# interview-system-designer

interview-system-designer — a skill for Claude Code and five other platforms that builds structured interview loops, writes questions with scoring rubrics, and runs calibration analysis on past results.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 137 installs · ★ 1183 repo stars
- Author: borghei
- License: LicenseRef-MIT-Commons-Clause · policy=link-only · description only; the file stays with the author
- Source: https://github.com/borghei/Claude-Skills/tree/HEAD/engineering/interview-system-designer/SKILL.md
- Updated: 2026-11-08
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/borghei-interview-system-designer

## What it does

The skill covers three scenarios: designing an interview loop for a role and seniority level, generating a question bank with rubrics, and doing statistical analysis of completed interview records.

Three Python scripts do the heavy lifting. `loop_designer.py` builds rounds, distributes competencies and produces scorecards. `question_bank_generator.py` pulls from scenario stems covering roughly 40 competencies — each with level-specific context (a senior prompt references "the service you own", a staff prompt references "a system several teams depend on"). Any competency without a ready stem gets questions marked `"generic": true`, which signals that those questions need replacing with scenarios drawn from the team's actual work. `hiring_calibrator.py` measures interviewer consistency and pass-rate drift; it emits a stderr warning when fewer than 50 records are present, because below that threshold group-level disparity figures are noise.

Calibration analysis requires a JSON file of interview results. Analysing demographic fields for adverse impact may need legal sign-off depending on jurisdiction.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill interview-system-designer -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/interview-system-designer/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/interview-system-designer/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill interview-system-designer -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/interview-system-designer/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill interview-system-designer -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/interview-system-designer/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install borghei/Claude-Skills engineering/interview-system-designer/SKILL.md
```

2. **Manually: put the files in place**
- File: `.github/skills/interview-system-designer/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill interview-system-designer -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/borghei/Claude-Skills --path engineering/interview-system-designer
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/interview-system-designer/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill interview-system-designer -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/borghei/Claude-Skills/tree/HEAD/engineering/interview-system-designer/SKILL.md

## When to use it
- design an interview loop for a specific role and seniority level
- write competency-based questions with 1–4 scoring anchors per round
- check whether interviewers apply the rubric consistently
- detect pass-rate drift across a batch of completed interviews
- swap out templated questions for scenarios from the team's real stack

## Example prompts
- Build an interview loop for a Senior Software Engineer on the platform team, focusing on system design and reliability
- Generate 9 questions for `react`, `typescript`, `system-design` competencies for a senior Frontend Engineer, output as JSON
- Run a comprehensive calibration analysis on `assets/sample_interview_results.json` and show interviewer drift

## Similar
- [evaluating-candidates](https://affpapa.org/en/nevibecode/skills/evaluating-candidates.md) — skill · 1 install
- [discovery-interview-prep](https://affpapa.org/en/nevibecode/skills/discovery-interview-prep.md) — skill · 3200 installs
- [interview-script](https://affpapa.org/en/nevibecode/skills/interview-script.md) — skill · 3100 installs
- [draft-offer](https://affpapa.org/en/nevibecode/skills/draft-offer.md) — skill · 2800 installs
- [hiring-scorecard](https://affpapa.org/en/nevibecode/skills/hiring-scorecard.md) — skill · 268 installs
- [job-post-writer](https://affpapa.org/en/nevibecode/skills/job-post-writer.md) — skill · 103 installs

## Other versions with the same name
- [interview-system-designer · alirezarezvani](https://affpapa.org/en/nevibecode/skills/interview-system-designer.md) — 672 installs

From the same set: [borghei/claude-skills](https://affpapa.org/en/nevibecode/by/borghei/claude-skills.md) — 120 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
