interview-prep

interview-prep is a skill for Claude Code from kyoungbinkim/give-me-job. It costs 65 tokens per session (1,125 once invoked), scanned A, original, MIT.

A process for preparing Korean job-interview questions and defensible answer points from a resume, job description, cover letter, and evidence map. It keeps answers tied to information the applicant can support.

In plain words
What is it for?
Creating expected interview questions, preparing answer points, and checking whether Korean application claims can be defended from the available career evidence.
Why use it?
Applicants may be asked to explain claims made in their application. Preparing follow-up questions and evidence links helps identify unsupported or weakly supported claims before the interview.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the give-me-job plugin — 8 skills shipped together

Good fit Creating expected interview questions, preparing answer points, and checking whether Korean application claims can be defended from the available career evidence.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kyoungbinkim/give-me-job/interview-prep
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add kyoungbinkim/give-me-job --skill interview-prep
Clone the repo
git clone --depth 1 https://github.com/kyoungbinkim/give-me-job

Made for: Claude Code.

Or install give-me-job, the plugin that ships this one along with the rest of its 8 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for interview-prep

README.md
[![agentmods](https://agentmods.dev/badge/skills/kyoungbinkim/give-me-job/interview-prep/github.svg)](https://agentmods.dev/skills/kyoungbinkim/give-me-job/interview-prep)
Your own site
<a href="https://agentmods.dev/skills/kyoungbinkim/give-me-job/interview-prep"><img src="https://agentmods.dev/badge/skills/kyoungbinkim/give-me-job/interview-prep/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for interview-prep

Your own site · 80×15
<a href="https://agentmods.dev/skills/kyoungbinkim/give-me-job/interview-prep"><img src="https://agentmods.dev/badge/skills/kyoungbinkim/give-me-job/interview-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,125 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00065 $0.01125
Opus 5 $0.00032 $0.00562
Sonnet 5 $0.00013 $0.00225
Haiku 4.5 $0.00006 $0.00112

Measured 2d ago against content hash d330aa58376d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

interview-prep scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/interview-prep/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interview Prep

Use this skill to turn a cover letter package into interview preparation that the applicant can defend from resume.md evidence.

Trigger

Use this skill after cover-letter-draft.md or cover-letter-final.md exists and an evidence map is available.

Use it when the user asks for 면접 준비, 꼬리질문, 예상 질문, 답변 포인트, 모의면접, 면접 복기, 결과 분석, or interview defense based on a Korean application package.

Do Not Trigger

Do not use this skill before JD analysis and resume evidence exist.

Do not invent missing answers, metrics, tools, or company context. If a claim cannot be defended from resume.md, mark it as missing evidence.

Autonomy Level

DoF: LOW

Follow the input evidence. Generate questions and answer points only from the JD, cover letter, and resume.md. Do not add new achievements or unsupported explanation.

Permitted inferences:

  • Likely interviewer follow-up questions from a specific cover-letter claim.
  • Risk level from the strength of the mapped resume evidence.

Prohibited inferences:

  • Do not infer unlisted tools, metrics, responsibilities, awards, or business impact.
  • Do not turn weak evidence into a confident answer point.

Input Contract

Required context:

  • resume.md: structured career evidence.
  • applications/<company-role>/jd-analysis.md: role requirements and evaluation criteria.
  • applications/<company-role>/evidence-map.md: claim-to-evidence mapping.
  • applications/<company-role>/cover-letter-final.md or cover-letter-draft.md: answer text to defend.

Optional context:

  • applications/<company-role>/hr-review.md: blocker and warning context.
  • applications/<company-role>/company-values.md: optional company values context.

Required parameters:

  • company: target company name.
  • role: target role title.

Outputs produced:

  • applications/<company-role>/interview-prep.md

Workflow

  1. Read the cover letter and split it into core claims.
  2. Match each claim to evidence-map.md and resume.md.
  3. Generate 2-3 follow-up questions for each core claim.
  4. Add verification questions for metrics, tools, role scope, collaboration, failure handling, and JD fit when relevant.
  5. For any claim whose strength rests on a decision, add a question about the alternatives considered and why they were rejected. Interviewers probe the reasoning behind a result more often than the result itself.
  6. For any 실패/성장과정 claim, add a question about what the candidate changed afterward and where that change applied later. An answer that stops at the lesson is the common weak point.
  7. Write answer points using only supported evidence.
  8. Mark missing or thin evidence clearly.
  9. Add a short preparation checklist for manual review before interview.

Read the full file on GitHub · 136 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago Changed · +24 lines d330aa58376d
  2. 11d ago First seen · 112 lines · 65 tokens per session scan A 2ed38630f9ab

Subscribe to this mod's changes

interview-prep is a skill published in the GitHub repository kyoungbinkim/give-me-job (5 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 1,125 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.