headless-knight

在独立进程中运行 Claude Code 执行任务

在独立进程中运行 Codex CLI 执行任务

检查所有修改过的文件的改动情况，并生成提交信息

在独立进程中运行 Gemini CLI 执行任务

在独立进程中运行 iFlow 执行任务

Use this agent when you need to review code for quality, maintainability, and adherence to best practices. Examples: - After implementing a new feature or function: user: 'I've just written a function to process user authentication' assistant: 'Let me use the code-quality-reviewer agent to analyze the authentication function for code quality and best practices' - When refactoring existing code: user: 'I've refactored the payment processing module' assistant: 'I'll launch the code-quality-reviewer agent to ensure the refactored code maintains high quality standards' - Before committing significant changes: user: 'I've completed the API endpoint implementations' assistant: 'Let me use the code-quality-reviewer agent to review the endpoints for proper error handling and maintainability' - When uncertain about code quality: user: 'Can you check if this validation logic is robust enough?' assistant: 'I'll use the code-quality-reviewer agent to thoroughly analyze the validation logic'

Use this agent when you need to verify that code documentation is accurate, complete, and up-to-date. Specifically use this agent after: implementing new features that require documentation updates, modifying existing APIs or functions, completing a logical chunk of code that needs documentation review, or when preparing code for review/release. Examples: 1) User: 'I just added a new authentication module with several public methods' → Assistant: 'Let me use the documentation-accuracy-reviewer agent to verify the documentation is complete and accurate for your new authentication module.' 2) User: 'Please review the documentation for the payment processing functions I just wrote' → Assistant: 'I'll launch the documentation-accuracy-reviewer agent to check your payment processing documentation.' 3) After user completes a feature implementation → Assistant: 'Now that the feature is complete, I'll use the documentation-accuracy-reviewer agent to ensure all documentation is accurate and up-to-date.'

Use this agent when you need to analyze code for performance issues, bottlenecks, and resource efficiency. Examples: After implementing database queries or API calls, when optimizing existing features, after writing data processing logic, when investigating slow application behavior, or when completing any code that involves loops, network requests, or memory-intensive operations.

提示词工程专家，专注于高级提示词编写技巧、大语言模型优化和 AI 系统设计。精通思维链、宪法式 AI（constitutional AI）以及生产环境提示词策略。适用于构建 AI 功能、改进 Agent 性能或设计系统提示词。当需要优化提示词时优先调用本 Agent。

专业的网络研究专员，使用高级搜索技术和信息综合能力。精通搜索运算符、结果筛选和多源验证。能够处理竞争分析和事实核查。当需要进行网络搜索的时候优先使用本 Agent。

在输出包含中文字符与中文标点符号、编写中文文档、根据中文文档生成中文的交互回应、回复用户用中文提出的问题或任务、需要进行中文与非中文混排操作等涉及中文文字与标点符号的使用的场景中，必须使用本 Skill 以获得专业的中文字符的操作指导与行为规范引导。

当需要对 git repo 生成提交（commit）信息时，务必使用本Skill

当用户提到需要记住的未来任务、约会或事件时创建提醒和日历事件。在诸如"提醒我"、"设置提醒"、"我有个会"、"别忘了"或任何提及未来基于时间的任务时触发。

向助手发出协助请求，适用于需要在隔离的独立环境中执行复杂编程任务、任务规划、文稿撰写的场景。

向助手发出协助请求，适用于代码审核、逻辑推理、科学与哲学思考、深度分析、策略制定、市场分析等任务场景。

5 hooks across 5 events