浜洪檯鐪熷疄鑱旂郴鍑忓皯锛岀ぞ浜よ〃闈㈠寲",
+        "communityDisintegration": "绀惧尯褰掑睘鎰熷噺寮憋紝涓綋鍘熷瓙鍖?,
+        "collectiveIdentityCrisis": "闆嗕綋璁ゅ悓鎰熺己澶憋紝涓汉涓讳箟鐩涜"
+      },
+      "consumptionAlienation": {
+        "commodityFetishism": "鍟嗗搧鎷滅墿鏁欑洓琛岋紝蹇借浣跨敤浠峰€?,
+        "identityThroughConsumption": "閫氳繃娑堣垂鏋勫缓韬唤锛岀湡瀹炶嚜鎴戣糠澶?,
+        "insatiableDesires": "鐗╄川娆叉湜鏃犻檺鑶ㄨ儉锛岀湡瀹為渶姹傝鎺╃洊"
+      },
+      "technologyAlienation": {
+        "digitalDependency": "瀵规暟瀛楁妧鏈繃搴︿緷璧栵紝鑷富鎬ч檷浣?,
+        "algorithmicControl": "绠楁硶鎺у埗琛屼负锛岄€夋嫨鏉冭鍓ュず",
+        "virtualIsolation": "铏氭嫙绀句氦澧炲锛岀湡瀹炶仈绯诲噺灏?
+      },
+      "alienationInterrelations": {
+        "amplificationEffects": "鍔冲姩寮傚寲鍔犲墽娑堣垂寮傚寲锛屽舰鎴愭伓鎬у惊鐜?,
+        "feedbackLoops": "鎶€鏈紓鍖栧己鍖栫ぞ浼氬紓鍖栵紝鐩镐簰淇冭繘"
+      },
+      "transcendencePath": {
+        "awarenessPath": "閫氳繃鏁欒偛鍜屾壒鍒ゆ€濈淮瑙夐啋寮傚寲鎰忚瘑",
+        "praxisPath": "閫氳繃闆嗕綋琛屽姩鏀归€犲紓鍖栨潯浠?,
+        "systemicChange": "鎺ㄥ姩鍒跺害鍜岀粨鏋勫眰闈㈢殑鍙橀潻",
+        "culturalRenewal": "閲嶅缓浠ヤ汉涓烘湰鐨勬枃鍖栦环鍊艰"
+      }
+    },
+    "qualityMetrics": {
+      "theoreticalAccuracy": 0.88,
+      "analysisDepth": 0.82,
+      "marxistAlignment": 0.91,
+      "practicalGuidance": 0.85
+    },
+    "interventionRecommendations": {
+      "immediateActions": [
+        "鍔犲己鍔冲姩鑰呯殑缁勭粐鍜屽洟缁?,
+        "鎻愰珮瀵瑰紓鍖栫幇璞＄殑璁よ瘑鍜屾壒鍒よ兘鍔?
+      ],
+      "mediumStrategies": [
+        "鎺ㄥ姩骞冲彴娌荤悊鐨勬皯涓诲寲",
+        "寤虹珛鏇村叕骞崇殑鍒╃泭鍒嗛厤鏈哄埗"
+      ],
+      "longTermVision": [
+        "鏋勫缓浠ヤ汉鐨勫叏闈㈠彂灞曚负涓績鐨勭粡娴庣ぞ浼氭ā寮?,
+        "瀹炵幇鎶€鏈负浜烘湇鍔¤€岄潪鐩稿弽"
+      ]
+    }
+  },
+  "metadata": {
+    "timestamp": "2025-12-26T10:30:00Z",
+    "version": "2.0.0",
+    "skill": "alienation_analysis",
+    "validationScore": 85
+  }
+}
+```
+
+## 璐ㄩ噺妫€鏌ユ竻鍗?
+鍦ㄥ畬鎴愬紓鍖栧垎鏋愬悗锛岃妫€鏌ヤ互涓嬮」鐩細
+
+- [ ] 寮傚寲鐜拌薄璇嗗埆鍑嗙‘
+- [ ] 椹厠鎬濆紓鍖栫悊璁哄簲鐢ㄦ纭?- [ ] 鍥涢噸寮傚寲鍒嗘瀽瀹屾暣
+- [ ] 寮傚寲绋嬪害璇勪及鍚堢悊
+- [ ] 瓒呰秺璺緞鍒囧疄鍙
+- [ ] 楠岃瘉鍒嗘暟杈惧埌瑕佹眰锛?0鍒嗕互涓婏級
+
+## 甯歌闂
+
+**蹇€熻瘖鏂?*锛?- 鍒嗘瀽缁撴灉涓嶅畬鏁?鈫?妫€鏌ヨ緭鍏ユ暟鎹槸鍚﹀畬鏁?- 寮傚寲绋嬪害璇勪及涓嶅噯纭?鈫?楠岃瘉鐞嗚妗嗘灦搴旂敤
+- 楠岃瘉鍒嗘暟浣?鈫?妫€鏌ョ悊璁轰竴鑷存€?
+## 娣卞叆瀛︿範
+
+鏇村璇︾粏鐞嗚鑳屾櫙鍜屽垎鏋愭柟娉曡鍙傝锛歚references/marx-alienation-theory.md` 鍜?`references/modern-alienation.md`
+
+## 瀹屾垚鏍囧織
+
+瀹屾垚楂樿川閲忕殑寮傚寲鐜拌薄鍒嗘瀽搴斾骇鍑猴細
+1. 瀹屾暣鐨勫洓閲嶅紓鍖栧垎鏋愮粨鏋?2. 鍑嗙‘鐨勫紓鍖栫▼搴﹁瘎浼?3. 鍒囧疄鍙鐨勮秴瓒婅矾寰?4. 绗﹀悎椹厠鎬濅富涔夌悊璁烘鏋剁殑鍒嗘瀽
+
+---
+
+*姝ゆ妧鑳戒负绀句細鐜拌薄鍒嗘瀽鎻愪緵涓撲笟鐨勫紓鍖栫悊璁哄垎鏋愭敮鎸侊紝鍩轰簬椹厠鎬濈殑缁忓吀鐞嗚妗嗘灦锛岀‘淇濆垎鏋愮殑鐞嗚娣卞害鍜屽疄璺垫寚瀵兼剰涔夛紝涓虹悊瑙ｇ幇浠ｇぞ浼氶棶棰樺拰瀵绘眰瑙ｅ喅鏂规鎻愪緵鐞嗚鍩虹銆?

package/skills/alienation_analysis/__init__.py

@@ -0,0 +1 @@
+# Alienation Analysis Skill Package

package/skills/alienation_analysis/scripts/__init__.py

@@ -0,0 +1 @@
+# Alienation Analysis Scripts Package