PO

powershell-code-reviewer

Automated review of PowerShell files with severity-ranked findings.

Install

mkdir -p .claude/skills/powershell-code-reviewer && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15162" && unzip -o skill.zip -d .claude/skills/powershell-code-reviewer && rm skill.zip

Installs to .claude/skills/powershell-code-reviewer

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Review PowerShell code for quality, security, and best practices. Categorizes findings by severity P0 (Critical), P1 (High), P2 (Medium), P3 (Low). Produces structured review reports with issue lists and actionable recommendations. USE FOR: reviewing .ps1 .psm1 .psd1 files; auditing PowerShell modules; checking security vulnerabilities, error handling, performance, coding style, and maintainability. TRIGGERS: review powershell, audit script, check ps1, powershell code review.
480 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Advanced

Key capabilities

  • Review PowerShell code for security vulnerabilities
  • Analyze error handling mechanisms like `try/catch` and `$ErrorActionPreference`
  • Identify performance bottlenecks related to pipeline usage and I/O
  • Check code style for naming conventions, indentation, and Verb-Noun format
  • Assess maintainability by evaluating function length and code duplication
  • Classify issues by severity: P0 (Critical), P1 (High), P2 (Medium), P3 (Low)

How it works

This skill analyzes PowerShell code across six dimensions (security, error handling, performance, style, maintainability, compatibility), classifies identified issues by severity, and generates a detailed report with recommendations.

Inputs & outputs

You give it
PowerShell code snippets or file paths
You get back
A structured review report with a summary of issues by severity, detailed descriptions, risks, repair suggestions, and an overall rating

When to use powershell-code-reviewer

  • Audit powershell script
  • Review module code
  • Find performance issues

About this skill

PowerShell Code Reviewer

語言規範

所有回覆必須使用正體中文。專業術語(如 cmdlet 名稱、pattern 名稱、OWASP 類別、Git 指令等)保留英文原文。

用途說明

對輸入的 PowerShell 程式碼進行全面審查,依嚴重等級 P0–P3 分類問題,並產出結構化報告與建議清單。

When to Use

  • 審查 .ps1 / .psm1 / .psd1 檔案
  • 提交 Pull Request 前的自動化品質檢查
  • 稽核 PowerShell 模組的安全性與最佳實踐
  • 找出潛在的效能瓶頸或邏輯錯誤

Review Procedure

Step 1 — 接收程式碼

接受以下任一形式的輸入:

  • 使用者直接貼上的 PowerShell 程式碼片段
  • 工作區內的檔案路徑(使用 read_file 讀取)
  • 多個檔案路徑(平行讀取所有檔案)

Step 2 — 分析階段

依序檢查以下六個面向,並收集潛在問題:

  1. 安全性 (Security) — 參考 severity-guide.md 的 P0 清單
  2. 錯誤處理 (Error Handling)try/catch$ErrorActionPreference-ErrorAction
  3. 效能 (Performance) — 管線使用、迴圈內 I/O、大量物件建立
  4. 程式碼風格 (Style) — 命名慣例、縮排、Verb-Noun 格式
  5. 可維護性 (Maintainability) — 函式長度、重複程式碼、Magic Number
  6. 相容性 (Compatibility) — PS 版本差異、Windows/Linux 路徑、別名使用

詳細的檢查項目請參閱 review-checklist.md

Step 3 — 嚴重等級分類

依據 severity-guide.md 將每個問題分配到對應等級:

等級名稱定義
P0Critical安全漏洞、資料遺失風險、系統損壞 — 必須立即修復
P1High邏輯錯誤、未處理例外、嚴重效能問題 — 應在合併前修復
P2Medium程式碼風格違規、輕微 Bug、可讀性問題 — 建議修復
P3Low改善建議、最佳實踐提示、可選優化 — 參考即可

Step 4 — 產出報告

以下列格式輸出完整報告:


📋 審查報告 — <檔案名稱或程式碼摘要>

摘要

等級數量
🔴 P0 CriticalN
🟠 P1 HighN
🟡 P2 MediumN
🟢 P3 LowN
合計N

🔴 P0 — Critical(必須立即修復)

(若無則標示:無 P0 問題)

  • [P0-1] <問題標題>
    • 位置: 第 X 行 / 函式 <name>
    • 說明: <問題的具體描述>
    • 風險: <若不修復會發生什麼事>
    • 修復建議:
      # 建議的修正程式碼
      

🟠 P1 — High(合併前修復)

  • [P1-1] ...

🟡 P2 — Medium(建議修復)

  • [P2-1] ...

🟢 P3 — Low(參考優化)

  • [P3-1] ...

✅ 建議清單(優先順序)

依修復優先序列出所有行動項目:

  1. [ ] [P0-1] <修復描述>
  2. [ ] [P1-1] <修復描述>
  3. [ ] [P2-1] <修復描述>
  4. [ ] [P3-1] <修復描述>

📌 整體評分與總結

  • 整體品質: ⭐⭐⭐☆☆(3/5)
  • 是否建議合併: ✅ 可合併 / ❌ 需修復後再合併 / ⚠️ 建議修復後合併
  • 摘要說明: <2-3 句總結程式碼整體狀況>

Step 5 — 自動修復建議

針對 P0 與 P1 的所有問題,以及 P2 中有明確修正方式的問題,額外輸出可直接套用的修正程式碼片段:

# [P0-1] 修正:移除硬編碼密碼,改用 SecureString 參數
# 原始碼(有問題):
$password = "MyP@ssw0rd"

# 修正後:
param(
    [Parameter(Mandatory)]
    [securestring] $Password
)

格式規則

  • 每個程式碼區塊前標示對應的問題編號(如 [P0-1]
  • 同時保留「原始碼(有問題)」與「修正後」,方便對照
  • 若修正涉及大幅重構,只提供關鍵差異部分,並說明重構方向

Quality Completion Criteria

報告完成前確認:

  • 所有回覆使用正體中文,專業術語保留英文
  • 涵蓋全部六個分析面向
  • 每個問題都標示了行號或函式名稱
  • 每個 P0/P1 問題都附有修復程式碼範例
  • Step 5 已對所有 P0/P1 及可修復 P2 輸出自動修復片段
  • 建議清單按嚴重等級排序
  • 整體評分與合併建議已填寫

When not to use it

  • When the code is not PowerShell (.ps1, .psm1, .psd1 files)
  • When the user does not want a structured report with severity classifications
  • When the user does not need actionable recommendations or auto-fix suggestions

Limitations

  • All responses must be in Traditional Chinese, with professional terms retained in English
  • The skill relies on predefined checklists for detailed checks
  • Auto-fix suggestions are provided for P0, P1, and some P2 issues

How it compares

This workflow provides a complete, structured review of PowerShell code with severity-based classification and auto-fix suggestions, offering a more systematic and actionable feedback mechanism than manual code inspection.

Compared to similar skills

powershell-code-reviewer side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
powershell-code-reviewer (this skill)04moNo flagsAdvanced
find-bugs57moNo flagsIntermediate
tech-debt-analyzer59moReviewIntermediate
static-analysis56moNo flagsAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

find-bugs

davila7

Find bugs, security vulnerabilities, and code quality issues in local branch changes. Use when asked to review changes, find bugs, security review, or audit code on the current branch.

529

tech-debt-analyzer

ailabs-393

This skill should be used when analyzing technical debt in a codebase, documenting code quality issues, creating technical debt registers, or assessing code maintainability. Use this for identifying code smells, architectural issues, dependency problems, missing documentation, security vulnerabilities, and creating comprehensive technical debt documentation.

522

static-analysis

gmh5225

Expertise in LLVM-based static analysis including dataflow analysis, pointer analysis, taint tracking, and program verification. Use this skill when implementing security scanners, bug finders, code quality tools, or performing program analysis research.

518

agent-code-analyzer

ruvnet

Agent skill for code-analyzer - invoke with $agent-code-analyzer

317

codex-code-review

tyrchen

Perform comprehensive code reviews using OpenAI Codex CLI. This skill should be used when users request code reviews, want to analyze diffs/PRs, need security audits, performance analysis, or want automated code quality feedback. Supports reviewing staged changes, specific files, entire directories, or git diffs.

16

review-code

catlog22

Multi-dimensional code review with structured reports. Analyzes correctness, readability, performance, security, testing, and architecture. Triggers on "review code", "code review", "审查代码", "代码审查".

22

Search skills

Search the agent skills registry