open-code-reviewScan AI-generated code for hallucinated packages, stale APIs, security anti-patterns, and over-engineering. Use when: (1) reviewing PRs with AI-generated cod...
Install via ClawdBot CLI:
clawdbot install raye-deng/open-code-reviewGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/raye-deng/open-code-reviewAudited Apr 17, 2026 · audit v1.0
Generated Mar 22, 2026
During pull request reviews in a fintech company, developers use AI tools like GitHub Copilot to generate code for new features. This skill scans the AI-generated code for hallucinated packages and security anti-patterns, such as hardcoded secrets, ensuring compliance with strict regulatory standards before merging.
An e-commerce platform integrates this skill into its CI/CD pipeline to run L1 structural analysis on AI-generated code from tools like Cursor. It catches stale APIs and context breaks in JavaScript and TypeScript, preventing production failures that traditional linters might miss during pre-merge checks.
A SaaS company evaluates third-party AI-generated code from vendors before integration. Using the L2 scan level with embedding recall, it detects hallucinated packages and over-engineering in Python and Go, ensuring code quality and reducing maintenance costs in cloud-based applications.
Healthcare software teams employ AI assistants like Claude for rapid prototyping. This skill scans the generated code for security anti-patterns, such as deprecated crypto in Java, and uses diff mode in CI/CD to flag issues early, maintaining patient data security and compliance with HIPAA regulations.
A gaming studio conducts periodic audits of its codebase, which includes AI-generated scripts from GPT. The skill performs L3 deep scans to identify over-engineering and context breaks in Kotlin and JavaScript, optimizing performance and reducing technical debt in game development pipelines.
Offers a free tier for individual developers with basic L1 scans, while charging teams for advanced features like L2/L3 scans, SARIF output, and priority support. Revenue is generated through monthly subscriptions based on scan volume and team size, targeting small to medium enterprises.
Provides custom licenses for large organizations, including on-premise deployment, dedicated support, and integration with existing tools like SonarQube. Revenue comes from annual contracts with tiered pricing based on the number of repositories and advanced scan capabilities.
Distributes the skill through platforms like Smithery and Cursor Directory, earning revenue via marketplace commissions or referral fees. Partners with AI tool vendors to bundle the scanner, generating income from joint sales and co-marketing efforts in developer ecosystems.
💬 Integration Tip
Start with the L1 scan in CI/CD for quick feedback, then upgrade to L2 for deeper analysis as needed; use the GitHub Action for seamless integration into existing workflows.
Scored Jun 19, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.