CVipher is an AI-powered web app that helps job seekers analyze, score, and improve their resumes for specific job applications. It combines ATS scoring, AI feedback, and a visual dashboard to provide clear, actionable insights into how well a CV matches a job description.
🔐 Authentication – Secure login via Puter.js before accessing features.
📂 Upload CV – Drag & drop PDF upload with instant preview.
🖼️ Resume Conversion – Converts PDFs into images for quick in-app preview.
📊 ATS Scoring – Automated ATS score (0–100) with icons and gradients.
🧠 AI Feedback – Personalized suggestions across:
- Tone & Style
- Content
- Structure
- Skills
📑 Resume Cards – Visual dashboard of all past submissions with score highlights.
📋 Detailed Review Page – Side-by-side PDF/image preview + AI feedback breakdown.
🧹 Data Management – Optional wipe route to clear stored files and feedback.
Frontend: React, React Router, TypeScript
Styling: TailwindCSS
Infra / Services: Puter.js for:
Authentication
File system (resume upload, storage, retrieval)
KV store (saving feedback + resume metadata)
AI API (resume analysis + suggestions)
PDF Processing: pdfjs-dist@5.3.93 (for PDF → image conversion)
/auth → login / logout page
/ → dashboard with uploaded resumes
/upload → upload CV + job description form
/resume/:id → detailed feedback page (ATS score + AI insights)
/wipe → developer utility route to clear app data
- Clone the Repository
git clone https://github.com/AtharvaP555/CVipher-CV_Analyzer.gitcd CVipher-CV_Analyzer
- Install Dependencies
npm install
- Run Dev Server
npm run dev
App will be available at: 👉 http://localhost:5173
npm uninstall pdfjs-dist
npm install pdfjs-dist@5.3.93
Login → Authenticate with Puter.
Upload → Select your CV + enter job details.
Analysis → File uploads, ATS score + AI feedback generated.
Review → View detailed feedback across Tone, Content, Structure, Skills.
Track → All resumes stored in dashboard with preview cards.
-
Multi-resume comparison (side-by-side).
-
Export AI feedback as PDF/Docx.
-
Advanced ATS keyword optimization.
-
UI improvements: dark mode + interactive charts.
-
More models & AI explanation capabilities.
Contributions are welcome! To contribute:
Fork the repo
Create a feature branch (git checkout -b feature/my-feature)
Commit changes (git commit -m "Add new feature")
Push to branch (git push origin feature/my-feature)
Open a Pull Request 🎉
MIT License © 2025 AtharvaP555