Skip to main content
skill CX Codex

interview-system-designer · borghei — Claude Code skill: what it does

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.

LicenseRef-MIT-Commons-Clause 137 installs ★ 1,183 updated 2026-11-08

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add borghei/Claude-Skills --skill interview-system-designer -a claude-code
Open on GitHub

What interview-system-designer 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.

What it helps with

  • 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 for the agent

  • 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

How to install interview-system-designer

1Skills CLI (Vercel)

npx skills add borghei/Claude-Skills --skill interview-system-designer -a claude-code

2Manually: put the files in place

~/.claude/skills/interview-system-designer/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/interview-system-designer/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about interview-system-designer

How do I install interview-system-designer in Claude Code?

Run npx skills add borghei/Claude-Skills --skill interview-system-designer -a claude-code. The skill is then available at ~/.claude/skills/interview-system-designer/SKILL.md.

What does the interview-system-designer skill do?

It designs a structured interview loop for a given role and level, generates questions with rubrics and 1–4 scoring anchors, and after real interviews analyses calibration and pass-rate drift via hiring_calibrator.py.

Can the generated question bank be used as-is?

Questions marked "generic": true are placeholders: the script sets that flag when no scenario stem exists for a competency. Those questions need to be replaced with ones grounded in the team's actual problems; the rest already carry level context and stack-specific framing.

Similar skills

All skills for Agent setup: memory, context, orchestration →

interview-system-designer by other authors comes first.

interview-system-designer Alireza Rezvani The interview-system-designer skill plans interview rounds by role and level, suggests questions, and helps align scoring. Use it when you need a structured hiring loop. CX Codex +1 672installs evaluating-candidates liqiongyu evaluating-candidates — a skill for evidence-based hiring decisions: scorecards, work samples, reference checks. Turns signals into a recommendation with risks and mitigations. CX Codex +1 1installs discovery-interview-prep deanpeters discovery-interview-prep guides product teams through planning customer discovery conversations. It sets up target segments, frames research goals, and filters out bias before you speak with users. CX Codex +1 3,200installs interview-script phuryn Creates structured customer interview scripts based on The Mom Test and JTBD principles. Focuses on past user behavior instead of pitches. CX Codex +1 3,100installs draft-offer official anthropics draft-offer — a skill for Claude Code, Codex, Cursor and more that assembles a complete offer letter with salary, equity and signing bonus. CX Codex +1 2,800installs hiring-scorecard OneWave-AI Builds a structured hiring scorecard for any role with weighted competencies, interview questions, evaluation matrix, red/green flags, and reference check questions. CX Codex +1 268installs job-post-writer OneWave-AI job-post-writer — a skill for Claude Code that writes realistic job postings with honest pay ranges and pruned requirements. Clarifies daily workflows and strips out corporate buzzwords before publishing. CX Codex +1 103installs

From the same set120

The whole set →
landing-page-generator The landing-page-generator Claude Code skill plans and builds landing pages around one conversion goal. It also supports campaign and lead-capture pages. CX Codex +1 142installs content-strategy content-strategy guides content planning by structuring topic clusters, defining content pillars, and auditing published material. CX Codex +1 140installs atlassian-templates atlassian-templates — a skill to build, validate, and manage Jira and Confluence templates across your organization. CX Codex +1 140installs rag-architect rag-architect — a skill for Claude Code and Cursor designs RAG pipelines and tunes chunking configurations. It benchmarks retrieval quality using Recall@K and MRR on real queries. CX Codex +1 137installs devops-workflow-engineer devops-workflow-engineer generates GitHub Actions workflows, analyzes pipelines for bottlenecks and builds deployment plans with strategy selection. CX Codex +1 136installs skill-tester skill-tester — a skill for Claude Code validates skill packages, runs Python checks, and scores quality. It fits workflows for building, auditing, or publishing a skill. CX Codex +1 136installs risk-management-specialist risk-management-specialist — a skill for medical device risk management under ISO 14971:2019: planning, hazard analysis, risk control and post-production monitoring. CX Codex +1 136installs design-auditor design-auditor is a Claude Code skill that grades a UI on three A–F scales: design, AI slop, and accessibility. CX Codex +1 133installs

Project sponsors

Companies that keep this analytics open