# recruiter-screen

The recruiter-screen Claude Code subagent checks a candidate’s LinkedIn and resume, then simulates an initial recruiter call. It is used to practise the first conversation after applying for a role.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 73 repo stars
- Author: Jerome Hardaway, Vets Who Code
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/Vets-Who-Code/ai-era-job-kit/tree/HEAD/agents/recruiter-screen.md
- Updated: 2026-11-11
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/recruiter-screen

## What it does

The subagent checks how a recruiter might compare a LinkedIn profile with a resume, including role titles and skills, and flags mismatches between them. When `linkedin-score.json` and `resume-score.json` are present, it reads those results; otherwise, it runs the `linkedin-scorer` and `resume-scorer` skills. It locates the kit through `scripts/linkedin_score.py`.

Next, it asks screening questions one at a time about motivation, a recent project and its portfolio evidence, the next role sought, location, work authorization, timing, and compensation. After the interview, it leaves the recruiter role and gives feedback on the pitch, possible concerns, and a tighter one-minute introduction built from the candidate’s stated facts. If the score files are missing, the two scoring skills need to be available.

## Requirements
- Works with: LinkedIn

## Install

### Claude Code (native platform)

1. **Plugin marketplace**
In the agent chat (not a shell):
```text
/plugin marketplace add Vets-Who-Code/ai-era-job-kit
```
In the agent chat (not a shell):
```text
/plugin install ai-era-job-kit@ai-era-job-kit
```

2. **Manually: put the files in place**
- File: `.claude/agents/recruiter-screen.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/recruiter-screen.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/recruiter-screen.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/Vets-Who-Code/ai-era-job-kit/tree/HEAD/agents/recruiter-screen.md

## When to use it
- rehearse the first recruiter call after applying
- spot differences between a LinkedIn profile and resume
- prepare answers about motivation, timing, and compensation
- shape a one-minute introduction from interview answers

## Example prompts
- Run a recruiter phone-screen rehearsal for this job description.
- Compare my LinkedIn profile with my resume, then interview me for the role.
- Help me refine a one-minute introduction and practise discussing compensation.

## Similar
- [job-hunt-skills](https://affpapa.org/en/nevibecode/plugins/job-hunt-skills.md) — plugin · ★ 19 repo stars
- [resume-refiner](https://affpapa.org/en/nevibecode/agents/resume-refiner.md) — subagent · ★ 6505 repo stars
- [resume-intelligence](https://affpapa.org/en/nevibecode/skills/resume-intelligence.md) — skill · 822 installs
- [icp-builder](https://affpapa.org/en/nevibecode/skills/crustdata-icp-builder.md) — skill · 343 installs
- [Job Search MCP](https://affpapa.org/en/nevibecode/mcp/job-search-mcp.md) — MCP server · ★ 5 repo stars
- [linkedin-profile-optimizer](https://affpapa.org/en/nevibecode/skills/linkedin-profile-optimizer.md) — skill · 149 installs

From the same set: [vets-who-code/ai-era-job-kit](https://affpapa.org/en/nevibecode/by/vets-who-code/ai-era-job-kit.md) — 18 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
