cowork-hiring-screener — Claude Code skill for resume screening
cowork-hiring-screener — a Claude Code skill that scores resumes against a job description and ranks candidates with supporting evidence. It takes a resume folder and the role requirements.
MIT 107 installs ★ 440 updated 2026-10-20
npx skills add OneWave-AI/claude-skills --skill cowork-hiring-screener -a claude-codeWhat cowork-hiring-screener does
The skill turns a folder of resumes and a job description into a candidate screening report. It separates required qualifications, preferred ones, and disqualifiers, then asks for approval of the scoring rubric. Vague job requirements need clarification before scoring begins.
Each nonzero score must have evidence from the resume. The resulting screening-report.md groups candidates into three tiers and records strengths, gaps, and open questions. For top-ranked candidates, the skill prepares tailored interview questions; it also drafts decline emails for the lowest tier. Emails are drafts only and are never sent.
Scoring covers skills and experience, not protected characteristics. When the folder contains more than 100 resumes, the skill first applies hard disqualifiers and reports how many candidates were removed and why.
What it helps with
- compare resumes with a job's requirements
- rank candidates with evidence for each score
- write interview questions tied to resume claims and gaps
- draft decline messages for candidates
Example prompts for the agent
- Screen the
resumesfolder againstjob-description.md. - Show me the scoring rubric for
job-description.mdbefore evaluating candidates. - Prepare interview questions for the top-ranked candidates.
How to install cowork-hiring-screener
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill cowork-hiring-screener -a claude-code2Manually: put the files in place
~/.claude/skills/cowork-hiring-screener/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/cowork-hiring-screener/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill cowork-hiring-screener -a codex2Manually: put the files in place
.agents/skills/cowork-hiring-screener/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill cowork-hiring-screener -a cursor2Manually: put the files in place
.cursor/skills/cowork-hiring-screener/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills cowork-hiring-screener2Manually: put the files in place
.github/skills/cowork-hiring-screener/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill cowork-hiring-screener -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path cowork-hiring-screenerManually: put the files in place
.devin/skills/cowork-hiring-screener/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill cowork-hiring-screener -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about cowork-hiring-screener
How do I install cowork-hiring-screener in Claude Code?
Run npx skills add OneWave-AI/claude-skills --skill cowork-hiring-screener -a claude-code. The skill is installed at ~/.claude/skills/cowork-hiring-screener/SKILL.md.
What does cowork-hiring-screener do?
It scores resumes against a job description, ranks candidates with evidence, and prepares interview questions and draft emails.
How does cowork-hiring-screener handle protected characteristics?
It evaluates skills and experience only. Age, gender, ethnicity, and family status are excluded from scoring.
Source text
SKILL.md · MIT
---
name: cowork-hiring-screener
description: Point Cowork at a folder of resumes plus a job description -- screens every candidate against the actual requirements, produces a ranked shortlist with evidence, drafts advance/decline emails, and builds interview kits for the top picks. Pairs with hiring-scorecard for the interview stage.
tools: Read, Glob, Grep, Write, Bash
model: inherit
---
# Cowork Hiring Screener
Screen a resume pile the way a disciplined recruiter does: score against the written requirements, cite evidence from the resume for every score, and never let formatting quality masquerade as candidate quality. Input is a folder of resumes (PDF, .docx, text) and a job description; output is a defensible shortlist.
## Workflow
1. **Extract requirements.** Parse the JD into must-haves, nice-to-haves, and disqualifiers. Present the rubric for approval before scoring -- the human may reweight. If the JD is vague ("rockstar", "wears many hats"), ask what actually matters before proceeding.
2. **Inventory.** Catalog every file in the folder. Flag unreadable files, duplicate submissions, and non-resume documents. Report the candidate count before starting.
3. **Score each candidate** against the rubric: 0-3 per must-have and nice-to-have, with a direct resume quote or specific experience justifying every non-zero score. No quote, no points.
4. **Rank and tier.** Produce `screening-report.md`: Tier 1 (interview now), Tier 2 (backup), Tier 3 (decline), each candidate with score breakdown, one-paragraph summary, strongest signal, and biggest gap or open question.
5. **Draft communications.** Advance emails for Tier 1 (with 2-3 proposed interview slots if calendar tools are connected) and respectful decline drafts for Tier 3. Drafts only -- never send.
6. **Interview kits.** For each Tier 1 candidate, generate 5-6 questions probing their specific gaps and claims -- "Your resume says you led the Series B data migration; walk me through the hardest call you made" -- not generic behavioral questions. Hand off to `hiring-scorecard` for structured interview evaluation.
## Rules
- Score the content, not the polish. A plain resume with strong evidence outranks a designed one with vague claims.
- Never infer or use protected characteristics (age, gender, ethnicity, family status, graduation years as an age proxy). Score skills and experience only.
- Distinguish "did the thing" from "was near the thing." "Led migration" and "team migrated during my tenure" are different scores.
- Flag inconsistencies (date overlaps, title inflation between sections) as open questions, not disqualifiers.
- Keep every scoring decision auditable: the report must let a hiring manager disagree with specifics, not vibes.
- If the pile exceeds 100 resumes, do a hard-disqualifier pass first and report how many were cut and why before deep-scoring the rest.
## Quick Commands
- "Screen [folder] against [JD]" -- full workflow
- "Just the rubric" -- step 1 only, for approval
- "Top 5 only" -- deep-score and report only the strongest candidates
- "Draft the declines" -- Tier 3 communication drafts
© OneWave-AI · MIT · OneWave-AI/claude-skills