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.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bloodandeath/keats-code-reviewerWhat This Skill Does
The code-reviewer skill is an adversarial, high-rigor tool for OpenClaw designed to combat code entropy. Unlike standard code assistants that offer polite feedback, this skill adopts a 'guilty until proven exceptional' mindset, ruthlessly vetting code for security vulnerabilities, architectural laziness, performance bottlenecks, and poor idiomatic patterns. It functions as a senior engineer peer-reviewer that prioritizes code integrity above all else. The skill supports two operational modes: a lightning-fast single-model adversarial review for day-to-day tasks, and a --dual cross-model iterative mode for mission-critical codebases that require exhaustive verification. Structured findings are categorized into severity tiers—Blocking, Required Changes, Suggestions, and Noted—ensuring actionable paths for remediation.
Installation
To integrate this skill into your environment, run the following command in your terminal:
clawhub install openclaw/skills/skills/bloodandeath/keats-code-reviewer
Use Cases
This skill is ideal for:
- Enforcing strict security standards in production-level code.
- Conducting PR reviews that require more than just a surface-level glance.
- Identifying subtle concurrency issues or edge-case failures that traditional linters ignore.
- Performing cross-model architectural audits where complex logic necessitates multiple perspectives to ensure total correctness.
Example Prompts
- "Critically review my PR, I need to ensure there are no SQL injection risks or performance bottlenecks in the data access layer."
- "What's wrong with this authentication module? I feel like the session handling is sloppy; please double review this using the --dual mode."
- "Critique my code for this microservice endpoint; I want zero tolerance for technical debt."
Tips & Limitations
- Be Selective with
--dual: Because the dual mode involves cross-model iteration, it increases token usage and latency significantly. Reserve it for complex logic, critical security paths, or architectural refactors. - Constructive Brutality: Remember that the AI's persona is designed to be direct. It will not sugarcoat issues, so prepare to receive feedback that focuses strictly on code quality.
- Human Oversight: While the adversarial review is highly effective, always perform final verification, especially when the skill suggests 'Blocking' changes that may affect build stability.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-bloodandeath-keats-code-reviewer": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read
Related Skills
agent-cost-monitor
Real-time token usage and cost tracking across all your OpenClaw agents — alerts, budgets, and optimization tips
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.
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.
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.
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.