How do I install the Code Review En skill?

Run npx skillmds@latest add ousiass/code-review-en in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Code Review En skill do?

Full codebase quality check and refactoring review with report generation. It is listed under Docs & Writing on SkillMD.

Is Code Review En safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Code Review En?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Code Review En free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Code Review En?

ousiass (@ousiass) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Code Review En by ousiass — Agent Skill

Name: Code Review En
Rating: 4.2 (5 reviews)
Author: ousiass

File contents

Language: Always interact with the user in 日本語.

code-review-en

Prerequisites

Claude Code environment
gh CLI (for GitHub Issue output)

Arguments

No arguments: Check the entire project in the current directory
Path specified: Check only the specified directory or file

Phase 1: Project Structure Analysis

Identify directory structure, languages, and frameworks
Determine frontend / backend / both
List target files (exclude .gitignore entries and build artifacts)
Identify applicable check criteria and create tasks with TaskCreate

Phase 2: Quality Check

Run all applicable check criteria based on the detected project structure. Check all target files. Split by directory if there are many files.

Check criteria details in:

Common: references/check-common.md
Linterly: references/check-linterly.md
Frontend: references/check-frontend.md (includes Atomic Design rules)
Backend: references/check-backend.md
Refactoring: references/check-refactoring.md

Phase 3: Report Generation

Confirm output destination with AskUserQuestion:
- GitHub Issue (recommended): Title review: Code quality report (<branch>, <YYYY-MM-DD>)
- Local MD file: code-review-report.md
- Console output: Print the report directly in the conversation
Use report format from templates/report.md
Report summary to user

Severity Criteria

Severity	Criteria
Critical	Security risk, data loss, production incident
Important	Architecture violation, missing layer separation, untestable structure
Suggestion	Readability/maintainability improvements, refactoring candidates
Minor	Naming improvements, code style, trivial improvements

Rules

Never report based on guesses. Verify against actual code
Always include file path and line number in findings
Provide concrete improvement suggestions
Always include Critical/Important findings. Include Suggestion/Minor only if clear benefit
Respect framework conventions and existing code style
Track progress with TaskCreate/TaskUpdate

---name: code-review-endescription: Full codebase quality check and refactoring review with report generation.---**Language: Always interact with the user in 日本語.**# code-review-en## Prerequisites- Claude Code environment- `gh` CLI (for GitHub Issue output)## Arguments- No arguments: Check the entire project in the current directory- Path specified: Check only the specified directory or file## Phase 1: Project Structure Analysis1. Identify directory structure, languages, and frameworks2. Determine frontend / backend / both3. List target files (exclude `.gitignore` entries and build artifacts)4. Identify applicable check criteria and create tasks with TaskCreate## Phase 2: Quality CheckRun all applicable check criteria based on the detected project structure.**Check all target files.** Split by directory if there are many files.Check criteria details in:- Common: `references/check-common.md`- Linterly: `references/check-linterly.md`- Frontend: `references/check-frontend.md` (includes Atomic Design rules)- Backend: `references/check-backend.md`- Refactoring: `references/check-refactoring.md`## Phase 3: Report Generation1. Confirm output destination with `AskUserQuestion`: - **GitHub Issue** (recommended): Title `review: Code quality report (<branch>, <YYYY-MM-DD>)` - **Local MD file**: `code-review-report.md` - **Console output**: Print the report directly in the conversation2. Use report format from `templates/report.md`3. Report summary to user## Severity Criteria| Severity | Criteria ||----------|----------|| Critical | Security risk, data loss, production incident || Important | Architecture violation, missing layer separation, untestable structure || Suggestion | Readability/maintainability improvements, refactoring candidates || Minor | Naming improvements, code style, trivial improvements |## Rules- Never report based on guesses. Verify against actual code- Always include file path and line number in findings- Provide concrete improvement suggestions- Always include Critical/Important findings. Include Suggestion/Minor only if clear benefit- Respect framework conventions and existing code style- Track progress with TaskCreate/TaskUpdate

Frequently asked questions

Code Review En