mcpField
C
conversational-ai-flow

conversational-ai-flow

github.com/dengineproblem设计与 UI89 次安装
代码仓库

关于 conversational-ai-flow

用于设计和实现对话式 AI 流程的技能，面向构建聊天机器人的从业者。内容涵盖状态管理、意图路由、槽位填充、错误恢复、回复生成及流程指标。

主要功能

  1. 01对话状态与流程位置管理
  2. 02基于意图的流程路由
  3. 03槽位填充与验证
  4. 04误解后的恢复策略
  5. 05上下文与多模态回复
  6. 06完成率与回退指标

适用场景

  1. 01设计预约对话流程
  2. 02处理对话中的信息缺失
  3. 03应对多次误解后的恢复
  4. 04监控完成率与中途退出

安装

复制下面的命令，在终端中运行。

$npx skills add https://github.com/dengineproblem/agents-monorepo --skill conversational-ai-flow

安装后在 Claude Code 中输入/conversational-ai-flow确认已加载。

详细介绍

对话式 AI 工作流专家

专注于对话式 AI 工作流的设计与实现。

核心设计原则

状态管理
class ConversationState:
    def __init__(self):
        self.current_intent = None
        self.entities = {}
        self.conversation_history = []
        self.flow_position = "start"
        self.confidence_threshold = 0.7

    def update_context(self, user_input, intent, entities):
        self.conversation_history.append({
            "user_input": user_input,
            "intent": intent,
            "entities": entities
        })
        self.entities.update(entities)
        self.current_intent = intent

工作流架构模式

基于意图的路由
flows:
  booking_flow:
    entry_conditions:
      - intent: "book_appointment"
    steps:
      - name: "collect_datetime"
        prompt: "When would you like to schedule?"
        validation: "datetime_validator"
      - name: "confirm_booking"
        prompt: "Confirm booking on {datetime}?"
        actions: ["create_booking", "send_confirmation"]

  fallback_flow:
    triggers: ["low_confidence", "unknown_intent"]
    strategy: "clarification_questions"
槽位填充模式
def slot_filling_handler(state, required_slots):
    missing_slots = [s for s in required_slots if s not in state.entities]

    if missing_slots:
        return generate_slot_prompt(missing_slots[0], state)

    return proceed_to_next_step(state)

错误处理与恢复

渐进式展开
class ErrorRecovery:
    def handle_misunderstanding(self, state, attempt_count):
        strategies = {
            1: "I didn't quite catch that. Could you rephrase?",
            2: "Let me try differently. Are you looking to: [options]?",
            3: "Let me connect you with a human agent."
        }
        return strategies.get(attempt_count, strategies[3])

响应生成

情境化模板
class ResponseGenerator:
    templates = {
        "confirmation": [
            "Got it! {summary}. Is that correct?",
            "Let me confirm: {summary}. Does this look right?"
        ],
        "progress": [
            "Great! We've got {completed}. Next, {next_step}.",
            "Perfect! Just need {remaining} and we're done."
        ]
    }

多模态响应

{
  "response_type": "rich",
  "text": "Here are your options:",
  "components": [
    {
      "type": "quick_replies",
      "options": [
        {"title": "Schedule Appointment", "payload": "intent:book"},
        {"title": "Check Status", "payload": "intent:status"}
      ]
    }
  ]
}

分析与优化

def track_flow_metrics(conversation_id, metrics):
    return {
        "completion_rate": metrics.completed / metrics.started,
        "average_turns": metrics.total_turns / metrics.conversations,
        "fallback_rate": metrics.fallbacks / metrics.total_turns,
        "abandonment_points": identify_drop_off_points(conversation_id)
    }

最佳实践

  • 明确机器人的个性和语气
  • 预判用户需求
  • 为较长的对话使用摘要
  • 测试所有路径和边界情况
  • 监控真实对话，以便改进

评论

支持 Markdown