What it does
The Resume app extracts structured information from a resume (PDF or DOC), optionally compares it with a job description, and produces a scored gap analysis with rewrite suggestions. It can also improve a resume to match a target role.
Inputs and limits
- Input file: a single resume file in PDF or DOC format placed in the task’s input folder (CLI) or uploaded on the web page.
- Optional job description: a URL (
--job-description-url) or inline text (--job-description-text) that the resume is compared against. - Supported sizes: limited by the host’s memory and the .NET runtime; typical PDFs up to several megabytes work without issue.
- Output: a text report (
resume_extract_report.txt) and a JSON hand‑off file; the web page also offers a downloadable PDF report.
Web app
The web page at /ai-prod/resume-extractor asks the user to upload a resume (PDF or DOC) and, optionally, a job description, job title, or target industry. After submission the AI extracts sections such as experience, education, technical skills, certifications, licenses, physical requirements and safety training, then compares them with the provided job context. The result is a numeric match score, a gap analysis, a red‑flag list, and concrete rewrite examples, available as a downloadable PDF report.
Command line (CLI)
The Documentize Resume CLI plugin extracts or tailors resume content using an LLM. It reads the resume PDF/DOC from a task‑specific input folder and writes the analysis report to the corresponding output folder.
Typical usage on Windows PowerShell: Set the environment variables for input and output folders, create a sub‑folder for the task, copy the resume file into that folder, then run the plugin:
$env:PLUGIN_INPUT_DIR = "C:\resume-work\input" $env:PLUGIN_OUTPUT_DIR = "C:\resume-work\output" New-Item -ItemType Directory -Force "$env:PLUGIN_INPUT_DIR\job1" Copy-Item cv.pdf "$env:PLUGIN_INPUT_DIR\job1\"
Run the plugin (default operation is extract): dotnet Documentize.Resume.dll --operation-type extract
Options (as listed in the README):
--operation-type(string, default extract) – operation to run (extract,analyze,compare,improve).--job-description-url(string, optional) – URL of a job description to tailor against.--job-description-text(string, optional) – Inline job description text.--target-industry(string, optional) – Target industry for tailoring.
A sample run that extracts data from a resume PDF and verifies that the report contains the applicant’s name:
# Linux / macOS (needs the .NET 10 runtime and documentize.lic next to the DLL)
export PLUGIN_INPUT_DIR=./work/input
export PLUGIN_OUTPUT_DIR=./work/output
mkdir -p "$PLUGIN_INPUT_DIR/job1"
cp cv.pdf "$PLUGIN_INPUT_DIR/job1/"
dotnet Documentize.Resume.dll --task-id job1
ls "$PLUGIN_OUTPUT_DIR/job1"
# Windows PowerShell
$env:PLUGIN_INPUT_DIR = "$PWD\work\input"
$env:PLUGIN_OUTPUT_DIR = "$PWD\work\output"
New-Item -ItemType Directory -Force "$env:PLUGIN_INPUT_DIR\job1" | Out-Null
Copy-Item cv.pdf "$env:PLUGIN_INPUT_DIR\job1\"
dotnet Documentize.Resume.dll --task-id job1
Get-ChildItem "$env:PLUGIN_OUTPUT_DIR\job1"
Verified
Every code sample on this page was run on 2026-11-03 and its result was checked:
- Extract resume data via CLI with text check (CLI plugin): passed in 43 s