jd-analyzer

JD Analyzer Skill

Trigger Conditions

When the user needs to:

Analyze a job description (JD)
Extract key skills and requirements
Assess the match between a resume and a JD
Identify skill gaps
Prepare for an interview for a specific company

Analysis Dimensions

1. Basic Information

Job title and level
Team and department
Work location
Job type (full-time/part-time/internship)

2. Skills Analysis

Programming Languages

Required languages (Required)
Preferred languages (Preferred)
Frameworks and libraries
Tools and platforms

System Design

Distributed systems
Microservices architecture
Database design
Scalability requirements
Performance optimization

Domain Knowledge

Industry-specific knowledge
Business domain understanding
Professional terminology

3. Soft Skills

Communication skills
Leadership
Team collaboration
Problem solving
Adaptability

4. Qualification Requirements

Educational background (degree, major)
Years of work experience
Experience in a specific field
Certifications or certificates

5. Scope of Responsibilities

Main job duties
Project types
Scope of impact
Decision-making authority

6. Bonus Points

Preferred skills
Additional certifications or experience
Special contributions or achievements

Workflow

Step 1: Extract Raw Information

Extract from the JD text:

All skill keywords
Experience requirements
Education requirements
Responsibility descriptions

Step 2: Structured Analysis

Classify the extracted information into:

{
  "structured_analysis": {
    "required_skills": [...],
    "preferred_skills": [...],
    "responsibilities": [...],
    "minimum_qualifications": [...],
    "preferred_qualifications": [...]
  }
}

Step 3: Skill Matching

Compare with the user's base resume (data/resume/base.json):

{
  "skill_match_analysis": {
    "matched_skills": [
      {"skill": "Python", "proficiency": "expert"}
    ],
    "partial_match_skills": [
      {"skill": "Java", "proficiency": "intermediate", "required": "advanced"}
    ],
    "missing_skills": [
      {"skill": "C++", "action": "需要学习基础"}
    ]
  }
}

Step 4: Generate Recommendations

Based on the match analysis, provide:

Skills that need to be supplemented
Experience that should be highlighted
Key points for interview preparation
Resume optimization suggestions

Skill Extraction Patterns

Programming Language Identification

Identify the following patterns:

"Proficiency in/with X"
"Experience with/using X"
"Strong knowledge of X"
"X developer"
"X, Y, or Z"

Experience Level Assessment

Entry: 0-2 years
Mid: 2-5 years
Senior: 5+ years
Staff/Principal: 8+ years

System Design Keywords

"Distributed systems"
"Microservices architecture"
"Scalable systems"
"High-availability"
"Large-scale systems"
"Cloud-native"

Soft Skill Identification

"Excellent communication"
"Leadership experience"
"Team player"
"Problem-solving skills"
"Self-motivated"

Output Format

Company Information File Update

Update data/companies/{company}.json 's job_descriptions section:

{
  "job_descriptions": {
    "pos_001": {
      "title": "Software Engineer III",
      "description_source": "...",
      "scraped_at": "2025-01-09T00:00:00Z",
      "raw_text": "完整JD文本...",

      "structured_analysis": {
        "required_skills": ["Python", "Distributed Systems"],
        "preferred_skills": ["Kubernetes", "ML"],
        "responsibilities": ["设计并开发软件"],
        "minimum_qualifications": ["计算机学位", "3年经验"],
        "preferred_qualifications": ["硕士", "5年经验"]
      },

      "skill_match_analysis": {
        "matched_skills": [...],
        "partial_match_skills": [...],
        "missing_skills": [...]
      }
    }
  }
}

Usage Examples

Scenario 1: When Adding a New Company

The user provides JD text, automatically:

Extract all skills and requirements
Analyze the match with the user's resume
Generate a structured analysis report
Save to the company information file

Scenario 2: Before Resume Optimization

Provide for the resume optimizer:

Key skills list
Priority ranking
Match score
Optimization suggestions

Scenario 3: During interview preparation

Generate interview preparation focus points:

Technical topics list
Possible question types
Areas requiring in-depth research

Matching rules

Exact match

User has direct experience using it
Actually applied in projects
Can discuss in depth

Partial match

Understands related technologies
Has experience with similar technologies
Can learn quickly

Missing

No experience at all
Needs to learn from scratch
Suggested learning path

Weight calculation

Used for match scoring:

Required skills: weight 2.0
Preferred skills: weight 1.0
Bonus items: weight 0.5

匹配度 = Σ(匹配等级 × 权重) / Σ(最大权重)

Notes

Context understanding: Consider the overall context of the JD, not isolated keywords
Skill categorization: Group skills with different names but the same essence
Company characteristics: Identify the company's technology culture (e.g., Google values scalability)
Implicit requirements: Identify expectations not explicitly stated in the JD
Dynamic updates: Re-evaluate the match score as the user's skills improve

Advanced analysis features (new in Phase 2)

Company culture analysis

Culture indicator identification

Work culture keywords:

{
  "culture_indicators": {
    "pace": {
      "fast": ["fast-paced", "move fast", "rapid iteration", "agile", "startup environment"],
      "balanced": ["work-life balance", "sustainable pace", "flexible hours"],
      "intense": ["high-pressure", "demanding", "deadline-driven"]
    },
    "collaboration": {
      "collaborative": ["team player", "cross-functional", "collaborate", "pair programming"],
      "independent": ["self-starter", "independent", "autonomous", "own initiatives"],
      "leadership": ["lead", "mentor", "guide", "influence", "drive decisions"]
    },
    "innovation": {
      "innovative": ["innovative", "cutting-edge", "pioneer", "breakthrough", "novel"],
      "stable": ["stable", "proven", "established", "reliable", "mature"],
      "scalable": ["scale", "growth", "expand", "multiply", "massive impact"]
    },
    "values": {
      "customer_obsessed": ["customer obsessed", "customer first", "user-centric"],
      "data_driven": ["data-driven", "analytics", "metrics", "experimentation"],
      "ownership": ["ownership", "end-to-end", "responsibility", "accountability"],
      "excellence": ["high standards", "excellence", "quality", "best practices"]
    }
  }
}

Culture match analysis

{
  "culture_analysis": {
    "company_culture_type": "Innovative & Fast-paced",
    "key_culture_traits": [
      "Data-driven decision making",
      "Fast iteration and experimentation",
      "Collaborative cross-functional work",
      "High ownership and accountability"
    ],
    "culture_indicators_found": [
      {"trait": "fast-paced", "evidence": "fast-paced environment", "frequency": 3},
      {"trait": "data-driven", "evidence": "data-driven approach", "frequency": 5},
      {"trait": "collaborative", "evidence": "cross-functional teams", "frequency": 2}
    ],
    "fit_assessment": {
      "score": 85,
      "strengths": ["匹配快速迭代环境", "有跨团队协作经验"],
      "considerations": ["需要适应高压环境", "强调数据驱动决策"]
    }
  }
}

Salary range detection

Salary information extraction

Recognition patterns:

# 基础薪资
"(\$?\d{2,3}k?[-–to]\$?\d{2,3}k?)\s*(per year|annually|/year|annual)"

# 股票/股权
"(stock|equity|RSU|option|grant).*?(\$?\d{2,3}k?)"

# 奖金
"(bonus|signing|target).*?(\$?\d{1,2}k?|\d{1,2}%)"

# 总薪酬
"(total compensation|TC|OTE).*?(\$?\d{2,3}k?)"

Salary structure analysis:

{
  "salary_analysis": {
    "base_salary": {
      "range": "$150,000 - $200,000",
      "currency": "USD",
      "period": "yearly",
      "confidence": "high"
    },
    "equity": {
      "mentioned": true,
      "estimated_range": "$50,000 - $100,000/year",
      "type": "RSU",
      "vesting": "4 years"
    },
    "bonus": {
      "mentioned": true,
      "percentage": "20%",
      "estimated_value": "$30,000 - $40,000"
    },
    "total_compensation": {
      "estimated_range": "$230,000 - $340,000",
      "breakdown": ["Base: $150k-$200k", "Bonus: $30k-$40k", "Equity: $50k-$100k"]
    },
    "market_comparison": {
      "percentile": "75th",
      "comparison": "Above market average"
    }
  }
}

Regional salary adjustment

{
  "location_adjustments": {
    "SF Bay Area": 1.0,
    "New York": 0.95,
    "Seattle": 0.90,
    "Austin": 0.80,
    "Remote (US)": 0.85,
    "Beijing": 0.60,
    "Shanghai": 0.62
  }
}

Enhanced skill extraction patterns

AI/ML skill identification

{
  "ai_ml_skills": {
    "machine_learning": ["Machine Learning", "ML", "Deep Learning", "Neural Networks"],
    "frameworks": ["TensorFlow", "PyTorch", "Keras", "Scikit-learn", "MXNet"],
    "nlp": ["NLP", "Natural Language Processing", "Transformers", "BERT", "GPT"],
    "computer_vision": ["Computer Vision", "CV", "Image Processing", "CNN"],
    "mlops": ["MLOps", "ML Engineering", "Model Deployment", "Feature Engineering"]
  }
}

Cloud platform skills

{
  "cloud_skills": {
    "aws": ["AWS", "Amazon Web Services", "EC2", "S3", "Lambda", "RDS", "DynamoDB"],
    "gcp": ["GCP", "Google Cloud", "GKE", "BigQuery", "Cloud Functions"],
    "azure": ["Azure", "Microsoft Azure", "AKS", "Azure Functions"],
    "cloud_native": ["Kubernetes", "K8s", "Docker", "Helm", "Istio", "Service Mesh"]
  }
}

Data skills

{
  "data_skills": {
    "databases": ["SQL", "NoSQL", "PostgreSQL", "MySQL", "MongoDB", "Redis", "Cassandra"],
    "data_engineering": ["ETL", "Data Pipeline", "Spark", "Kafka", "Airflow", "Hadoop"],
    "analytics": ["Data Analysis", "Analytics", "Visualization", "Tableau", "Power BI"],
    "big_data": ["Big Data", "Distributed Computing", "Data Lakes", "Data Warehousing"]
  }
}

Multilingual JD support

Language detection

{
  "language_detection": {
    "detected_language": "zh-CN",
    "confidence": 0.95,
    "supported_languages": ["en", "zh-CN", "zh-TW", "ja", "ko"],
    "translation_needed": false
  }
}

Bilingual JD processing

{
  "bilingual_jd": {
    "primary_language": "en",
    "secondary_language": "zh-CN",
    "merge_strategy": "primary_first",
    "skill_extraction": {
      "from_primary": true,
      "from_secondary": true,
      "merge_duplicates": true
    }
  }
}

Cross-language skill mapping

{
  "skill_translation": {
    "machine_learning": {
      "en": "Machine Learning",
      "zh": "机器学习",
      "ja": "機械学習",
      "ko": "기계 학습"
    },
    "distributed_systems": {
      "en": "Distributed Systems",
      "zh": "分布式系统",
      "ja": "分散システム",
      "ko": "분산 시스템"
    }
  }
}

Intelligent skill grouping

Related skill clustering

{
  "skill_clusters": {
    "backend_development": {
      "skills": ["Python", "Java", "Go", "APIs", "Microservices"],
      "weight": 2.0,
      "priority": "high"
    },
    "data_processing": {
      "skills": ["SQL", "ETL", "Kafka", "Spark"],
      "weight": 1.5,
      "priority": "medium"
    },
    "frontend": {
      "skills": ["React", "JavaScript", "TypeScript", "HTML/CSS"],
      "weight": 1.0,
      "priority": "low"
    }
  }
}

Skill dependency analysis

{
  "skill_dependencies": {
    "Kubernetes": {
      "prerequisites": ["Docker", "Linux", "Networking"],
      "related": ["Helm", "Istio", "Prometheus"],
      "advanced": ["Cloud Native", "Service Mesh"]
    },
    "Machine Learning": {
      "prerequisites": ["Python", "Statistics", "Linear Algebra"],
      "related": ["Deep Learning", "MLOps", "Data Engineering"],
      "advanced": ["Neural Networks", "Computer Vision", "NLP"]
    }
  }
}

Implicit skill requirement identification

Infer skills based on responsibilities

{
  "inferred_skills": {
    "from_responsibility": "Design and build scalable web applications",
    "inferred_skills": [
      {"skill": "Web Development", "confidence": 0.95},
      {"skill": "API Design", "confidence": 0.90},
      {"skill": "Scalability", "confidence": 0.85},
      {"skill": "Performance Optimization", "confidence": 0.80}
    ],
    "reasoning": "Building scalable web apps requires these core skills"
  }
}

Infer experience based on project scale

{
  "scale_inference": {
    "indicators": ["millions of users", "petabytes of data", "high QPS"],
    "inferred_requirements": [
      {"skill": "Distributed Systems", "importance": "critical"},
      {"skill": "Scalability", "importance": "critical"},
      {"skill": "Performance Tuning", "importance": "high"},
      {"skill": "System Design", "importance": "high"}
    ]
  }
}

Market demand analysis

Skill trend analysis

{
  "market_analysis": {
    "skill_demand": {
      "Distributed Systems": {
        "demand_level": "high",
        "trend": "increasing",
        "market_saturation": "low"
      },
      "Kubernetes": {
        "demand_level": "very_high",
        "trend": "stable",
        "market_saturation": "medium"
      }
    },
    "competitiveness": {
      "score": 75,
      "interpretation": "Moderately competitive position",
      "recommendations": [
        "Strengthen distributed systems fundamentals",
        "Gain hands-on Kubernetes experience",
        "Build system design portfolio"
      ]
    }
  }
}

Enhanced output formats

Complete JD analysis report

{
  "jd_analysis_report": {
    "metadata": {
      "company": "Example Tech",
      "position": "Senior Software Engineer",
      "analysis_date": "2024-01-15T10:00:00Z",
      "jd_language": "en",
      "confidence_score": 0.92
    },

    "basic_info": {
      "title": "Senior Software Engineer",
      "level": "L4-L5",
      "department": "Cloud Infrastructure",
      "location": "Remote / SF",
      "employment_type": "Full-time"
    },

    "culture_analysis": {
      "culture_type": "Innovative & Data-driven",
      "key_traits": ["Fast-paced", "Collaborative", "Customer-obsessed"],
      "work_style": "Hybrid remote",
      "team_size": "5-10 engineers"
    },

    "compensation": {
      "base_salary": "$180k-$220k",
      "equity": "$80k-$120k/year",
      "bonus": "20% target",
      "total_range": "$280k-$360k",
      "market_position": "75th percentile"
    },

    "skills": {
      "required": [
        {"skill": "Python", "weight": 2.0, "proficiency": "advanced"},
        {"skill": "Distributed Systems", "weight": 2.0, "proficiency": "advanced"},
        {"skill": "Kubernetes", "weight": 2.0, "proficiency": "intermediate"}
      ],
      "preferred": [
        {"skill": "Go", "weight": 1.0, "proficiency": "intermediate"},
        {"skill": "ML Engineering", "weight": 1.0, "proficiency": "intermediate"}
      ]
    },

    "skill_match_analysis": {
      "overall_match": 85.5,
      "matched_skills": 7,
      "partial_match": 3,
      "missing_skills": 2,
      "gap_analysis": {
        "critical_gaps": ["Kubernetes depth"],
        "nice_to_have": ["Go proficiency"],
        "recommendations": ["Take Kubernetes course", "Build Go side project"]
      }
    },

    "readiness_assessment": {
      "technical_readiness": 80,
      "experience_match": 85,
      "culture_fit": 90,
      "overall_score": 85,
      "ready_to_apply": true,
      "prep_time_estimate": "2-3 weeks"
    }
  }
}

Analysis quality assurance

Verification checklist items:

All key skills identified
Salary information extracted (if present)
Culture indicators analyzed
Implicit skills inferred
Match score calculated accurately
Suggestions are actionable
Multilingual support is correct
Output format complies with Schema

Confidence score:

高置信度 (90%+): 清晰的技能描述，明确的要求
中置信度 (70-89%): 有一些歧义，需要推断
低置信度 (<70%): JD描述模糊，信息不完整