Agent skill

Expert Code Reviewer

by GulajavaMinistudio in GulajavaMinistudio/Mayukai-Theme

Language-agnostic workflow for code reviews and security audits against Clean Code/SOLID principles, generating formal refactoring plans.

MITAuto-check passedDevelopment

Install Expert Code Reviewer

skills CLI
$ npx skills add GulajavaMinistudio/Mayukai-Theme --skill expert-code-reviewer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install GulajavaMinistudio/Mayukai-Theme expert-code-reviewer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/GulajavaMinistudio/Mayukai-Theme.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/expert-code-reviewer .claude/skills/expert-code-reviewer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
expert-code-reviewer
GitHub stars
139
Token cost
~1.4k tokens
SKILL.md length
268 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Language-agnostic workflow for code reviews and security audits against Clean Code/SOLID principles, generating formal refactoring plans.

  • Works in 2 steps: Code & Security Review Workflow → Implementation Plan Generation Workflow
  • Tasks that involve Code review
  • SKILL.md covers Overview, When to Use, Phase 1: Code & Security… and Phase 2: Implementation Plan…, plus 1 more section
  • Reaches img.shields.io

What it does

Expert Code Reviewer is an agent skill from GulajavaMinistudio/Mayukai-Theme. Language-agnostic workflow for code reviews and security audits against Clean Code/SOLID principles, generating formal refactoring plans.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Code review, Refactoring and Security review. It works with Visual Studio Code. The repository describes itself as: Combination theme for VS Code and VSCodium that inspired from Ayu Theme, Monokai , Andromeda, Material Color, and Gruvbox Darktooth Color. The licence is MIT.

When your agent uses it

  • Tasks that involve Code review
  • Tasks that involve Refactoring
  • Tasks that involve Security review

Example prompts

  • “/expert-code-reviewer”

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Code & Security Review Workflow
  2. Implementation Plan Generation Workflow

What it can do on your machine

Read from SKILL.md and the folder at commit c8c9159. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • img.shields.io

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Expert Code Reviewer loads about 1.4k tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 268 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~40
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from GulajavaMinistudio/Mayukai-Theme at commit c8c9159, republished under its MIT licence (© GulajavaMinistudio). 268 words, ~1,430 tokens.

Download SKILL.mdSave it as .claude/skills/expert-code-reviewer/SKILL.md (or your agent's skills folder).
name
expert-code-reviewer
description
Language-agnostic workflow for code reviews and security audits against Clean Code/SOLID principles, generating formal refactoring plans.
license
MIT
<!-- markdownlint-disable -->

Expert Code Reviewer Skill

Overview

This skill provides the structured workflow for analyzing codebase implementations, identifying architectural flaws, detecting security vulnerabilities, and generating formal, executable implementation plans for refactoring and remediation. This skill accompanies the @ExpertCodeReviewer agent.

When to Use

  • When the coding phase is complete and needs a comprehensive audit.
  • When security vulnerabilities or code smells are suspected.
  • When you need to create a structured refactoring plan in the /plan/ directory.

Phase 1: Code & Security Review Workflow

  1. Evaluate Against Clean Code & SOLID: Check for meaningful naming, function size, proper abstractions, error handling, and adherence to SOLID principles.
  2. Security Scan: Look for injection risks, insecure data handling, hardcoded secrets, and improper authorization (OWASP Top 10).
  3. Present Findings: Output your review in the chat using the following structured format (in Bahasa Indonesia):
    • Summary (Ringkasan): Brief overview of the code's quality.
    • Detailed Findings (Temuan Detail): For each issue:
      • Issue (Isu): Description.
      • Category (Kategori): Clean Code / SOLID / Security / Other.
      • Severity (Tingkat Keparahan): Low (Rendah) / Medium (Sedang) / High (Tinggi).
      • Location (Lokasi): Line numbers or function names.
      • Recommendation (Rekomendasi): Concrete approach to fix it.
  4. Discuss Strategy: Discuss the refactoring strategy with the user and ensure they agree before moving to Phase 2.

Phase 2: Implementation Plan Generation Workflow

  1. Ask the user (in Bahasa Indonesia): "Saya telah menyelesaikan review. Apakah Anda ingin saya membuat dokumen Implementation Plan resmi untuk perbaikan dan refactoring ini?"
  2. Filename: Use the naming convention refactor-[component]-[version].md and save it in the /plan/ directory.
  3. Template: The file MUST strictly adhere to the template below, enforcing step-by-step execution and mandatory approval checkpoints.

Mandatory Refactoring Plan Template

md
---
goal: [Concise Title Describing the Refactoring & Security Plan's Goal]
version: [Optional: e.g., 1.0, Date]
date_created: [YYYY-MM-DD]
last_updated: [Optional: YYYY-MM-DD]
owner: [Optional: Team/Individual responsible for this spec]
status: "Planned"
tags: ["refactor", "clean-code", "architecture", "security"]
---

# Introduction

![Status: <status>](https://img.shields.io/badge/status-<status>-<status_color>)

[A short concise introduction to the refactoring plan, the technical debt being addressed, the architectural goal, and any security vulnerabilities being remediated.]

## 1. Requirements & Constraints (Architecture & Security Focus)

[Explicitly list the architectural and security principles guiding this refactoring.]

- **REQ-001**: Requirement 1
- **PRN-001**: Architectural Principle (e.g., Ensure Single Responsibility Principle)
- **SEC-001**: Security Requirement (e.g., Prevent SQL Injection via parameterized queries)
- **CON-001**: Constraint 1

## 2. Implementation Steps

> **⚠️ EXECUTION DIRECTIVE FOR AI AGENTS:** 
> You MUST execute this plan phase by phase. You MUST run the specific testing/verification task at the end of each phase. After a phase is tested, you **MUST STOP AND WAIT** for the user's explicit approval before proceeding to the next phase.

### Implementation Phase 1: Security Remediation & Decoupling
- GOAL-001: [Describe the goal of this phase]

| Task     | Description                                                             | Completed | Date |
| -------- | ----------------------------------------------------------------------- | --------- | ---- |
| TASK-001 | Description of task 1 (include exact file paths)                        |           |      |
| TASK-00X | **VERIFY**: [Specific testing/verification step for this phase]         |           |      |
| TASK-00Y | **APPROVAL**: Wait for explicit user confirmation to proceed to Phase 2 |           |      |

### Implementation Phase 2: Core Architectural Refactoring
- GOAL-002: [Describe the goal of this phase]

| Task     | Description                                                     | Completed | Date |
| -------- | --------------------------------------------------------------- | --------- | ---- |
| TASK-003 | Description of task 3                                           |           |      |
| TASK-00X | **VERIFY**: [Specific testing/verification step for this phase] |           |      |
| TASK-00Y | **APPROVAL**: Wait for explicit user confirmation to proceed    |           |      |

## 3. Alternatives

[A bullet point list of any alternative architectural/security approaches considered.]
- **ALT-001**: Alternative approach 1

## 4. Dependencies

[List any new dependencies introduced or removed, including security libraries or sanitization packages.]
- **DEP-001**: Dependency 1

## 5. Files Affected

[List all files that will be modified, deleted, or created.]
- **FILE-001**: Description of file 1

## 6. Testing

[List the tests that need to be updated or implemented to verify behavior and ensure security vulnerabilities are patched. Phase-specific tests are in the Implementation Steps.]
- **TEST-001**: Description of test 1

## 7. Risks & Assumptions

[List any risks related to the refactoring or potential edge cases in the security patch.]
- **RISK-001**: Risk 1

© GulajavaMinistudio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/expert-code-reviewer of GulajavaMinistudio/Mayukai-Theme.

Open the folder on GitHubat commit c8c9159

Compare with similar skills

Expert Code Reviewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Expert Code Reviewer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Expert Code Reviewer this skillGulajavaMinistudio/Mayukai-Theme139—~1.4kAutomated safety check: PassMIT
Brooks Reviewhyhmrright/brooks-lint1.5k1 repos~430Automated safety check: PassMIT
Uncle Bob Craftsickn33/agentic-awesome-skills47k2 repos~2.6kAutomated safety check: PassMIT
Dignified Python Standardsdocling-project/docling69k—~1.5kAutomated safety check: PassApache-2.0
Clean Code GuardamElnagdy/guard-skills1.3k2 repos~4.3kAutomated safety check: PassMIT
Code Review Skillawesome-skills/code-review-skill2.1k—~2.8kAutomated safety check: NotesMIT

Similar skills

  • Brooks Review

    hyhmrright/brooks-lint

    PR code review that surfaces decay risks, design smells, and maintainability issues with concrete Symptom → Source → Consequence → Remedy findings, drawing on twelve classic engineering books.

    1.5k GitHub starsUsed in 1 repo~430 tokens
    DevelopmentAuto-check passed
  • Uncle Bob Craft

    sickn33/agentic-awesome-skills

    A skill your agent uses when performing code review, writing or refactoring code, or discussing architecture; complements clean-code and does not replace project linter/formatter.

    47k GitHub starsUsed in 2 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Dignified Python Standards

    docling-project/docling

    Applies opinionated production Python conventions chosen by the project's Python version: modern type syntax, pathlib, explicit checks and interface guidance.

    69k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Clean Code Guard

    amElnagdy/guard-skills

    Reviews generated or changed production code against Clean Code, SOLID, DRY, KISS, YAGNI and LLM-specific failure modes before it ships, in any language.

    1.3k GitHub starsUsed in 2 repos~4.3k tokens
    DevelopmentAuto-check passed
  • Code Review Skill

    awesome-skills/code-review-skill

    Provides comprehensive code review guidance for React 19, Vue 3, Angular 17+, Svelte 5, Rust, TypeScript, Java, Java 8, PHP, Ruby, Rails, Python, Django, FastAPI, Go, C/.NET, Kotlin, Swift, Dart…

    2.1k GitHub stars~2.8k tokensUpdated 1 mo ago
    DevelopmentAuto-check: notes
  • A code-change gate for the iPolloWork repository: search and reuse first, keep one source of truth, justify every new file or dependency, and audit the change.

    6.8k GitHub stars~2.7k tokensUpdated today
    DevelopmentAuto-check passed

More from GulajavaMinistudio/Mayukai-Theme

All 11 skills in this repo
  • Omni Dev

    GulajavaMinistudio/Mayukai-Theme

    Omni-expert principal software architect. An agent skill from GulajavaMinistudio/Mayukai-Theme.

    139 GitHub stars~736 tokensUpdated 3 mo ago
    Auto-check passed
  • Artifact Consistency Checker

    GulajavaMinistudio/Mayukai-Theme

    Performs consistency and traceability audits across documents (PRD vs Spec vs Plan) to detect missing coverage and scope creep.

    139 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Brainstorming Explorer

    GulajavaMinistudio/Mayukai-Theme

    Systematic codebase exploration, architectural critique, and generation of Project Discovery Drafts for SDLC Phase 0.

    139 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Bug Remediation Architect

    GulajavaMinistudio/Mayukai-Theme

    Workflow for analyzing bug reports, tracing root causes, and generating structured bug-fix implementation plans with rollback strategies.

    139 GitHub stars~1.4k tokensUpdated 3 mo ago
    Auto-check passed
  • Clarification Analyst

    GulajavaMinistudio/Mayukai-Theme

    Helps interrogate Product Requirements (PRD), Technical Specifications, and Implementation Plans to find ambiguities, missing edge cases, and hidden assumptions.

    139 GitHub stars~1.1k tokensUpdated 3 mo ago
    Auto-check passed
  • Memory Manager

    GulajavaMinistudio/Mayukai-Theme

    Standardized workflow for discovering, reading, and writing the project's memory file (memory.instructions.md) to persist context across chat sessions.

    139 GitHub stars~1.6k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about Expert Code Reviewer

What does Expert Code Reviewer do?

Language-agnostic workflow for code reviews and security audits against Clean Code/SOLID principles, generating formal refactoring plans. Expert Code Reviewer is an agent skill from GulajavaMinistudio/Mayukai-Theme. Language-agnostic workflow for code reviews and security audits against Clean Code/SOLID principles, generating formal refactoring plans.

When should I use Expert Code Reviewer?

Expert Code Reviewer fits situations like: tasks that involve Code review; tasks that involve Refactoring; tasks that involve Security review.

How do I install Expert Code Reviewer in Claude Code?

Run `npx skills add GulajavaMinistudio/Mayukai-Theme --skill expert-code-reviewer -a claude-code`. Or copy the skill folder (.agents/skills/expert-code-reviewer in GulajavaMinistudio/Mayukai-Theme) into .claude/skills/expert-code-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Expert Code Reviewer in Codex?

Run `npx skills add GulajavaMinistudio/Mayukai-Theme --skill expert-code-reviewer -a codex`. Or copy the skill folder (.agents/skills/expert-code-reviewer in GulajavaMinistudio/Mayukai-Theme) into .agents/skills/expert-code-reviewer in your project. Codex loads it when a task matches its description.

Can I use Expert Code Reviewer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add GulajavaMinistudio/Mayukai-Theme --skill expert-code-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/expert-code-reviewer, .gemini/skills/expert-code-reviewer, .github/skills/expert-code-reviewer and .opencode/skills/expert-code-reviewer in your project.

What does Expert Code Reviewer need to run?

SKILL.md names no scripts, command-line tools or credentials: Expert Code Reviewer is instructions for the agent only.

Does Expert Code Reviewer access the network?

SKILL.md names 1 domain. In commands or code: img.shields.io; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Expert Code Reviewer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Expert Code Reviewer use?

Expert Code Reviewer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Expert Code Reviewer use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Expert Code Reviewer?

Skills that share tags, products or a category with Expert Code Reviewer: Brooks Review (hyhmrright/brooks-lint, 1.5k stars), Uncle Bob Craft (sickn33/agentic-awesome-skills, 47k stars), Dignified Python Standards (docling-project/docling, 69k stars) and Clean Code Guard (amElnagdy/guard-skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Expert Code Reviewer?

GulajavaMinistudio (a GitHub user) maintains it in GulajavaMinistudio/Mayukai-Theme, which has 139 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on July 1, 2026.

Source: GulajavaMinistudio/Mayukai-Theme on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.