jev-resume-match
Next.js resume review app where Jev returns typed scores for overall fit, individual criteria and each experience bullet.
Overview
Job Match (repository jev-resume-match) is a simple resume review app. You upload a PDF, DOCX or TXT resume and add the target role and, optionally, a job description. Jev returns an overall score, individual criteria scores, a score for each experience bullet and a suggested bullet order, as typed results rather than generated text.
The server key allows five demo reviews per browser, after which visitors can enter their own TypeSafe key for a request, which is not saved. The app does not store resumes or results but sends extracted text and role context to TypeSafe; scanned PDFs need OCR first. The README is candid that its demo limit (a signed cookie plus an in-memory daily cap) is a small-project safeguard rather than a reliable spending limit, and advises setting provider budgets and a shared rate-limit store before public deployment. Docs explain the pipeline and scoring.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Score | How well does this resume match the role overall? | — |
| Score | How strong is this experience bullet for the role? | — |
How it works
- Upload a resume and enter role and optional job description
- Extract text and send it with criteria to Jev
- Show overall, criteria and bullet scores
- Suggest a bullet order
Strengths
- Typed, explainable scores rather than prose
- No storage of resumes or results
- Demo allowance with bring-your-own-key fallback
Caveats
- Resume text is sent to TypeSafe
- Demo limit is not a robust spending cap
- No OCR for scanned PDFs
Getting started
pnpm install, copy .env.example to .env.local and set TYPESAFE_API_KEY, then pnpm dev.At a glance
- Type
- App
- Status
- prototype
- Language
- TypeScript
- Runtime
- Next.js app
- Has code
- yes
- Has tests
- yes
Use cases and integrations
How curated lists describe it
Score how well a resume matches a job description using Jev (TypeSafe AI). Next.js app that returns typed, explainable match scores instead of generated text.
hellogumbo/awesome-jev
Frequently asked questions
What does Jev score?
Overall match, individual criteria and each experience bullet.
Are resumes stored?
No, but extracted text is sent to TypeSafe for scoring.
Can I use my own key?
Yes, after the five free demo reviews.
Related projects
Resume review app and MCP server where a Cloudflare Worker asks Jev typed questions and composes a JevScore, generally or per job.
AppbetaTypeScriptCV review app where Jev makes traceable document-level judgments on clarity, contribution and results, optionally against a job posting.
ProjectprototypePythonAgent skill where Jev scores a task prompt's clarity, the agent refines it up to three times until it reaches 80/100, then builds.
ProjectbetaJavaScriptClaude Code plugin that logs your prompts locally and later has Jev score how well you prompt the coding agent over time.
PluginbetaTypeScriptChrome extension that grades readable page sections on ten rubric scores with Jev via Vercel AI Gateway and gives the page an A-E grade.
ProjectbetaTypeScriptCLI and agent skill that checks every line of a document against every rule with Jev and outputs flags for an AI agent to fix.
Agent skillbetaTypeScript