ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 4/5

code-reviewer

Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Default behavior is a single-model adversarial review that identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Supports an optional `--dual` mode for heavier cross-model iterative review when deeper scrutiny is worth the added cost and latency. Use when users ask to "critically review my code", "critically review" code or a PR, "critique my code", "find issues in my code", "find issues" in code, ask "what's wrong with this code", ask to "review this code", "critique my PR", say "double review this", or request a "cross-model review". Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required Changes, Suggestions, Noted) and specific, actionable recommendations.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/bloodandeath/adversarial-code-reviewer
Or

What This Skill Does

The code-reviewer skill is a high-rigor, adversarial analysis tool designed for professional software engineers who demand absolute excellence. Unlike standard linting or superficial PR reviews, this skill assumes code is guilty of being suboptimal until proven otherwise. It ruthlessly probes for security vulnerabilities, architectural flaws, edge-case failures, and lazy patterns. It covers a vast range of languages including Python, R, JavaScript/TypeScript, SQL, and various front-end frameworks. The tool categorizes findings into four clear severity tiers: Blocking, Required Changes, Suggestions, and Noted, ensuring you know exactly where to focus your refactoring efforts.

Installation

You can integrate this skill into your OpenClaw environment by running the following command in your terminal: clawhub install openclaw/skills/skills/bloodandeath/adversarial-code-reviewer

Use Cases

  • Pre-Commit Review: Running a deep scan on a PR before pushing it to the production branch.
  • Legacy Code Analysis: Using the --dual flag to identify deeply buried bugs in complex, undocumented codebases.
  • Security Hardening: Identifying potential injection, buffer, or logic flaws that standard security scanners might overlook.
  • Code Quality Enforcement: Maintaining a zero-tolerance policy for technical debt in enterprise-level repositories.

Example Prompts

  1. "Critically review my PR on the user authentication module; I need to ensure there are no race conditions."
  2. "Double review this TypeScript file for performance bottlenecks and type safety—use the --dual flag for maximum scrutiny."
  3. "What's wrong with this SQL query? It feels sluggish and I suspect an indexing issue or a Cartesian product error."

Tips & Limitations

  • Default vs. Dual: Use the default mode for quick, day-to-day sanity checks. Reserve the --dual flag for critical architecture, high-stakes security patches, or when you are truly stuck on a persistent bug. Note that --dual incurs higher latency due to the iterative cross-model logic.
  • The Adversarial Mindset: The AI is instructed to be blunt and constructive. It does not provide 'fluff' feedback; it focuses strictly on actionable technical improvements.
  • Human-in-the-Loop: In --dual mode, you act as the final arbiter. The primary model audits the sub-agent’s suggestions—always verify critical changes before implementation to ensure the automated suggestions align with your specific domain context.

Metadata

Stars4190
Views0
Updated2026-04-18
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-bloodandeath-adversarial-code-reviewer": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#code-review#adversarial#pr-analysis#security#developer-tools
Safety Score: 4/5

Flags: file-read, code-execution

Related Skills

design-engineering

Orchestrate iterative design and frontend engineering work through research, planning, sub-agent execution, and validation loops. Use when a visual/UI task requires multiple iterations, when the first implementation needs refinement based on feedback, when choosing between competing technical approaches (Canvas vs SVG vs CSS), or when coordinating sub-agents on design-heavy work. Covers animation architecture decisions, progressive enhancement patterns, performance-aware rendering choices, and the research→plan→execute→validate workflow. Complements frontend-design (which handles aesthetics) by adding engineering discipline, iteration management, and technical decision-making.

bloodandeath 4190

agent-cost-monitor

Real-time token usage and cost tracking across all your OpenClaw agents — alerts, budgets, and optimization tips

bloodandeath 4190

web-monitor

Monitor web pages for content changes and get alerts. Track URLs, detect updates, view diffs. Use when asked to watch a website, track changes on a page, monitor for new posts/content, set up page change alerts, or check if a site has been updated. Supports CSS selectors for targeted monitoring.

bloodandeath 4190

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

bloodandeath 4190

code-reviewer

Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Default behavior is a single-model adversarial review that identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Supports an optional `--dual` mode for heavier cross-model iterative review when deeper scrutiny is worth the added cost and latency. Use when users ask to "critically review my code", "critically review" code or a PR, "critique my code", "find issues in my code", "find issues" in code, ask "what's wrong with this code", ask to "review this code", "critique my PR", say "double review this", or request a "cross-model review". Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required Changes, Suggestions, Noted) and specific, actionable recommendations.

bloodandeath 4190