惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

Y
Y Combinator Blog
B
Blog
S
SegmentFault 最新的问题
Vercel News
Vercel News
博客园 - 聂微东
宝玉的分享
宝玉的分享
C
Check Point Blog
有赞技术团队
有赞技术团队
IT之家
IT之家
V
V2EX
爱范儿
爱范儿
GbyAI
GbyAI
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Microsoft Azure Blog
Microsoft Azure Blog
P
Proofpoint News Feed
博客园 - 司徒正美
博客园_首页
Last Week in AI
Last Week in AI
博客园 - 叶小钗
量子位
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
F
Fortinet All Blogs
腾讯CDC
J
Java Code Geeks

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
I was tired of copy-pasting between job tracker and CV to...
Sylumk · 2026-04-28 · via DEV Community

Sylumk

Last year when I was applying for jobs, my setup was a mess.

I had 10 tabs open, a spreadsheet to track applications, and multiple versions of my CV. Every time I wanted to tailor my CV for a role, I had to copy paste the job description somewhere, paste my CV somewhere else, and manually compare the two.

It worked, but it was slow and annoying. So I built a small tool to fix that.

The idea

I wanted one place where I could both track applications and tailor my CV without jumping between tabs.

The flow is simple.

  • You open a job in your tracker. You click “Tailor my CV for this role”. A new tab opens with your CV and the job description already there.

  • From there, you get suggestions. Keywords to add, bullet points to rewrite, things to remove. You pick what you want.

  • When you're done, the result syncs back to the original tab. You can close everything and come back later without doing the work again.

That’s it. No copy paste loop.

The tracker

The tracker is just a small column based board with four columns: Draft, Applied, Interview, Offer.

Each card has the company name, role, job description, and your notes. Enough to stop using a spreadsheet, nothing more.

I did not add drag and drop. A simple “Move to” dropdown does the job and took an hour instead of a day. That tradeoff felt right.

How the sync works

The interesting part is how the two tabs talk to each other.

When the CV tab finishes generating suggestions or when you apply changes, it writes the result to localStorage.

The tracker listens to the localStorage storage event. When it fires, the card updates automatically. No refresh, no manual reload.

It is a small thing, but it removes a lot of friction. You do the work in one tab and see the result in another instantly.

How the CV analysis works

There are two modes.

  • The first one is keyword matching. It runs instantly and highlights missing or weak matches between your CV and the job description.

  • The second one uses an AI model through your own Gemini API key. It gives more detailed suggestions like rewriting bullet points or spotting gaps.

In both cases, the output is not a full rewrite. I tried that first and dropped it. It felt like a black box and I did not trust it.

Now it gives small, specific suggestions. You pick what to apply.

PDF support

You can upload your CV as a PDF. The text is extracted directly in the browser and used for the analysis.

What I chose not to build

A few things I skipped on purpose.

  • A full CV rewrite, as mentioned.

  • Drag and drop on the board. Nice to have, not worth the time for a first version.

  • Anything that adds friction or setup. The goal was to make this faster than my old copy paste workflow, not more complex.

What’s next

Right now, adding a job to the tracker is still manual. You copy the job description and paste it into a card.

The next step is a browser extension.

The idea is to open a job page and click a button to send everything to the tracker. Title, company, description. No copy paste at all.

That would complete the loop.

If you want to try it

The tracker and the CV tools are available at https://sylumk.dev

If you are not job hunting, you probably know someone who is. Feel free to share it with them.

If you have feedback, I would love to hear it !