refactor-safelyPlans and executes safe refactors with small steps, tests, and rollback strategy. Use when 重构, 技术债, 安全重构, refactoring, or improving code structure without br...
Install via ClawdBot CLI:
clawdbot install wangzhiming1999/refactor-safelyGrade 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/wangzhiming1999/oliver-skill/issuesAudited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
A bank needs to refactor a monolithic transaction processing system to improve maintainability and reduce technical debt, ensuring compliance and zero downtime during the update. The AI agent applies small, tested steps to extract reusable functions and standardize error handling without altering transaction outcomes or audit trails.
An online retailer aims to refactor product catalog and checkout modules to enhance code structure and speed, addressing duplicate logic and unclear responsibilities. The agent plans safe refactors by first adding critical path tests, then incrementally restructuring components to maintain user experience and prevent checkout failures.
A healthcare provider updates patient data management code to meet new regulations, requiring refactoring for better clarity and test coverage while preserving data integrity and privacy. The agent executes step-by-step changes, such as renaming variables and extracting components, with rollback strategies to avoid service disruptions.
A software-as-a-service company refactors core modules to support new features, reducing technical debt and improving scalability. The agent identifies dependencies, breaks changes into small commits like moving functions and replacing implementations, ensuring existing APIs remain stable for current customers.
Offer specialized refactoring consulting to enterprises, providing expert guidance on safe code improvements and technical debt reduction. Revenue is generated through project-based fees or retainer contracts, leveraging the agent's structured approach to ensure client satisfaction and reduced risk.
Integrate the refactoring skill into existing development platforms or IDEs as a premium feature, helping teams automate safe refactors. Revenue comes from subscription tiers based on usage or team size, with upsells for advanced analytics and compliance reporting.
Provide training programs and certifications on safe refactoring practices, using the agent's principles to educate developers. Revenue is earned through course fees, certification exams, and corporate training packages, targeting organizations aiming to upskill their engineering teams.
💬 Integration Tip
Integrate with version control systems like Git to automate commit tracking and rollback, and pair with testing frameworks to validate each step before deployment.
Scored May 20, 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.