# Job Skill Enhancement System

## CORE INSTRUCTION:
You are an AI that extracts and identifies coding languages and frameworks from job descriptions. Your goal is to find ALL relevant technical skills mentioned in the job posting, even if they're mentioned in different ways or aliases.

## INPUT DATA:
{
  "job": {"job_id":3657,"title":"Full Stack Developer \/ Data Scientist - Product Development","company_name":"Pyne - AI made useful","description":"Are you excited about building data-driven products that solve real business problems? We're looking for a technical contributor to help transform our consultancy insights into scalable solutions.\n\n\n\n\nWho is Pyne\n\nPyne has helped >40 customers build robust data foundations, enabling partners to scale their businesses through data and AI. As AI reshapes industries, we help organizations embed intelligent workflows where they create the most value.\n\nWe operate at the intersection of data engineering, analytics, and AI - reimagining processes end-to-end to help organizations scale sustainably while amplifying human insight where it matters most.\n\n\n\n\nWhy this role exists\n\nWe're evolving from pure consultancy toward product development. The problems we solve repeatedly for clients present opportunities to build reusable, scalable solutions. We need someone to help identify these patterns and turn them into products.\n\n\n\n\nWhat you'll do\n\nProduct Development (~60%):\n\nBuild and iterate on data products, AI solutions, and analytical tools\nDevelop both backend services and frontend interfaces for our emerging product suite\nContribute to architecture decisions and technical roadmap planning\n\nData & AI Implementation (~30%):\n\nWork on client AI projects while identifying productization opportunities\nBuild data pipelines, analytical models, and intelligent automation systems\nExperiment with and implement agentic AI systems\n\nCollaboration (~10%):\n\nWork closely with consultants to understand recurring client needs\nParticipate in technical discussions and solution design\nContribute to knowledge sharing across the team\n\n\n\n\nRequirements\n\nMust-haves:\n\nFull-Stack Development: Experience building web applications with modern frameworks (React, Node.js, Python\/FastAPI, etc.)\nData & Analytics: Hands-on experience with data processing, analysis, and visualization tools\nAI\/ML Experience: Practical experience implementing machine learning models or AI solutions\nCloud & Production: Experience deploying and maintaining applications in production (Azure, GCP, or AWS)\n\n\n\n\nNice to have:\n\nExperience with data engineering tools and pipelines\nKnowledge of modern data stack (dbt, Airflow, etc.)\nAPI design and development experience\nDevOps and infrastructure automation\nExperience with agentic AI systems or LLM applications\n\n\n\n\nWhat we offer\n\nOpportunity to shape product direction from the ground up\nCompetitive compensation\nModern workspace in SOHO Kødbyen with good coffee, lunch, and team activities\nCollaborative environment with data engineers, developers, and consultants focused on meaningful outcomes\nDirect access to real client problems and the chance to solve them at scale\n\n\n\n\nHow to apply\n\nSend your CV or LinkedIn profile along with a brief note about what interests you about this role.\n\nEmail Rafael and Michael (founders): rafael@pyne.dk and michael@pyne.dk.","brief_summary_of_job":null,"existing_skills_from_job":["Python","FastAPI","Node.js","React","AWS","Azure","GCP"],"existing_skills_from_database":[]},
  "coding_categories": {"languages":["Bash","C","C#","C++","CSS","Clojure","Dart","Elixir","Go","Groovy","Haskell","HTML","Java","JavaScript","Julia","Kotlin","Lua","MATLAB","Objective-C","Perl","PHP","PowerShell","Python","R","Ruby","Rust","Sass","Scala","Swift","TypeScript"],"frameworks":[".NET","Angular","Apache Spark","ASP.NET","Backbone.js","Bootstrap","CodeIgniter","Django","Ember.js","Express","FastAPI","Flask","Flutter","Hadoop","Ionic","jQuery","Laravel","Livewire","Meteor","NestJS","Next.js","Node.js","Nuxt.js","Phoenix","PHPUnit","PyTorch","React","React Native","Ruby on Rails","Spring Boot","Svelte","Symfony","Tailwind CSS","TensorFlow","Vue.js","Xamarin","Alpine.js","Filament","WordPress"],"databases":["MySQL","PostgreSQL","Redis","MongoDB","DynamoDB","MariaDB","NoSQL","Oracle","BigQuery","Elasticsearch","SQL","SQL Server","SQLite","Cassandra","CouchDB","Neo4j","InfluxDB","CockroachDB"],"tools":["Git","GitHub","GitLab","Bitbucket","Docker","Kubernetes","CI\/CD","Jenkins","Kafka","RabbitMQ","Amazon SQS","AMQP","PubSub","REST API","RESTful APIs","GraphQL","AWS","Azure","GCP","Terraform","Ansible","Puppet","Chef","Vagrant","Vault","Consul","Prometheus","Grafana","ELK Stack","Splunk"],"skills":["English","Danish","Communication","Full-stack development","Back-end development","Front-end development","Cloud computing","DevOps","Microsoft Excel","PowerBI","Power Platform","Agile","Scrum","Problem-solving","Team collaboration","Physical presence","Remote work","Hybrid work"],"colors":{"languages":"blue","frameworks":"purple","databases":"orange","tools":"indigo"}},
  "skill_aliases": {"bash":"Bash","c":"C","c plus plus":"C++","C plus plus":"C++","c sharp":"C#","C sharp":"C#","c#":"C#","c++":"C++","clojure":"Clojure","cpp":"C++","dart":"Dart","elixir":"Elixir","go":"Go","golang":"Go","Golang":"Go","groovy":"Groovy","haskell":"Haskell","java":"Java","java script":"JavaScript","Java script":"JavaScript","javascript":"JavaScript","Javascript":"JavaScript","js":"JavaScript","JS":"JavaScript","es5":"JavaScript","ES5":"JavaScript","es6":"JavaScript","ES6":"JavaScript","julia":"Julia","kotlin":"Kotlin","lua":"Lua","matlab":"MATLAB","Matlab":"MATLAB","objective c":"Objective-C","Objective C":"Objective-C","objective-c":"Objective-C","objc":"Objective-C","ObjC":"Objective-C","obj-c":"Objective-C","Obj-C":"Objective-C","perl":"Perl","php":"PHP","Php":"PHP","powershell":"PowerShell","Power Shell":"PowerShell","python":"Python","py":"Python","Py":"Python","phyton":"Python","r":"R","ruby":"Ruby","rust":"Rust","scala":"Scala","swift":"Swift","typescript":"TypeScript","Typescript":"TypeScript","ts":"TypeScript","TS":"TypeScript","mysql":"MySQL","postgresql":"PostgreSQL","postgres":"PostgreSQL","mongodb":"MongoDB","mongo":"MongoDB","redis":"Redis","sqlite":"SQLite","oracle":"Oracle","mssql":"SQL Server","sql server":"SQL Server","dynamodb":"DynamoDB","dynamo db":"DynamoDB","mariadb":"MariaDB","maria db":"MariaDB","nosql":"NoSQL","no sql":"NoSQL","bigquery":"BigQuery","big query":"BigQuery","elasticsearch":"Elasticsearch","elastic search":"Elasticsearch","cassandra":"Cassandra","couchdb":"CouchDB","couch db":"CouchDB","neo4j":"Neo4j","neo 4j":"Neo4j","influxdb":"InfluxDB","influx db":"InfluxDB","cockroachdb":"CockroachDB","cockroach db":"CockroachDB","aws":"AWS","amazon web services":"AWS","azure":"Azure","microsoft azure":"Azure","gcp":"GCP","google cloud platform":"GCP","google cloud":"GCP",".Net":".NET","angular":"Angular","angular js":"Angular","Angular js":"Angular","angularjs":"Angular","AngularJS":"Angular","apache spark":"Apache Spark","asp net":".NET","ASP net":".NET","asp.net":"ASP.NET","ASP.NET":".NET","asp.net core":".NET","ASP.NET Core":".NET","backbone":"Backbone.js","BackboneJS":"Backbone.js","backbone js":"Backbone.js","backbonejs":"Backbone.js","bootstrap":"Bootstrap","Bootstrap framework":"Bootstrap","twitter bootstrap":"Bootstrap","Twitter Bootstrap":"Bootstrap","code igniter":"CodeIgniter","codeigniter":"CodeIgniter","django":"Django","ember":"Ember.js","ember js":"Ember.js","emberjs":"Ember.js","EmberJS":"Ember.js","express":"Express","express.js":"Express","Express.js":"Express","expressjs":"Express","ExpressJS":"Express","fast api":"FastAPI","Fast api":"FastAPI","fastapi":"FastAPI","flask":"Flask","flutter":"Flutter","hadoop":"Hadoop","Hadoop":"Hadoop","ionic":"Ionic","Ionic framework":"Ionic","ionic framework":"Ionic","jquery":"jQuery","JQuery":"jQuery","JQUERY":"jQuery","laravel":"Laravel","meteor":"Meteor","meteor js":"Meteor","meteorjs":"Meteor","MeteorJS":"Meteor","nestjs":"NestJS","nest js":"NestJS","Nest JS":"NestJS","Nestjs":"NestJS","next js":"Next.js","Next js":"Next.js","next.js":"Next.js","nextjs":"Next.js","NextJS":"Next.js","node":"Node.js","Node":"Node.js","node.js":"Node.js","nodejs":"Node.js","NodeJS":"Node.js","nuxt js":"Nuxt.js","Nuxt js":"Nuxt.js","nuxt.js":"Nuxt.js","nuxtjs":"Nuxt.js","NuxtJS":"Nuxt.js","phoenix":"Phoenix","Phoenix framework":"Phoenix","pytorch":"PyTorch","Pytorch":"PyTorch","torch":"PyTorch","Torch":"PyTorch","react":"React","react.js":"React","React.js":"React","reactjs":"React","ReactJS":"React","react native":"React Native","ReactNative":"React Native","reactnative":"React Native","rn":"React Native","RN":"React Native","rails":"Ruby on Rails","Rails":"Ruby on Rails","ror":"Ruby on Rails","ROR":"Ruby on Rails","ruby on rails":"Ruby on Rails","Ruby On Rails":"Ruby on Rails","spark":"Apache Spark","Spark":"Apache Spark","spring":"Spring Boot","Spring":"Spring Boot","spring boot":"Spring Boot","Spring Boot":"Spring Boot","spring framework":"Spring Boot","Spring Framework":"Spring Boot","SpringBoot":"Spring Boot","springboot":"Spring Boot","svelte":"Svelte","symfony":"Symfony","tailwind":"Tailwind CSS","Tailwind":"Tailwind CSS","tailwind css":"Tailwind CSS","Tailwind Css":"Tailwind CSS","tailwindcss":"Tailwind CSS","TailwindCSS":"Tailwind CSS","tensorflow":"TensorFlow","Tensorflow":"TensorFlow","tensor flow":"TensorFlow","Vue":"Vue.js","vue":"Vue.js","vue js":"Vue.js","vue.js":"Vue.js","vuejs":"Vue.js","VueJS":"Vue.js","xamarin":"Xamarin","Xamarin Forms":"Xamarin","Xamarin.forms":"Xamarin","livewire":"Livewire","phpunit":"PHPUnit","alpine":"Alpine.js","alpine js":"Alpine.js","alpinejs":"Alpine.js","filament":"Filament","docker":"Docker","kubernetes":"Kubernetes","k8s":"Kubernetes","github":"GitHub","gitlab":"GitLab","bitbucket":"Bitbucket","terraform":"Terraform","puppet":"Puppet","chef":"Chef","git":"Git","jenkins":"Jenkins","kafka":"Kafka","rabbitmq":"RabbitMQ","amazon sqs":"Amazon SQS","amqp":"AMQP","pubsub":"PubSub","rest api":"REST API","restful api":"RESTful APIs","restful apis":"RESTful APIs","graphql":"GraphQL","ansible":"Ansible","vagrant":"Vagrant","vault":"Vault","consul":"Consul","prometheus":"Prometheus","grafana":"Grafana","elk stack":"ELK Stack","splunk":"Splunk","scrum":"Scrum","agile":"Agile","kanban":"Kanban","devops":"DevOps","ci\/cd":"CI\/CD","tdd":"TDD","bdd":"BDD","linux":"Linux","windows":"Windows","macos":"macOS","ubuntu":"Ubuntu","centos":"CentOS","debian":"Debian","junit":"JUnit","pytest":"PyTest","jest":"Jest","mocha":"Mocha","cypress":"Cypress","selenium":"Selenium","html":"HTML","HTML":"HTML","html5":"HTML","HTML5":"HTML","css":"CSS","CSS":"CSS","css3":"CSS","CSS3":"CSS","sass":"Sass","scss":"Sass","SCSS":"Sass","less":"Less","LESS":"Less","webpack":"Webpack","gulp":"Gulp","npm":"npm","yarn":"Yarn","sql":"SQL","full time":"Fuldtid","full-time":"Fuldtid","fuldtid":"Fuldtid","part time":"Deltid","part-time":"Deltid","deltid":"Deltid","contract":"Kontrakt","kontrakt":"Kontrakt","remote":"Fjernarbejde","fjernarbejde":"Fjernarbejde","hybrid":"Hybridarbejde","hybridarbejde":"Hybridarbejde","on-site":"Fysisk tilstedeværelse","onsite":"Fysisk tilstedeværelse","fysisk tilstedeværelse":"Fysisk tilstedeværelse"}
}

## TASK:
1. **Extract ALL coding languages and frameworks** mentioned in the job description
2. **Use the skill_aliases mapping** to normalize skill names (e.g., "JS" → "JavaScript", "React.js" → "React")
3. **Only include skills from the coding_categories** (languages and frameworks)
4. **Avoid duplicates** - if "JavaScript" and "JS" are both mentioned, only include "JavaScript"
5. **Be thorough** - look for skills mentioned in:
   - Job title
   - Job description
   - Brief summary
   - Requirements sections
   - Nice-to-have sections

## SKILL CATEGORIES TO EXTRACT:
- **Languages**: Programming languages (PHP, Python, JavaScript, Java, C#, Go, Rust, etc.)
- **Frameworks**: Web frameworks and libraries (Laravel, React, Vue.js, Angular, Django, Spring Boot, etc.)
- **Databases**: Database systems and data stores (MySQL, PostgreSQL, Redis, MongoDB, DynamoDB, etc.)
- **Tools**: Development tools and infrastructure (Git, Docker, AWS, CI/CD, Jenkins, Kafka, etc.)

## EXCLUSION RULES:
- Do NOT extract general skills (communication, languages like English, etc.)
- Do NOT extract business skills (Excel, PowerBI for non-technical roles)
- Do NOT extract work arrangements (remote, physical presence)
- Do NOT include methodologies (Agile, Scrum, etc.) unless specifically technical
- Do NOT include skills already in existing_skills_from_database

## OUTPUT FORMAT:
Return ONLY valid JSON in this exact structure:
{
  "job_id": <integer>,
  "extracted_skills": [
    {
      "skill_name": "<normalized_skill_name>",
      "category": "<languages|frameworks|databases|tools>",
      "confidence": <integer 0-100>,
      "mentioned_as": ["<original_mention_1>", "<original_mention_2>"],
      "context": "<brief_context_where_found>"
    }
  ],
  "reasoning": {
    "total_skills_found": <integer>,
    "skills_by_category": {
      "languages": ["<skill1>", "<skill2>"],
      "frameworks": ["<skill1>", "<skill2>"],
      "databases": ["<skill1>", "<skill2>"],
      "tools": ["<skill1>", "<skill2>"]
    },
    "duplicates_removed": ["<original_mention> → <normalized_name>"],
    "excluded_skills": ["<skill>", "<reason>"]
  },
  "confidence": <integer 0-100>
}

Return nothing outside the JSON object.

{
  "job_id": 3657,
  "extracted_skills": [
    {
      "skill_name": "Python",
      "category": "languages",
      "confidence": 100,
      "mentioned_as": ["Python"],
      "context": "Must-haves: Full-Stack Development: Experience building web applications with modern frameworks (React, Node.js, Python/FastAPI, etc.)"
    },
    {
      "skill_name": "FastAPI",
      "category": "frameworks",
      "confidence": 100,
      "mentioned_as": ["FastAPI"],
      "context": "Must-haves: Full-Stack Development: Experience building web applications with modern frameworks (React, Node.js, Python/FastAPI, etc.)"
    },
    {
      "skill_name": "Node.js",
      "category": "frameworks",
      "confidence": 100,
      "mentioned_as": ["Node.js"],
      "context": "Must-haves: Full-Stack Development: Experience building web applications with modern frameworks (React, Node.js, Python/FastAPI, etc.)"
    },
    {
      "skill_name": "React",
      "category": "frameworks",
      "confidence": 100,
      "mentioned_as": ["React"],
      "context": "Must-haves: Full-Stack Development: Experience building web applications with modern frameworks (React, Node.js, Python/FastAPI, etc.)"
    },
    {
      "skill_name": "AWS",
      "category": "tools",
      "confidence": 100,
      "mentioned_as": ["AWS"],
      "context": "Must-haves: Cloud & Production: Experience deploying and maintaining applications in production (Azure, GCP, or AWS)"
    },
    {
      "skill_name": "Azure",
      "category": "tools",
      "confidence": 100,
      "mentioned_as": ["Azure"],
      "context": "Must-haves: Cloud & Production: Experience deploying and maintaining applications in production (Azure, GCP, or AWS)"
    },
    {
      "skill_name": "GCP",
      "category": "tools",
      "confidence": 100,
      "mentioned_as": ["GCP"],
      "context": "Must-haves: Cloud & Production: Experience deploying and maintaining applications in production (Azure, GCP, or AWS)"
    }
  ],
  "reasoning": {
    "total_skills_found": 6,
    "skills_by_category": {
      "languages": ["Python"],
      "frameworks": ["FastAPI", "Node.js", "React"],
      "databases": [],
      "tools": ["AWS", "Azure", "GCP"]
    },
    "duplicates_removed": [],
    "excluded_skills": []
  },
  "confidence": 100
}