# ai-interviewer

The ai-interviewer Claude Code subagent runs a practice interview against a revised resume and scores answers against job criteria. It probes specific resume claims, then reviews the transcript.

- 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/ai-interviewer.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/ai-interviewer

## What it does

The subagent creates a rubric from the job posting before asking questions, then conducts the interview one question at a time. Each score needs supporting words from the transcript, and weighted criteria feed into the final result. The rubric is saved before the first question and stays fixed once the interview begins.

It flags claims that go beyond the resume, lines the candidate could not defend, and answers that sound rehearsed. It also checks for missing parts of STAR-L and asks candidates to replace vague “we” statements with a clear account of their own actions. Accent, tone, fluency, pace, pauses, personality, and confidence do not affect scores.

## 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/ai-interviewer.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/ai-interviewer.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/ai-interviewer.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/ai-interviewer.md

## When to use it
- test whether a candidate can defend each resume line
- compare interview answers with job criteria
- spot claims that go beyond the resume
- find missing parts of a STAR-L answer

## Example prompts
- Run a practice interview using my revised resume and this job posting.
- Ask one question at a time and challenge specific claims on my resume.
- Score this interview transcript against the job criteria and cite evidence for each score.

## Similar
- [job-hunt-skills](https://affpapa.org/en/nevibecode/plugins/job-hunt-skills.md) — plugin · ★ 19 repo stars
- [dev-event-hiring](https://affpapa.org/en/nevibecode/skills/dev-event-hiring.md) — skill · 6800 installs
- [job-post-builder](https://affpapa.org/en/nevibecode/skills/job-post-builder.md) — skill · 1800 installs
- [talent-acquisition](https://affpapa.org/en/nevibecode/skills/talent-acquisition.md) — skill · 348 installs
- [hiring-scorecard](https://affpapa.org/en/nevibecode/skills/hiring-scorecard.md) — skill · 268 installs
- [resume-intelligence](https://affpapa.org/en/nevibecode/skills/resume-intelligence.md) — skill · 822 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
