A popular role pulls in hundreds of applications, and a recruiter reads each resume against the same checklist over and over. It is slow, it gets inconsistent by Friday, and good candidates get skimmed past when the pile is tall.
sonnet1 weekERPNextOpenAIGoogle DriveSlack
Claude
88ROI
74Scale
$4.9k92Saved
ROI for
README.md
Why this subagent
A popular role pulls in hundreds of applications, and a recruiter reads each resume against the same checklist over and over. It is slow, it gets inconsistent by Friday, and good candidates get skimmed past when the pile is tall.
This agent scores every applicant against your job description rubric, with a written reason behind each criterion so the ranking is defensible. It shortlists the strongest, flags the rest, and posts a ranked list to the hiring channel. Recruiters start with a sorted pile instead of a raw inbox.
How it runs
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.
Parse the resume into skills, years of experience, and relevant roles.
pending
Score the applicant against the job description rubric with a reason for each criterion.
pending
Shortlist the top scorers, flag the rest, and post the ranked list to the hiring channel.
pending
Sample output
json
// Sample output
// (generated when the pipeline finishes)
Score an applicant against a JD rubric and return a per-criterion breakdown, a total score, and a shortlist yes or no with reasons.
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.