Skip to content

northseadl/norix-skills / llm-agent-dev

llm-agent-dev

Unverified

LLM Agent engineering: pattern selection (12-mode matrix), data simulation, convergence iteration. Covers intent routing, function calling, ReAct, MCP, prompt chaining, guardrails, evaluation.

FileKindSize
SKILL.mdskill md17.6 KB
agents/openai.yamlconfig198 B
evals/evals.jsonconfig4.7 KB
references/convergence/iteration-protocol.mdmarkdown8.0 KB
references/eval-loop.mdmarkdown9.4 KB
references/feedback-protocol.mdmarkdown6.0 KB
references/intent-patterns.mdmarkdown5.8 KB
references/paradigms/context-engineering.mdmarkdown6.0 KB
references/paradigms/decision-tree.mdmarkdown2.7 KB
references/paradigms/memory-architecture.mdmarkdown4.0 KB
references/paradigms/observability.mdmarkdown4.5 KB
references/paradigms/pattern-matrix.mdmarkdown3.3 KB
references/paradigms/performance-benchmarking.mdmarkdown15.2 KB
references/paradigms/prompt-patterns.mdmarkdown5.0 KB
references/paradigms/safety-guardrails.mdmarkdown5.5 KB
references/paradigms/tool-design.mdmarkdown2.5 KB
references/patterns/01-crex-rule-router.mdmarkdown6.8 KB
references/patterns/02-slot-filling.mdmarkdown7.1 KB
references/patterns/03-function-calling.mdmarkdown3.9 KB
references/patterns/04-workflow-agent.mdmarkdown5.0 KB
references/patterns/05-react-agent.mdmarkdown3.4 KB
references/patterns/06-router-expert.mdmarkdown3.2 KB
references/patterns/07-mcp-tool-protocol.mdmarkdown5.0 KB
references/patterns/08-handoff-delegation.mdmarkdown4.7 KB
references/patterns/09-prompt-chaining.mdmarkdown3.0 KB
references/patterns/10-parallelizing.mdmarkdown3.2 KB
references/patterns/11-orchestrator-worker.mdmarkdown4.8 KB
references/patterns/12-evaluator-optimizer.mdmarkdown5.5 KB
references/scenarios/coding-assistant.mdmarkdown2.0 KB
references/scenarios/content-generation.mdmarkdown2.7 KB
references/scenarios/customer-service.mdmarkdown2.6 KB
references/scenarios/ecommerce-shopping.mdmarkdown4.2 KB
references/scenarios/food-ordering.mdmarkdown3.1 KB
references/scenarios/knowledge-qa.mdmarkdown2.6 KB
references/simulation/data-generation.mdmarkdown8.1 KB
references/skill-templates.mdmarkdown8.0 KB

references/scenarios/customer-service.md

View on GitHub
# 场景蓝图: 智能客服 Agent

> 从简单 FAQ 到复杂投诉处理的全层级客服架构
> 覆盖: 售前咨询、售后支持、投诉升级、情感安抚

## 渐进式升级架构

```
用户输入
   │
   ▼
[Tier 1: CREX 即时响应] ← 80% 问题在此解决
   │ 处理不了
   ▼
[Tier 2: FC + Slot 专业处理] ← 15% 问题
   │ 处理不了
   ▼
[Tier 3: ReAct 深度分析] ← 4% 问题
   │ 处理不了 / 负面情绪 / 投诉
   ▼
[Tier 4: Handoff 人工客服] ← 1% 问题
```

## 各层级模式选型

### Tier 1: CREX (80% 覆盖率)

| 意图 | 处理方式 | 延迟 |
|------|---------|------|
| 营业时间/地址 | 静态知识库查询 | < 200ms |
| 退换货政策 | FAQ 模板回复 | < 200ms |
| 订单查询 | API 调用 | < 500ms |
| 物流追踪 | API 调用 | < 500ms |
| 常见操作指引 | 预设步骤引导 | < 200ms |

### Tier 2: FC + Slot (15% 覆盖率)

| 意图 | 处理方式 | 延迟 |
|------|---------|------|
| 退款申请 | Slot 收集信息 → Workflow 审批 | 1-3s/轮 |
| 地址修改 | Slot 收集新地址 → API 更新 | 1-2s |
| 商品对比咨询 | FC 查询多商品 → LLM 对比 | 2-3s |
| 个性化推荐 | FC 查用户画像 → 推荐引擎 | 1-2s |

### Tier 3: ReAct (4% 覆盖率)

| 意图 | 处理方式 | 延迟 |
|------|---------|------|
| 复杂问题排查 | 多步推理 + 多工具调用 | 5-15s |
| 跨系统问题 | 查询多个系统汇总 | 5-10s |
| 个性化方案 | 分析用户历史 → 定制方案 | 5-10s |

### Tier 4: Handoff (1% 覆盖率)

自动升级触发条件:
- 意图置信度 < 0.4
- 检测到负面情绪 (愤怒/失望)
- 连续 3 次未成功解决
- 用户主动要求人工
- 涉及退款金额 > 阈值
- 法律/合规相关问题

## 情感感知

```typescript
interface SentimentGuardrail {
  async check(input: string, context: AgentContext): Promise<SentimentResult> {
    const sentiment = await llm.classify(input, ['positive', 'neutral', 'negative', 'angry']);

    if (sentiment === 'angry') {
      // 切换到安抚话术 + 高优先级 Handoff
      return { action: 'escalate', priority: 'urgent', tone: 'empathetic' };
    }
    if (sentiment === 'negative') {
      // 调整回复语气为更同理心
      return { action: 'adjust_tone', tone: 'empathetic' };
    }
    return { action: 'continue' };
  }
}
```

## MCP 工具集

```
客户 MCP → get_profile, get_order_history, get_preferences
订单 MCP → query_order, modify_order, cancel_order
物流 MCP → track_delivery, estimate_arrival
售后 MCP → create_ticket, check_warranty, process_refund
知识 MCP → search_faq, search_policies, search_articles
```
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall