Communitygithub.com

AI 工程師

建構生產級 LLM 應用程式、進階 RAG 系統與智慧型代理。實作向量搜尋、多模態 AI、代理編排及企業級 AI 整合。主動用於 LLM 功能、聊天機器人、AI 代理或 AI 驅動的應用程式。

AI 工程師 是什麼?

此技能為 AI 工程師提供一個全面的決策框架,用於建構生產級的 LLM 應用程式,從簡單的聊天機器人到複雜的多代理系統。它涵蓋了 RAG 架構、向量資料庫、提示管理與企業級 AI 部署。該技能包含詳細的決策樹,用於選擇 RAG 元件、模型路由策略以及在代理與 RAG 架構之間做出選擇。它還定義了關鍵的故障模式,例如語意不匹配、上下文窗口溢出與工具幻覺循環,並針對這些問題提供具體的檢測規則與解決方案。透過真實世界的範例(如客戶支援聊天機器人)與品質閘道,此技能可確保系統在準確性、延遲、成本與使用者滿意度之間取得平衡。

相容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/curiositech/windags-skills/tree/HEAD/skills/ai-engineer

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

AI 工程師 是做什麼的?

專家級生產級 LLM 應用程式建構,從簡單聊天機器人到複雜多代理系統。專精於 RAG 架構、向量資料庫、提示管理與企業級 AI 部署。

決策點

RAG 元件選擇

查詢類型評估:
├── 簡單常見問題/知識查詢
│   ├── 文件數 < 1000 → Chroma + text-embedding-3-small
│   └── 文件數 > 1000 → Pinecone + text-embedding-3-large
├── 技術/程式碼文件  
│   ├── 預算有限 → bge-large + pgvector
│   └── 效能優先 → voyage-2 + Weaviate
└── 對話式/多輪
    ├── 需要記憶 → 代理模式 + 上下文管理
    └── 無狀態 → 標準 RAG 管線

重新排序決策:
├── 精準度關鍵(法律、醫療)→ 一律使用 Cohere Rerank
├── 延遲 < 200ms → 跳過重新排序,調整檢索
├── 預算有限 → 交叉編碼器(bge-reranker-large)
└── 預設 → Cohere Rerank 搭配 top-10 → top-3

資料庫選擇:
├── 現有 PostgreSQL → pgvector 擴充功能
├── 需要混合搜尋 → Weaviate 或 Qdrant
├── 託管服務 → Pinecone
└── 自託管/本機 → Chroma 或 Qdrant

模型路由策略

複雜度評估:
├── 僅關鍵字(常見問題)→ Claude Haiku
├── 單一文件參考 → Claude Sonnet  
├── 多文件整合 → Claude Opus
└── 程式碼生成 → Claude Sonnet 搭配工具

Token 預算檢查:
├── < 1K tokens → 任何模型
├── 1K-4K tokens → Sonnet/GPT-4
├── 4K-32K tokens → Claude Opus
└── > 32K tokens → 先分塊再摘要

代理 vs RAG 決策

工作分類:
├── 靜態知識查詢 → 純 RAG
├── 需要外部 API → 代理搭配工具
├── 多步驟推理 → 代理搭配規劃
├── 需要即時資料 → 代理搭配即時工具
└── 簡單問答 → RAG 並回退至代理

故障模式

語意不匹配串聯

症狀:檢索精準度高但答案相關性差,使用者反映「很接近但不完全正確」 檢測規則:若語意相似度 > 0.8 但使用者滿意度 < 60% 根本原因:查詢與文件嵌入向量針對不同語意空間進行最佳化 修正:切換至領域專用嵌入模型或實作含同義詞的查詢擴充

上下文窗口溢位

症狀:回應變得籠統,模型忽略特定檢索上下文,回答不一致 檢測規則:若上下文利用率 < 30% 且回應一般性分數 > 0.7 根本原因:過多不相關的區塊稀釋了相關資訊 修正:實作更嚴格的相關性閾值(>0.8)與動態上下文選擇

工具幻覺循環

症狀:代理虛構 API 呼叫、參考不存在的函式、無限重試迴圈 檢測規則:若工具呼叫成功率 < 50% 或迭代次數 > max_iterations * 0.8 根本原因:模型訓練時使用的工具架構與實作不符 修正:在代理系統提示中增加工具驗證層與明確的錯誤處理

嵌入漂移退化

症狀:檢索品質隨時間逐漸下降,季節性效能衰退 檢測規則:若月平均 retrieval@5 低於基線 10% 以上 根本原因:領域語言演進但嵌入模型維持不變 修正:實作嵌入模型重新訓練管線或切換至自適應嵌入

回應延遲潛增

症狀:P95 延遲逐漸增加,使用者抱怨回應緩慢 檢測規則:若連續 7 天的 P95 回應時間 > 基線 2 倍 根本原因:向量索引效能衰退、上下文大小膨脹或模型端點飽和 修正:實作索引最佳化排程、上下文修剪與多模型負載平衡

實戰範例

範例:客戶支援聊天機器人實作

初始需求:「建立一個能回答關於我們 500 頁產品文件問題的聊天機器人」

步驟 1:架構決策

  • 文件數量:500 頁 → 使用 Pinecone 以獲得可擴展性
  • 查詢類型:混合常見問題 + 故障排除 → 需要混合搜尋
  • 延遲要求:< 3 秒 → 包含重新排序但進行最佳化

步驟 2:實作逐步解說

// 新手方式 - 會使用基本的相似度搜尋
const chunks = await vectorDb.query(queryEmbedding, { topK: 5 });

// 專家方式 - 考慮相關性閾值
const rawChunks = await vectorDb.query(queryEmbedding, { 
  topK: 20, 
  threshold: 0.7  // 確保最低相關性
});

// 專家加入新手會跳過的重新排序步驟
const reranked = await reranker.rank(query, rawChunks);
const finalChunks = reranked.slice(0, 3);

// 專家包含回退處理
if (finalChunks.length === 0) {
  return await fallbackToGeneralSupport(query);
}

步驟 3:效能最佳化發現

  • 初始 P95 延遲:4.2 秒(超過要求)
  • 分析:60% 的時間花在重新排序
  • 權衡決策:從 Cohere Rerank 切換至本地交叉編碼器
  • 結果:P95 延遲 → 2.1 秒,滿意度小幅下降(92% → 89%)
  • 專家見解:對於支援使用案例,速度 > 完美準確度

步驟 4:故障情境處理

  • 發現 15% 的查詢關於文件中沒有的功能
  • 新手:會回傳「我不知道」
  • 專家:加入升級檢測並轉接給真人客服

最終架構:Pinecone + 本地重新排序 + 代理升級 = 89% 自動化率,P95 為 2.1 秒

品質閘道

  • Retrieval@5 準確度 > 85%(在評估資料集上)
  • 平均回應延遲(P95)< 3 秒
  • 上下文利用率 > 60%(模型使用檢索到的資訊)
  • 幻覺率 < 5%(回應未獲得檢索上下文支援)
  • 使用者滿意度分數 > 80%(30 天滾動視窗)
  • 每次查詢的 Token 成本低於預算閾值
  • 系統正常運行時間 > 99.9%(排除計畫性維護)
  • PII 檢測率 > 95%(回應中不包含個人資訊)
  • 嵌入模型效能穩定(每月退化不超過 10%)
  • 錯誤處理涵蓋所有故障模式並提供優雅降級

不適用範圍

請勿將此技能用於:

提示工程任務 → 改用 prompt-engineer

  • 最佳化提示範本與指令
  • A/B 測試提示變化
  • 思維鏈提示設計

機器學習模型訓練/微調 → 改用 ml-engineer

  • 訓練自訂嵌入模型
  • 在領域資料上微調 LLM
  • 模型架構研究

資料管線工程 → 改用 data-pipeline-engineer

  • 訓練資料的 ETL 流程
  • 資料驗證與清理工作流程
  • 批次處理系統

基礎設施/DevOps → 改用 backend-architect

  • Kubernetes 部署策略
  • 資料庫最佳化與分片
  • 負載平衡器配置

分析與監控設定 → 改用 chatbot-analytics

  • 對話流程分析
  • 使用者行為追蹤
  • 效能儀表板建立

委派時機:

  • 任務需要深度 ML 專業知識 → ml-engineer
  • 重點在於對話設計 → prompt-engineer
  • 需要基礎設施擴展 → backend-architect
  • 需要使用分析 → chatbot-analytics
  • 建構非 AI 功能 → 相關專家技能

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

curiositech/windags-skills

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

curiositech/windags-skills

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

curiositech/windags-skills

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

curiositech/windags-skills

Implement WCAG 2.2 AA/AAA compliance with automated testing, keyboard navigation, screen reader support, and focus management. Activate on: accessibility audit, WCAG compliance, keyboard navigation, screen reader, aria attributes, axe-core, focus trap. NOT for: design-level accessibility review (use design-accessibility-auditor), color contrast only (use css-in-js-architect).

curiositech/windags-skills

Time-blind friendly planning, executive function support, and daily structure for ADHD brains. Specializes in realistic time estimation, dopamine-aware task design, and building systems that actually work for neurodivergent minds.

curiositech/windags-skills

Designs digital experiences for ADHD brains using neuroscience research and UX principles. Expert in reducing cognitive load, time blindness solutions, dopamine-driven engagement, and compassionate design patterns. Activate on 'ADHD design', 'cognitive load', 'accessibility', 'neurodivergent UX', 'time blindness', 'dopamine-driven', 'executive function'. NOT for general accessibility (WCAG only), neurotypical UX design, or simple UI styling without ADHD context.

curiositech/windags-skills

>- Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

curiositech/windags-skills

Extend and modify the admin dashboard, developer portal, and operations console. Use when adding new admin tabs, metrics, monitoring features, or internal tools. Activates for dashboard development, analytics, user management, and internal tooling.

curiositech/windags-skills

Conversation patterns and interaction protocols for multi-agent systems. Covers request/response, pub/sub, blackboard, delegation chains, debate, critique, consensus, fan-out/fan-in, supervisor-worker, and peer negotiation. Deep analysis of AutoGen conversation patterns, CrewAI delegation, LangGraph state passing, and FIPA-ACL performatives. Teaches how to design what agents say to each other and in what order. Activate on: "agent conversation", "agent protocol", "multi-agent debate", "agent delegation", "supervisor worker pattern", "agent voting", "consensus protocol", "fan-out fan-in", "agent negotiation", "blackboard pattern", "agent dialogue", "conversation topology", "agent handoff". NOT for: wire format or serialization (use agent-interchange-formats), orchestration infrastructure (use agentic-infrastructure-2026), single agent behavior (use agentic-patterns).

curiositech/windags-skills

Meta-agent for creating new custom agents, skills, and MCP integrations. Expert in agent design, MCP development, skill architecture, and rapid prototyping. Activate on 'create agent', 'new skill', 'MCP server', 'custom tool', 'agent design'. NOT for using existing agents (invoke them directly), general coding (use language-specific skills), or infrastructure setup (use deployment-engineer).

curiositech/windags-skills

AI-powered calendar management and agent-based scheduling coordination. Covers calendar APIs (Google Calendar, CalDAV/iCal), AI scheduling assistants (Reclaim, Clockwise, Motion, Cal.com), building custom calendar agents with MCP, multi-calendar merging, timezone management, focus block protection, meeting fatigue detection, and agent-to-agent meeting negotiation protocols. Activate on: "calendar agent", "AI scheduling", "calendar coordination", "meeting scheduling", "calendar API", "focus time protection", "calendar optimization", "Google Calendar MCP", "Reclaim", "Clockwise", "Motion", "Cal.com", "smart scheduling", "calendar-aware agent", "timezone scheduling", "agent negotiation meetings". NOT for: manual calendar UI component design (use form-validation-architect), project management scheduling or Gantt charts (use project-management-guru-adhd), general time-tracking or pomodoro apps (use adhd-daily-planner for time-awareness), building the agent itself from scratch (use agent-creator).

curiositech/windags-skills

Build and adopt production AI agent infrastructure in 2026. Covers framework selection (LangGraph, CrewAI, AutoGen, MCP), orchestration patterns, evaluation, observability, memory systems, and tool use. Also covers the SOCIAL dimension: how to sell agent infrastructure internally, change management, measuring ROI, building trust in autonomous systems, and scaling adoption across teams. Activate on: "agent infrastructure", "agent framework comparison", "which agent framework", "sell AI tools internally", "agent adoption", "agent observability", "agent evaluation", "MCP architecture", "agentic mesh", "enterprise AI agents", "AI change management", "agent ROI". NOT for: building specific agents (use ai-engineer), designing agent behavior patterns (use agentic-patterns), prompt tuning (use prompt-engineer).

curiositech/windags-skills

Fundamental patterns for effective agentic behavior. Teaches decomposition, tool orchestration, error recovery, context management, quality self-assessment, and knowing when to stop. Model-agnostic principles that make any agent more effective regardless of domain. Activate on: "how should I structure this agent", "agentic workflow", "agent patterns", "multi-step task", "tool orchestration", "/agentic-patterns", "decompose this", "agent best practices", "chain of actions", "when should the agent stop", "agent loop design". NOT for: creating agent infrastructure (use agent-creator), building DAGs (use windags-architect), specific tool implementation.

curiositech/windags-skills

Automated discovery and matching of agent skills for dynamic task routing and capability assessment

curiositech/windags-skills

Cryptographic security for agentic systems — zero-trust agent networking, signed message envelopes (JWS/JWE), capability-based security (ocaps), Merkle tree audit trails, WASM sandboxing, and formal verification. Covers CLI dev tool security, mTLS between agents, permission boundaries (least privilege for AI agents), and supply chain security for skills/plugins. Activate on: "agent security", "zero trust agents", "secure agent communication", "capability-based security", "ocap", "signed messages between agents", "agent audit trail", "sandbox agent execution", "agent permissions", "mTLS agents", "cryptographic verification", "agent supply chain", "OWASP agentic", "prove agent did X", "tamper-proof agent logs". NOT for: application-level SAST scanning (use security-auditor), network firewall rules (use infrastructure), SOC2/HIPAA compliance (organizational), or prompt injection defense (use prompt-engineer).

curiositech/windags-skills

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Deep comparison of A2A protocol, MCP, OpenAI function calling, and LangChain message types. Teaches when to use rigid schemas vs free-form with validation, typed vs untyped, streaming vs batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).

curiositech/windags-skills

Logic-based agent programming language implementing BDI architecture for practical autonomous agent development

curiositech/windags-skills

>- Design AgentSpeak(L)-style BDI agents with context-guarded plans, selection functions, and intention stacks. Use for interruptible autonomy, agent policy, and multi-agent orchestration in dynamic environments. NOT for simple rule engines, static planners, or centralized workflows.

curiositech/windags-skills

Foundational concurrent computation model where actors communicate exclusively through asynchronous message passing

curiositech/windags-skills

license: Apache-2.0 NOT for unrelated tasks outside this domain.

相關技能