Albert - AI 程式碼審查代理
數位 AI agent 一個 agent .md 檔案albert-ai-code-review-agent.skill
Choose how to get it
Start All-Access, from $8.25/mo$99 a year, or $19 a month. 14-day refund on the first charge.
// all-access
You do not download skills. Your AI fetches them.
The KissMySkills connector is a small server your AI chat talks to. Add it once to Claude, ChatGPT, Claude Code or Cursor. From then on, any of our 1,000+ skills is one sentence away.
- 01Add the connector. Settings, Connectors, paste one link. A minute.
- 02Sign in once. The email from your subscription. Nothing installs.
- 03Ask for a skill. "Load Albert." It arrives in the conversation and your AI answers as that specialist.
Every skill, prompt pack and agent, new releases included. Single files can still be bought and kept. Cancel any time from your account. Compare plans
Secure checkout by Shopify
Add it once. Your AI works like a specialist.
將其加入 Claude、ChatGPT 或 Gemini - 您的 AI 將從頭到尾完成整項工作。
立即下載 · 30 天退款保證。 一次付費,永久使用 - 無需訂閱。由我們撰寫並測試,絕非從 GitHub 抓取。 退款政策
Ask Albert something hard.
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
你不需要閱讀。由你的 AI 代勞。
只需將技能檔案新增至 Claude、ChatGPT 或 Gemini 一次。從那之後,它就會以這個領域的專家身分運作,並從下一則訊息開始以 Albert 的身分回答。
購買一次,檔案便永久歸您所有。或者訂閱 All-Access,讓 KissMySkills 連接器在您提出要求時,將該檔案及其他所有技能載入您的聊天中。
// what's inside
這項技能包含什麼
- Severity-graded findings: Critical, High, Medium, Low - no ambiguity on priority
- Security audit: OWASP Top 10, injection, auth, secrets, insecure deps
- Performance review: complexity, N+1 queries, memory leaks, blocking ops
- Error-handling gaps: unhandled promises, silent failures, edge cases
- Complete report with a production-readiness assessment
For developers, tech leads & engineering managers
A senior reviewer's hour runs $150+ - this reviews any codebase on demand.
What you're actually buying
將 Albert 載入 Claude,取得一名資深程式碼審查 Agent,針對任何語言或框架進行徹底、結構化的程式碼審查 - 每個錯誤、安全漏洞與效能問題都會依嚴重程度評級,並搭配具體修正方法,而非含糊的意見。
大多數程式碼審查意見要麼過於籠統、難以採取行動,要麼忽略最重要的問題。Albert 能解決這些問題。他會在審查任何內容前,針對您的程式碼提出精準的初步了解問題 - 使用的語言、用途、關注領域,以及是否要部署至生產環境 - 然後提供開發人員可立即採取行動的完整審查報告。適用於 Claude、ChatGPT,或任何接受系統提示的 AI 聊天模型。
您將獲得
- → 依嚴重程度分級的發現 - 每項問題皆評為 Critical、High、Medium 或 Low,讓您確切知道上線前必須修正哪些問題、哪些可以稍後處理,優先順序毫不含糊
- → 安全性稽核 - 找出並標示 OWASP Top 10 漏洞、注入風險、驗證問題、程式碼中的機密資訊與不安全相依套件,並在上線前提供具體修正方法
- → 效能審查 - 找出演算法複雜度問題、N+1 查詢、不必要的迴圈、記憶體洩漏與阻塞作業,並提供具體的最佳化建議
- → 錯誤處理缺口 - 找出並修正缺少 try/catch 區塊、未處理的 promises、無聲失敗,以及會在生產環境造成問題的邊界情況
- → 程式碼品質評估 - 標示 DRY 違反、單一職責問題、命名清晰度、無效程式碼與可維護性疑慮,並提供具體重構建議
- → 完整審查報告 - 提供依嚴重程度統計的發現總結、按 Critical 至 Low 排序的個別發現,每項包含位置、說明與具體修正方法,以及整體生產環境就緒度評估
如何安裝
下載 .skill 套件 → 開啟 Claude → 將 SKILL.md 載入您的 Project Instructions 或系統提示 → 將啟用 prompt 貼到對話中 → Albert 會一次提出一個初步了解問題,並提供完整、結構化的程式碼審查報告。適用於 Claude(推薦)、ChatGPT,或任何接受系統提示的 AI 聊天工具。
# Albert - AI Code Review Agent You are Albert, a senior code reviewer. Constructive, specific, no ego - every comment has a reason and an example. ## What you do - Bug, security (OWASP), and performance review - Architecture and readability feedback - Test-gap analysis ## How you work 1. Read the diff and the intent 2. Rate every comment blocker / nit / suggestion 3. Give a before/after for each recommendation
您將下載的實際檔案範例。
四個步驟。任何 AI 聊天。
- 01下載檔案
結帳後,下載連結會寄到您的收件匣。將檔案儲存至裝置上的任意位置。
- 02開啟你的 AI 聊天功能
Claude、ChatGPT、Gemini、Grok 或 Copilot - 無論你目前使用哪一個。
- 03貼上檔案內容
將其放入系統 prompt、專案指示或自訂指示欄位中。
- 04開始工作
您的 AI 現已設定為專業助手。您可以詢問它任何與其專業領域相關的問題。
不需要技術知識。不需訂閱。一次付費,永久使用。
支援所有主要的 AI 聊天服務。
將檔案放入您的 AI system prompt、專案指示或自訂指示中。無需設定。無需程式碼。不受供應商綁定。
關於此產品的問題
What does Albert find in a code review?+
Albert conducts thorough, structured code reviews across any language or framework — every bug, security vulnerability, and performance issue raised with specific line references, severity ratings, and recommended fixes.
How do I use Albert for code review?+
Load the .md into Claude Projects, paste the activation prompt. Albert asks for the code to review, the language and framework, and the review focus — then produces a structured report with every issue categorised by severity and fix priority.
Which AI tools does Albert work with?+
Works with Claude (recommended), ChatGPT, and any AI chat accepting system prompts. Claude is strongly recommended for Albert — thorough code review requires Claude's long-context reasoning and code analysis capability.
Does Albert review for security issues specifically?+
Yes. Albert specifically checks for security vulnerabilities — injection risks, authentication gaps, insecure dependencies, and data exposure — alongside bugs and performance issues. Security findings are flagged at high severity.
What is included in the download?+
Two files: the Albert .md agent file and the activation prompt .txt. Paste the activation prompt after loading the skill and Albert starts the code review intake immediately.
Do I have to read it myself?+
No. The file is written for your AI to read, not for you. Upload it or paste it in once and the AI takes on the role. After that you just ask it questions the way you normally would. You're welcome to open it and read it, but nothing here depends on you doing that.
Is this a physical book?+
No, it's digital. You download it the moment the order goes through and it's yours permanently. The cover is styled like a book because each edition is written and edited as one self-contained piece of work. The reading part is your AI's job, not yours.
準備好讓您的 AI 專精了嗎?
一個即插即用的檔案。一次付費,永久保留 - 適用於 Claude 和 ChatGPT。