Can CVMatchScore be vibe coded?
Scores your resume against a job description across 19 parameters before you hit apply
The core loop, resume plus job posting into an LLM holding a scoring rubric, is one prompt and an afternoon, and for improving one resume against one posting it genuinely works. The honest gap is calibration: a rubric you wrote today measures today's mood, two runs of the same resume can disagree, and a 72 means nothing without a baseline of scored applications behind it. Fine as a mirror, thin as a measuring stick.
Jump to the build brief ↓Legacy-calibrated assessment
Checked Aug 2026
What you pay today, before any DIY hosting
medium editorial confidence
Tracked separately from the pricing check
Buildability by layer
Screens, forms, and focused interactions
The repeatable job the product performs
Availability and legality of required data
Uptime, queues, support, and maintenance
Security, compliance, and user confidence
The achievable core
- Extract text from the resume PDF, send it with the job description to an LLM holding a fixed scoring rubric, get structured JSON scores per criterion with quoted evidence, render a Markdown report.
- Tailor resumes, track applications, and rehearse answers from your own history.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- a calibrated rubric that scores the same resume the same way twice
- 50+ language support tested per parameter
- DOC, DOCX, and RTF parsing beyond PDF
- improvement plans and tailored cover letters built from the same analysis
- The last 20 percent is sync, migration fidelity, speed, and edge cases.
- The useful dataset is owned, accumulated, or expensive to reproduce.
Build, switch, or keep paying
Narrower, with trade-offs
Extract text from the resume PDF, send it with the job description to an LLM holding a fixed scoring rubric, get structured JSON scores per criterion with quoted evidence, render a Markdown report.
Use the build brief ↓1 checked option
- Resume-Matcher ↗A local resume-vs-posting matcher that runs against Ollama, so the scoring stays on your machine; you install it, it does the job, and nobody bills you.
$4.08/mo
At 49 USD a year it is priced below the hassle of maintaining your own: job seekers pay for stable scores they can track across applications, cover letters generated from the same pass, and not burning API credits mid job hunt.
Visit CVMatchScore ↗Why people still pay
At 49 USD a year it is priced below the hassle of maintaining your own: job seekers pay for stable scores they can track across applications, cover letters generated from the same pass, and not burning API credits mid job hunt.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
The useful dataset is owned, accumulated, or expensive to reproduce.
The brief
Context, requirements, acceptance criteria, non-goals, and the full production standard — as Markdown, ready for any coding agent.
Build brief — a focused alternative to CVMatchScore
Context
CVMatchScore — Scores your resume against a job description across 19 parameters before you hit apply. It currently costs $4.08/mo.
The core loop, resume plus job posting into an LLM holding a scoring rubric, is one prompt and an afternoon, and for improving one resume against one posting it genuinely works. The honest gap is calibration: a rubric you wrote today measures today's mood, two runs of the same resume can disagree, and a 72 means nothing without a baseline of scored applications behind it. Fine as a mirror, thin as a measuring stick.
This brief describes a focused, single-operator replacement for the part of CVMatchScore that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.
What you are building
Extract text from the resume PDF, send it with the job description to an LLM holding a fixed scoring rubric, get structured JSON scores per criterion with quoted evidence, render a Markdown report.
Tailor resumes, track applications, and rehearse answers from your own history.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
Pdf-parse or pdfplumber for resume text extraction.
A written rubric with a 0-10 definition per criterion.
A few real resume and posting pairs to sanity-check the scores.
Data and integrations
OpenAI or Anthropic API key.
Each of these needs a real account, credential, or quota. Set them up before writing feature code.
Non-functional
Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
Security: server-side secrets, validated input, and no credentials in the client bundle.
Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
Portability: the operator can export their data and leave without losing it.
Implementation brief
Build me a local resume match scorer to replace CVMatchScore. Requirements:
A Node 22 CLI: match score resume.pdf job.txt prints a score table and writes
a Markdown report to reports/YYYY-MM-DD-<company>.md.
Extract resume text with pdf-parse; accept .txt and .md for the job posting.
Keep the rubric in rubric.json: 10 criteria (skills overlap, seniority fit,
domain experience, quantified achievements, education, keyword coverage,
employment gaps, clarity, length, ATS-safety), each with a 0-10 definition
and a weight.
One Anthropic structured-outputs call scores all criteria at once and must
quote the resume line that justifies each score, no unquoted claims.
A second cheap pass lists the 10 most important posting keywords missing from
the resume and where each could honestly fit.
Weighted total out of 100, computed in code from rubric.json, not by the model.
Store every run in SQLite via better-sqlite3: date, company, total, and the
per-criterion JSON, so match history shows my scores over time.
API key from .env. No accounts, no telemetry, the resume never leaves my
machine except the API call.
Out of scope: cover letter generation, DOC/DOCX parsing, multi-language
support, and recruiter-style bulk ranking.
README: setup, cost per run, and a warning that scores are only comparable
within one rubric version, so bump a version field in rubric.json when I edit it.
Delivery standard
Inspect the repository first, then write a short implementation plan before writing code.
Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
Add structured logs around every external call and return actionable errors without leaking sensitive details.
Write unit tests for the core logic and one automated test of the main user journey.
Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.
Acceptance criteria
A clean install starts the app using only the README and .env.example.
The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
Tests, type checking, linting, and a production build all pass with no ignored failures.
No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.
Non-goals
Do not build these, and do not claim to have replaced them:
A calibrated rubric that scores the same resume the same way twice.
50+ language support tested per parameter.
DOC, DOCX, and RTF parsing beyond PDF.
Improvement plans and tailored cover letters built from the same analysis.
Scores comparable across weeks of applications.
What you still own after launch
Secure credentials, rotate secrets, and handle provider rate limits.
Run migrations, backups, restores, and dependency updates.
Test the critical journey after every model, API, or hosting change.
Monitor failures and fix the edge cases a first prompt will miss.
Risk
Operational risk. The code is achievable; dependable data, integrations, and ongoing operations are the real cost.
Editorial confidence in this assessment: medium. No reviewed project implementation is linked yet.
Existing alternatives
Before building, compare these checked options:
Resume-Matcher — A local resume-vs-posting matcher that runs against Ollama, so the scoring stays on your machine; you install it, it does the job, and nobody bills you
Prior art
Working open-source software you can read, fork, or borrow from before starting:
pdfplumber — reliable PDF text extraction, the unglamorous half of every resume tool
Resume-Matcher (repo) — open-source resume vs job description matcher, a working reference for the whole loop
Generated by Can It Be Vibe Coded? · Full report: https://www.canitbevibecoded.com/cvmatchscore
You still own the product
- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
Projects built from this idea
No reviewed implementation has been linked for CVMatchScore yet. A submission is evidence for review, not automatic proof that the whole product was replaced.
Built a version of CVMatchScore?Submit the project as evidence for this report.
Open-source prior art
Before you start
Can CVMatchScore be vibe coded?
Partly, if you narrow it. The core loop, resume plus job posting into an LLM holding a scoring rubric, is one prompt and an afternoon, and for improving one resume against one posting it genuinely works. The honest gap is calibration: a rubric you wrote today measures today's mood, two runs of the same resume can disagree, and a 72 means nothing without a baseline of scored applications behind it. Fine as a mirror, thin as a measuring stick.
What can an AI coding agent reproduce from CVMatchScore?
Extract text from the resume PDF, send it with the job description to an LLM holding a fixed scoring rubric, get structured JSON scores per criterion with quoted evidence, render a Markdown report. Tailor resumes, track applications, and rehearse answers from your own history. A responsive interface with real empty, loading, success, and error states.
What will a DIY CVMatchScore replacement still be missing?
a calibrated rubric that scores the same resume the same way twice; 50+ language support tested per parameter; DOC, DOCX, and RTF parsing beyond PDF; improvement plans and tailored cover letters built from the same analysis; The last 20 percent is sync, migration fidelity, speed, and edge cases.; The useful dataset is owned, accumulated, or expensive to reproduce.
What do I still own after building a CVMatchScore alternative?
Secure credentials, rotate secrets, and handle provider rate limits. Run migrations, backups, restores, and dependency updates. Test the critical journey after every model, API, or hosting change. Monitor failures and fix the edge cases a first prompt will miss.