community-automations/cv-parser

Content & Docs

PublicClaude subagent

CV Resume Parser

Resumes come in every layout imaginable and plain text parsers choke on the creative ones. This reads them like a person does, with vision, then returns clean JSON.

sonnet1 weekGPT-4 VisionPDF.con8nPostgres
ClaudeClaude
ROI for
README.md

Why this subagent

Resumes come in every layout imaginable and plain text parsers choke on the creative ones. This reads them like a person does, with vision, then returns clean JSON.

It renders each page as an image, captures names, roles, dates, and skills, and maps them to a fixed schema your ATS can ingest. Tricky two-column designs stop breaking the import.

How it runs

    • Read

      Used at step 01 to kick off the pipeline.

    • Write

      Used at step 01 to kick off the pipeline.

    • WebFetch

      Used at step 01 to kick off the pipeline.

    • WebSearch

      Used at step 01 to kick off the pipeline.

Sample output

json
// Sample output
// (generated when the pipeline finishes)

Parse the resume into the fixed JSON schema; use null for missing fields and never invent employers or dates.

Unlock the rest

The full agent definition, install snippet, and starter task are gated for community members.

Members get the full `.md` agent file, the npm / pnpm install one-liners, a starter prompt that we've tuned against real runs, and the open-source repo when this automation ships there. One email, magic link, done.