code-runner-2通过PTY调用Claude Code执行代码生成、审查、重构、调试及CI/CD集成，支持非TTY环境下的自动化编程任务。
Install via ClawdBot CLI:
clawdbot install thcjp/code-runner-2Grade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawhub.ai/user/thcjpAudited Sep 5, 2026 · audit v1.0
Generated Sep 5, 2026
Development teams can use the skill to automatically review codebases for bugs, security issues, and improvements. This reduces manual review time and helps maintain high code quality across projects.
When modernizing legacy systems, the skill can automate the refactoring process, such as converting raw SQL to an ORM. This lowers the risk of errors and speeds up the modernization effort.
Startups and product teams can quickly add new features, like REST endpoints, with the help of the skill. It generates code, includes validation, and even writes unit tests, accelerating development cycles.
In production environments, the skill can be invoked to fix specific bugs, such as memory leaks in WebSocket handlers. This reduces downtime and improves system stability.
The skill can be integrated into CI/CD pipelines to automate code analysis, test generation, and deployment tasks. This ensures consistent quality checks and faster release cycles.
Offer the skill as part of a subscription-based developer tool that enhances coding efficiency and code quality. Subscribers get automated code review, refactoring, and debugging capabilities.
Package the skill with consulting services to help enterprises integrate automation into their development workflows. Consulting fee covers setup, customization, and training.
Provide a free basic version of the skill with limited features, and charge for advanced features like static analysis, batch review, and CI/CD integration. Attract users at scale and convert to paid plans.
💬 Integration Tip
Ensure your environment supports PTY and install Claude Code separately. Start with simple prompts, then gradually incorporate into CI/CD pipelines.
Scored Sep 5, 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.
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.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.