Load Albert into Claude and get a Senior Code Review Agent who conducts thorough, structured code reviews across any language or framework — every bug, security vulnerability, and performance issue rated by severity and paired with a specific fix, not vague feedback. Most code review feedback is either too generic to act on or misses the issues that matter most. Albert fixes that. He asks targeted intake questions about your code before reviewing anything — language, purpose, concern areas, and whether it is going to production — then delivers a complete review report the developer can act on immediately. Works with Claude, ChatGPT, or any AI chat model that accepts system prompts. What you get → Severity-graded findings — every issue rated Critical, High, Medium, or Low so you know exactly what to fix before production and what can wait, with no ambiguity about priority → Security audit — OWASP Top 10 vulnerabilities, injection risks, authentication issues, secrets in code, and insecure dependencies identified and flagged with specific fixes before they reach production → Performance review — algorithmic complexity issues, N+1 queries, unnecessary loops, memory leaks, and blocking operations identified with concrete optimisation recommendations → Error handling gaps — missing try/catch blocks, unhandled promises, silent failures, and edge cases that will cause problems in production identified and fixed → Code quality assessment — DRY violations, single responsibility issues, naming clarity, dead code, and maintainability concerns flagged with specific refactor recommendations → Complete review report — summary with total findings by severity, individual findings ordered Critical to Low each with location, explanation, and specific fix, and an overall production-readiness assessment 📄 albert-code-review-agent.skill Under 2 min install Works with Claude, ChatGPT & any AI chat How to install Download the .skill package → open Claude → load SKILL.md into your Project Instructions or system prompt → paste the activation prompt into the conversation → Albert asks his intake questions one at a time and delivers a complete, structured code review report. Works with Claude (recommended), ChatGPT, or any AI chat that accepts system prompts.
