cfn-intervention-system
关于
The cfn-intervention-system skill detects when automated CFN Loop processes require human oversight and orchestrates intervention workflows. It manages escalation paths and approval gates for human-in-the-loop scenarios. This consolidated mega-skill combines detection and orchestration capabilities for complete intervention management.
快速安装
Claude Code
推荐npx skills add mattnigh/skills_collection -a claude-code/plugin add https://github.com/mattnigh/skills_collectiongit clone https://github.com/mattnigh/skills_collection.git ~/.claude/skills/cfn-intervention-system在 Claude Code 中复制并粘贴此命令以安装该技能
GitHub 仓库
Frequently asked questions
What is the cfn-intervention-system skill?
cfn-intervention-system is a Claude Skill by mattnigh. Skills package instructions and resources that Claude loads on demand, so Claude can perform cfn-intervention-system-related tasks without extra prompting.
How do I install cfn-intervention-system?
Use the install commands on this page: add cfn-intervention-system to Claude Code as a plugin, or clone its repository into your skills directory, then restart Claude so it picks up the skill.
What category does cfn-intervention-system belong to?
cfn-intervention-system is in the Design category, tagged mega-skill, intervention, human-in-the-loop and escalation.
Is cfn-intervention-system free to use?
Yes. cfn-intervention-system is listed on AIMCP and free to install. It runs inside Claude, so no separate service account is required to use the skill itself.
相关推荐技能
该Skill用于当开发者提供完整实施计划时，以受控批次方式执行代码实现。它会先审阅计划并提出疑问，然后分批次执行任务（默认每批3个任务），并在批次间暂停等待审查。关键特性包括分批次执行、内置检查点和架构师审查机制，确保复杂系统实现的可控性。
该Skill可在完成任务、实现主要功能或合并代码前自动调度代码审查子代理，确保实现符合需求和计划。它支持通过指定git SHA范围进行精准的代码变更审查，帮助开发者在关键节点及时发现潜在问题。核心原则是"早审查、勤审查"，适用于开发流程的各个关键阶段。
这个Skill指导开发者如何将MCP服务器连接到Claude Code，支持HTTP、stdio和SSE三种传输协议。它涵盖了从安装配置到认证安全的完整流程，适用于集成GitHub、Notion、数据库等外部服务。当开发者需要添加集成、配置外部工具或提及MCP相关功能时，这个Skill能提供实用的操作指南。
该Skill帮助开发者根据任务特性选择Claude Code的Web或CLI界面，并指导如何在两种环境间无缝迁移会话。它能分析任务复杂度、迭代需求等要素，推荐最优工作界面和工作流。关键特性包括会话状态管理、环境切换指导和上下文优化建议。