{"id":29445436,"url":"https://github.com/arh-mnajs/tech-track-decoded","last_synced_at":"2026-04-16T05:32:48.659Z","repository":{"id":304237861,"uuid":"1018204101","full_name":"ARH-MNAJS/Tech-Track-Decoded","owner":"ARH-MNAJS","description":"This repository features two hands-on, real-world AI-driven applications built using Python","archived":false,"fork":false,"pushed_at":"2025-07-11T19:58:27.000Z","size":39,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"dev","last_synced_at":"2025-07-11T21:29:24.483Z","etag":null,"topics":["flask","llm","ollama","python","streamlit"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ARH-MNAJS.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-07-11T19:42:52.000Z","updated_at":"2025-07-11T19:59:50.000Z","dependencies_parsed_at":"2025-07-11T21:39:30.347Z","dependency_job_id":null,"html_url":"https://github.com/ARH-MNAJS/Tech-Track-Decoded","commit_stats":null,"previous_names":["arh-mnajs/tech-track-decoded"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/ARH-MNAJS/Tech-Track-Decoded","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ARH-MNAJS%2FTech-Track-Decoded","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ARH-MNAJS%2FTech-Track-Decoded/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ARH-MNAJS%2FTech-Track-Decoded/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ARH-MNAJS%2FTech-Track-Decoded/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ARH-MNAJS","download_url":"https://codeload.github.com/ARH-MNAJS/Tech-Track-Decoded/tar.gz/refs/heads/dev","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ARH-MNAJS%2FTech-Track-Decoded/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31872621,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-15T15:24:51.572Z","status":"online","status_checked_at":"2026-04-16T02:00:06.042Z","response_time":69,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["flask","llm","ollama","python","streamlit"],"created_at":"2025-07-13T17:12:02.681Z","updated_at":"2026-04-16T05:32:48.641Z","avatar_url":"https://github.com/ARH-MNAJS.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/8eef13b2-b8e6-4584-8078-3bff3ddd1c59.jpg\" alt=\"SkillScore.AI \u0026 LinkScope.AI Banner\" width=\"100%\" /\u003e\n\u003c/p\u003e\n\u003ch1 align=\"center\" style=\"color:#0B5394;\"\u003eTech Track Decoded | AI-ML Track\u003c/h1\u003e\n\u003cp align=\"center\"\u003e\n  \u003ci\u003eThis repository features two hands-on, real-world AI-driven applications built using Python\u003c/i\u003e\n\u003c/p\u003e\n\n## 📦 Project 1: SkillScore.AI (Built with Streamlit)\n\n### 🎯 Goal\nA smart and simple **skill assessment and roadmap generator** designed for students to self-evaluate their technical competencies and get a personalized learning roadmap — all within the Python ecosystem using Streamlit.\n\n### 🧰 Features\n- Interactive form for entering known skills and confidence levels\n- Smart scoring system to evaluate readiness for career paths like Web Dev, Data Science, DevOps, etc.\n- Dynamic roadmap and suggestions based on inputs\n- Visualization of skill scores using radar charts\n- Fully deployable via Streamlit Cloud\n\n### 🧠 Key Technologies\n- Streamlit – Python web framework for building interactive apps quickly\n- Plotly – For generating dynamic visualizations like radar charts\n- Pandas – Used to process user inputs and apply scoring logic on skillsets\n- Custom Python Logic – For evaluating skill depth and generating roadmaps\n- Streamlit Cloud – For quick deployment and sharing of the app with users\n\n### 💡 Learning Outcomes\n- Introduction to Streamlit UI elements (forms, sliders, buttons)\n- Logic building for recommendations\n- Visualizations with Python libraries like Plotly\n- PDF export capability\n- End-to-end deployment and hosting\n\n---\n\n## 📦 Project 2: LinkScope.AI (Built with Flask + Ollama)\n\n### 🎯 Goal\nA **LinkedIn Profile Analyzer** powered by a locally hosted LLM (via [Ollama](https://ollama.com/)). The app allows users to upload their exported LinkedIn profile PDF and receive an AI-generated feedback report, including strengths, weaknesses, and suggestions to enhance their public professional presence.\n\n### 🧰 Features\n- Upload and parse LinkedIn profile PDFs (exported directly from LinkedIn)\n- Extract relevant sections: Summary, Experience, Skills, Education\n- Send parsed data to a local LLM via Ollama’s API\n- Get smart analysis in clean markdown (converted to HTML)\n- Display:\n  - Profile Strengths\n  - Weaknesses\n  - Suggested Summary Rewrite\n  - Top 3-5 Career Enhancement Tips\n- Downloadable PDF improvement report\n- Fully local setup — no external LLM APIs required\n\n### 🧠 Key Technologies\n- Flask – Python web framework for routing, templating, and handling file uploads\n- PyMuPDF or pdfminer.six – For extracting clean text from exported LinkedIn PDF files\n- Ollama LLM – Runs local open-source language models like LLaMA 3, Mistral, DeepSeek, or Gemma for analysis\n- Markdown Rendering – To convert AI-generated markdown into styled HTML within the app\n- PDFKit or ReportLab – To generate downloadable improvement reports in PDF format\n\n### 💡 Learning Outcomes\n- Flask project structure and route handling\n- File upload handling and PDF parsing\n- Local LLM integration using HTTP APIs\n- Templating with Jinja2\n- Markdown-to-HTML conversion\n- PDF export from dynamic content\n- Deployment on local or cloud infrastructure\n\n---\n\n## ✨ Bonus Highlights\n\n| Feature | SkillScore.AI (Streamlit) | LinkScope.AI (Flask + Ollama) |\n|--------|----------------------------|-------------------------------|\n| Stack | Streamlit, Plotly, Python | Flask, Ollama, PyMuPDF |\n| Input | Manual (skills, confidence) | PDF upload (LinkedIn export) |\n| Output | Roadmap, skill graph, PDF | AI-generated feedback, PDF report |\n| Deployment | Streamlit Cloud | Localhost / HuggingFace Spaces |\n| LLM Use | ❌ None | ✅ Ollama (local LLM) |\n| Offline Friendly | ✅ Fully | ✅ Fully (runs on local LLM) |\n\n---\n\n## 📬 Contact\n\nFeel free to reach out or connect on [LinkedIn](https://linkedin.com/in/arhmnajs) if you'd like feedback, collaboration, or mentorship in building AI-powered tools using Python.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farh-mnajs%2Ftech-track-decoded","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Farh-mnajs%2Ftech-track-decoded","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Farh-mnajs%2Ftech-track-decoded/lists"}