Resume–JD match scorer
Score a batch of resumes against one job description with a single fixed ruler: per-requirement verdicts, the resume quote behind each verdict, and a defensible ranking.
About this tool
Screening fifty resumes against one job description takes hours, and the reasons for rejecting a candidate are usually impossible to reconstruct afterwards. This scorer fixes the ruler first: the model extracts the JD into a requirement list once — your must-have weight, minimum years and deal-breakers are folded in locally — and then every resume is judged against that identical list, requirement by requirement.
Each verdict (met, partial, missing) must quote the resume line it rests on, and the ranking score is a weighted sum computed on your device, so the same resume always earns the same score and every rejection can be shown to a hiring manager with its evidence attached. Resumes are parsed in your browser; their text goes only to the provider behind your own key.
How to use Resume–JD match scorer
- Add your provider API key in the key panel.
- Paste the job description (or upload it), set weights, minimum years and any deal-breakers.
- Drop up to 50 resumes (PDF, DOCX or TXT) — they are parsed locally.
- Review the ranking: every verdict quotes the resume line it rests on. Export the table and report.
Keep the original files and inspect the exported result before publishing or sharing it.
Frequently asked questions
How is the score calculated?
The model extracts the JD requirements once. Each resume is judged requirement by requirement (met / partial / missing, with a quoted line as evidence), and the score is a weighted sum computed locally — the same ruler for every candidate.
What are deal-breakers?
Requirements you list as non-negotiable. They are added to the rubric at the highest weight and called out in the report when missing.
Is candidate data uploaded to Localcraft?
No. Files are parsed in your browser; resume text is sent only to the AI provider behind your own key.
How many resumes per run?
Up to 50. Each resume is one model call after the JD is extracted.
Related tools
- AI chat — Chat with OpenAI, Claude or Gemini using your own API key. Your key stays in your browser; requests go straight to the provider.
- AI summarizer — Summarize long text with your own OpenAI, Claude or Gemini API key. Brief, detailed or bullet-point summaries, all in your browser.
- AI translator — Translate text between 30 languages with your own OpenAI, Claude or Gemini API key. Private by design: key and text stay with you and the provider.
- AI writing assistant — Improve, expand, shorten or re-tone your writing with your own API key. Six editing modes, direct browser-to-provider calls.
- AI code explainer — Paste code and get a plain-English explanation using your own OpenAI, Claude or Gemini API key. Language auto-detect included.
- AI PDF chat — Upload a PDF and ask questions about it. The PDF is parsed in your browser; only the extracted text and your question go to your chosen AI provider.
- AI image analyzer — Upload an image and let AI describe it, extract text (OCR), or identify objects. Uses vision models from OpenAI, Claude or Gemini with your own key.
- AI voice generator — Turn text into natural-sounding speech with OpenAI TTS. Six voices, speed control, play in the browser and download MP3.
- AI data analyst — Upload a CSV and ask questions in plain English. The file is parsed locally; the AI sees only a schema summary and sample rows.
- AI spend analyzer — Turn your AI provider usage export into an independent cost receipt: per-model and per-day breakdowns, spike alerts and a monthly projection. Runs 100% in your browser — your billing data is never uploaded.