code-review-ProMax

    1

    Multi-dimensional code review: requirement coverage, regression risk, edge cases, upstream impact. Structured report plus guided fix mode.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    code-review-ProMax

    Example session with this skill installed

    Review my changes / check this code for issues.

    • Read your context and instructions
    • Compiled the code-review-promax

    A structured review report covering requirement coverage, regression risk, and edge cases, with optional step-by-step fixes.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    A multi-dimensional code review skill for AI coding agents. Reviews changes for requirement completion, regression risk, edge cases, and upstream/downstream impact. Outputs a structured report with fix instructions, and auto-switches to fix mode to apply fixes one by one when the user asks to fix. Works with Claude Code, Cursor, OpenClaw, Codex and any agent that reads SKILL.md.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Code Quality & Review.

    Restricted to diff/PR/commit analysis. Large changes (>500 lines) focused on core logic only. Requires Git/GitHub/GitLab access for remote reviews.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 14 days ago

    • Free with an Agensi account

    Software
    Git

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Listed14 days ago

    What's inside

    Frequently Asked Questions

    code-review-ProMax is designed to move beyond basic syntax checking by identifying deep architectural risks, thread safety issues, and potential regressions that generic prompts often miss. It focuses on the 'chain of impact,' ensuring that a change in one module doesn't silently break a downstream dependency.

    The skill is compatible with AI agents that support Git CLI, GitHub CLI, or GitLab API integrations. It is optimized for use within developer-focused agent environments where it can access repository diffs and issue structured reporting blocks.

    While it is language-agnostic regarding logic and patterns, it excels in web-focused environments where it can perform specialized SEO audits and security checks for JavaScript injection or cloaking. For non-web languages, it focuses primarily on functional correctness and architectural integrity.

    To maintain high analysis quality, diffs exceeding 500 lines are automatically switched to a high-level review mode focusing on public interfaces and core logic. For larger PRs, we recommend breaking changes into smaller, logical commits to ensure the agent catches every granular detail.

    Beyond identifying bugs, the skill generates a dedicated 'Code Review 修复任务' (Fix Task) block. This provides ready-to-use code instructions that can be passed to a code-execution agent to automate the patching process immediately.

    Your purchase includes the full skill manifest, configuration instructions for Git/GitHub/GitLab integrations, and lifetime access to version updates as we refine its 'intent inference' and risk-prioritization algorithms.

    New in Code Quality & Review

    Free