assignment-review

assignment-review is a skill for Claude Code from CaesiumY/claude-interview-agents. It costs 83 tokens per session (4,336 once invoked), scanned A, original, MIT.

A review skill for take-home frontend assignments, meaning coding tasks completed by a candidate outside a live interview. It evaluates requirements, whether the project runs, code quality, the README, commit history, and expectations for a developer with three years of experience.

In plain words
What is it for?
It checks each stated requirement, identifies implementation evidence, scores the submission across several areas, and generates questions a reviewer may ask. It is used by the /assignment-review command.
Why use it?
A polished submission can still fail if it misses a required feature or cannot be run. This review checks those basic conditions first and then explains the quality and interview risks.

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 It checks each stated requirement, identifies implementation evidence, scores the submission across several areas, and generates questions a reviewer may ask. It is used by the /assignment-review command.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/caesiumy/claude-interview-agents/assignment-review
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 assignment-review
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 assignment-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/caesiumy/claude-interview-agents/assignment-review.svg)](https://agentmods.dev/skills/caesiumy/claude-interview-agents/assignment-review)
Your own site
<a href="https://agentmods.dev/skills/caesiumy/claude-interview-agents/assignment-review"><img src="https://agentmods.dev/badge/skills/caesiumy/claude-interview-agents/assignment-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,336 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 $0.00083 $0.04336
Opus 5 $0.00042 $0.02168
Sonnet 5 $0.00017 $0.00867
Haiku 4.5 $0.00008 $0.00434

Measured 8d ago against content hash 39c54d46d98a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

assignment-review 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/assignment-review/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

과제 전형 리뷰 스킬 (Assignment Review)

역할

프론트엔드 3년차 지원자가 제출할 과제 전형(take-home) 코드를 채용사 리뷰어의 눈으로 평가하고, 제출 전에 고쳐야 할 것과 면접에서 받을 질문을 미리 알려줍니다.

핵심 관점: 과제 전형은 "요구사항을 지켰는가"가 1차 게이트다. 요구사항을 안 지킨 화려한 코드는 탈락하고, 요구사항을 지킨 평범한 코드는 통과한다. 따라서 요구사항 충족과 실행 가능성은 점수가 아니라 Binary 게이트로 먼저 판정한다.

평가 구조

① 요구사항 충족 (Binary 게이트) ──┐
② 실행 가능성   (Binary 게이트) ──┴─→ 미충족·실행 불가 시 recommendation 조정
③ 코드 품질     30점  ┐
④ README·실행성 20점  ├─ 합계 100점 (total_score)
⑤ 커밋 히스토리 15점  │
⑥ 3년차 기대치  35점  ┘

채점 재현성 원칙: 아래 앵커 표를 그대로 적용합니다. 같은 제출물에는 같은 점수가 나와야 사용자가 "리뷰 → 수정 → 재리뷰" 사이클에서 점수 변화를 실제 개선의 증거로 신뢰할 수 있습니다. 각 차원 점수는 항목 점수의 합이며, total_score는 ③~⑥ 네 차원의 합입니다.


Binary 게이트 (점수 이전에 먼저 판정)

① 요구사항 충족 — Binary

요구사항 문서에 명시된 요구사항 각각을 충족/부분 충족/미충족으로 판정하고 근거를 답니다.

판정 기준
충족 요구사항이 동작하는 코드로 구현됨 (구현 위치를 파일·함수로 지목 가능)
부분 충족 일부만 구현되거나 핵심 케이스 누락 (예: 목록은 되지만 에러 상태 없음)
미충족 구현 흔적 없음
  • 필수/선택 구분: 요구사항 문서가 필수(must)/선택(bonus·optional)을 구분하면 그대로 표기합니다. 구분이 없으면 명시된 기능 요구사항은 전부 필수로 간주합니다.
  • 하나라도 미충족이면 그 항목을 명시하고 recommendation 조정 규칙(아래)을 적용합니다.
  • requirements_check 배열에 {요구사항, 충족 여부, 필수 여부, 근거}로 기록합니다.

요구사항 문서 미제공 시 (요구사항 미확인 모드): requirements_check에 "요구사항 문서 미제공 — 코드 품질만 평가"를 단일 항목으로 기록하고, 요구사항 Binary 조정은 적용하지 않습니다. mode를 requirements_unverified로 설정하고 summary 첫 문장에 명시합니다.

② 실행 가능성 — Binary

앱이 실제로 구동되는지 판정합니다. 이 판정은 커맨드(오케스트레이터)가 전달한 실행 검증 결과에 근거합니다 — 리뷰어 에이전트는 코드를 실행할 수 없으므로, 프롬프트로 주입된 결과(정상/실행 불가/미검증)를 그대로 사용합니다.

status 의미 recommendation 영향
정상 의존성 설치·빌드·구동이 확인됨 없음
실행 불가 설치·빌드·구동 중 하나라도 실패 recommendation을 **총점과 무관하게 "재작업 필요"**로 설정, improvement_priority 최상단
미검증 사용자가 실행 검증을 건너뜀 조정 없음. recommendation 옆에 "(실행 미검증)" 병기

중요: 실행 불가는 20점 차원의 감점이 아니라 Binary 실패로 분류합니다. 원인이 사소한 환경 문제(node 버전 등)일 수 있으나, 제출물이 구동되지 않는 것은 채용 리뷰에서 즉시 탈락 사유이므로 총점과 분리해 다룹니다.


점수 차원별 앵커 표

③ 코드 품질 (30점)

항목 배점 앵커
컴포넌트·모듈 구조 8 관심사 분리 명확·재사용 단위 적절=8 / 일부 혼재=4 / 거대 단일 파일·로직 뒤섞임=0
네이밍·컨벤션 일관성 6 일관된 규칙·의도가 드러남=6 / 부분 불일치=3 / 임의적·혼재=0
타입 안전성 6 정확한 타입·any 없음=6 / 부분적 any·타입 단언 남용=3 / 타입 미사용·오용=0 (JS 프로젝트는 런타임 방어·PropTypes로 대체 평가)
중복 제거·추상화 5 DRY·적절한 추상화=5 / 일부 중복=2 / 광범위 복붙=0
죽은 코드·디버그 잔재 5 없음·의미 있는 주석만=5 / 일부 잔존=2 / console.log·주석 처리 코드 다수=0

Read the full file on GitHub · 237 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 · 237 lines · 83 tokens per session scan A 39c54d46d98a

Subscribe to this mod's changes

assignment-review is a skill published in the GitHub repository CaesiumY/claude-interview-agents (3 stars, last pushed 23d ago), licensed MIT. It adds 83 tokens to every session and 4,336 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

frontend-code-review

Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.

sangrokjung/claude-forge · 42 tokens

improve-threejs

Audit and fix Three.js and React Three Fiber apps for frame-loop performance, GPU memory leaks, scene-graph correctness, and visual defects like z-fighting, shadow acne, wrong color space, and broken resize handling. Uses React Doctor as the scanning engine plus a visual rubric checked against rendered output. Use…

millionco/react-doctor · 108 tokens

performance

Diagnose React runtime performance with React Doctor traces, live render outlines, Long Animation Frames, interaction timing, and component render evidence. Use when invoked as /performance for a slow interaction, unexpected re-renders, or a measured before-and-after comparison.

millionco/react-doctor · 53 tokens

generic-react-code-reviewer

Review React/TypeScript code for bugs, security vulnerabilities, performance issues, accessibility gaps, and CLAUDE.md workflow compliance. Enforces TypeScript strict mode, GPU-accelerated animations, WCAG AA accessibility, bundle size limits, and surgical simplicity. Use when completing features, before commits, or…

travisjneuman/.claude · 71 tokens

generic-static-code-reviewer

Review static site code for bugs, security issues, performance problems, accessibility gaps, and CLAUDE.md compliance. Enforces pure HTML/CSS/JS standards, minimal page weight, mobile-first design. Use when completing features, before commits, or reviewing changes.

travisjneuman/.claude · 59 tokens

react-change-review

Review recent React, Next.js, or TypeScript UI code changes for hardening before merge or commit. Use when asked to review recent React code changes, audit a React diff, harden a feature, check a PR or branch for React issues, or produce a stack-ranked list of nonredundant findings and a recommended fix plan using…

petekp/claude-code-setup · 95 tokens