interview-retro

interview-retro is a skill for Claude Code from CaesiumY/claude-interview-agents. It costs 81 tokens per session (3,521 once invoked), scanned A, original, MIT.

A skill for recording what happened in a real job interview and comparing the questions with existing preparation material. It finds missing or weakly covered areas and feeds them back into interview notes, question banks, and future practice.

In plain words
What is it for?
Use it soon after an interview to capture the stage, questions, answer summaries, self-assessments, and overall impressions. It helps identify repeated weak areas and update preparation resources.
Why use it?
Interview questions are easy to forget, especially after a stressful session. Recording them without immediate judgment preserves useful information and shows what to prepare before the next application.

Skill for Claude Code

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

Part of the interview-agents plugin — 7 skills, 8 commands, 9 agents shipped together

Good fit Use it soon after an interview to capture the stage, questions, answer summaries, self-assessments, and overall impressions. It helps identify repeated weak areas and update preparation resources.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/caesiumy/claude-interview-agents/interview-retro
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 CaesiumY/claude-interview-agents --skill interview-retro
Clone the repo
git clone --depth 1 https://github.com/CaesiumY/claude-interview-agents

Made for: Claude Code.

Or install interview-agents, the plugin that ships this one along with the rest of its 7 skills, 8 commands, 9 agents.

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-retro

README.md
[![agentmods](https://agentmods.dev/badge/skills/caesiumy/claude-interview-agents/interview-retro.svg)](https://agentmods.dev/skills/caesiumy/claude-interview-agents/interview-retro)
Your own site
<a href="https://agentmods.dev/skills/caesiumy/claude-interview-agents/interview-retro"><img src="https://agentmods.dev/badge/skills/caesiumy/claude-interview-agents/interview-retro.svg" alt="Measured on agentmods" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,521 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 $0.00081 $0.03521
Opus 5 $0.00041 $0.01760
Sonnet 5 $0.00016 $0.00704
Haiku 4.5 $0.00008 $0.00352

Measured 8d ago against content hash 51f54faa06b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

interview-retro 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 8d 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-retro/SKILL.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

실전 면접 회고 스킬

핵심 관점

실전 면접은 가장 비싼 모의면접이다 — 받은 질문을 버리면 그 비용이 사라진다.

  • 회고의 목적은 잘잘못 채점이 아니라 자산 축적입니다. 실전에서 받은 질문은 질문지 커버리지·인터뷰 노트·다음 모의면접으로 환류되어 다음 지원의 준비 비용을 낮춥니다
  • 합격/불합격 결과와 무관하게 실행 가치가 있습니다 — 어느 쪽이든 받은 질문은 남습니다
  • 기억은 빠르게 증발하므로 면접 직후 실행할수록 회수율이 높습니다

회고 수집 프로토콜

비난 없는 회고 톤 — 수집 전 구간 필수 준수

하지 않는 것 하는 것
수집 중 답변에 대한 평가·교정·훈수 ("그건 이렇게 답했어야죠") 정보만 수집하고, 분석은 갭 분석 단계에서 일괄 수행
"못 답함"을 실패로 규정하는 표현 "다음 지원 전에 채울 수 있는 갭을 발견했다"로 리프레이밍
자책성 발화("제가 부족해서…")에 동조하거나 반박 발화에서 사실(질문·답변·판정)만 추출하고 판단은 보류
기억나지 않는 질문·답변을 추측으로 채움 "(기억 안 남)"을 그대로 기록 — 답변 창작 금지

이 원칙은 /mock-interview의 "세션 중 피드백 금지"와 같은 설계입니다: 수집 중 훈수가 시작되면 사용자가 기억을 꺼내는 것을 멈추고 방어를 시작해 회수율이 떨어집니다.

수집 순서와 단위

한 번에 하나씩 진행합니다 (목록을 한꺼번에 요구하지 않음):

  1. 면접 단계 (택 1): 서류후 과제 / 1차 기술 / 2차 심층 / 임원·컬처핏
  2. 질문 루프 — 질문마다 3단계로 수집하고 즉시 보고서 파일에 append:
    • 받은 질문 (기억나는 대로 — 정확하지 않아도 됨)
    • 당시 답변 요지 (요지만 — 원문 복원을 강요하지 않음)
    • 자가 판정 (아래 3단계 앵커)
  3. 전체 소감 (자유 발화 — 분위기, 예상과 달랐던 점, 스스로 느낀 것)

자가 판정 3단계 앵커

판정 앵커 (하나라도 해당하면 그 판정)
잘 답함 준비한 구조대로 답했고, 꼬리질문에도 막히지 않음
버벅임 답은 했지만 구조 없이 헤맴 / 수치·근거를 대지 못함 / 꼬리질문에서 말이 꼬임
못 답함 "모르겠습니다"로 넘어감 / 질문 의도와 다른 답을 함 / 답변을 시작하지 못함

판정이 애매하면 더 나쁜 쪽을 선택합니다 (보수 판정 — 환류 대상을 놓치는 손해가 과잉 환류의 손해보다 큽니다).


갭 분류 기준 3종

받은 질문마다 A → B → C 순서로 검사하고 첫 매칭에서 확정합니다.

분류 정의 판정 기준
A. 질문지 수록 (리허설 효과 확인) 받은 질문이 resumes/[이름]_questionnaire.md의 특정 질문과 같은 검증 대상을 겨냥 질문지의 Qn(꼬리질문 3줄 포함)과 검증 대상이 일치 — 매칭된 Qn 번호를 근거로 기록
B. 질문은행 영역 내 미수록 질문지에는 없지만 질문은행이 커버하는 영역에 속함 아래 '질문은행 영역 목록'의 어느 한 영역에 속함 — 영역명을 근거로 기록
C. 완전 신규 (커버리지 갭) A·B 모두 아님 회사 도메인 특화, 최신 기술, 질문은행 밖 CS 등 — 가장 값진 수확이므로 반드시 기록

매칭은 표면 문구가 아니라 검증 대상 기준입니다:

받은 질문 "리액트에서 리스트가 느릴 때 어떻게 하시겠어요?" ↔ 질문지 Q "리렌더링 최적화 경험을 설명해주세요" → 검증 대상이 동일(렌더링 성능 최적화) → A (표현이 달라도 매칭)

질문은행 영역 목록 (B 판정용)

트랙 영역 출처
기술 JS/TS · 프레임워크 · CSS/스타일링 · 웹 성능 · 협업/커뮤니케이션 · 브라우저/네트워크/보안 skills/interview-questionnaire/SKILL.md
임원(executive) A(커리어·성장 서사) · B(사업·조직 관점) · C(책임·판단) skills/culture-fit-interview/SKILL.md
컬처핏(culture) A(협업 스타일) · B(일하는 방식·가치관) · C(자기 인식) skills/culture-fit-interview/SKILL.md

Read the full file on GitHub · 225 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. 8d ago First seen · 225 lines · 81 tokens per session scan A 51f54faa06b1

Subscribe to this mod's changes

interview-retro is a skill published in the GitHub repository CaesiumY/claude-interview-agents (3 stars, last pushed 23d ago), licensed MIT. It adds 81 tokens to every session and 3,521 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

playwright

Use when the task requires capturing or automating a real browser from the terminal.

openai/openai-agents-python · 19 tokens

good-docs-writing

Writing style guide derived from Modal's documentation voice. Apply when writing or editing docs, guides, tutorials, or technical prose that should read direct, second-person, confident, low-jargon, and example-first. Use to draft new docs in this voice or to revise existing prose toward it.

ComposioHQ/composio · 63 tokens

tooluniverse-organic-chemistry

Organic chemistry reasoning guide for reaction product prediction, mechanism analysis (electrophilic/nucleophilic substitution, addition, elimination, pericyclic, radical), and spectroscopy interpretation (1H/13C NMR, IR, MS). Reasons from first principles (electron flow, kinetic vs thermodynamic) rather than…

mims-harvard/ToolUniverse · 86 tokens

eli5

Explain concepts in very simple terms suitable for a five-year-old.

genkit-ai/genkit · 16 tokens

stride-analysis-patterns

Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.

sangrokjung/claude-forge · 30 tokens

blind-spot-pass

Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…

sangrokjung/claude-forge · 221 tokens