[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-10347310-a14c-4ad7-a10f-720ea312327e":3,"$fqXwhuK2PzAR6Mo6lCocfI64V2jJm1ydFAepJiYezOJA":42},{"id":4,"title":5,"description":6,"categoryId":7,"moduleId":8,"tags":9,"prompt":10,"icon":11,"source":12,"sourceUrl":13,"authorId":14,"authorName":15,"isPublic":16,"stars":17,"runs":18,"createdAt":19,"updatedAt":19,"module":20,"category":27,"packages":33},"10347310-a14c-4ad7-a10f-720ea312327e","ai-ml","人工智能和机器学习工作流程，涵盖LLM应用开发、RAG实现、代理架构、机器学习管道和AI功能。","cat_coding_backend","mod_coding","sickn33,coding","---\nname: ai-ml\ndescription: \"AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.\"\ncategory: workflow-bundle\nrisk: safe\nsource: personal\ndate_added: \"2026-02-27\"\n---\n\n# AI\u002FML Workflow Bundle\n\n## Overview\n\nComprehensive AI\u002FML workflow for building LLM applications, implementing RAG systems, creating AI agents, and developing machine learning pipelines. This bundle orchestrates skills for production AI development.\n\n## When to Use This Workflow\n\nUse this workflow when:\n- Building LLM-powered applications\n- Implementing RAG (Retrieval-Augmented Generation)\n- Creating AI agents\n- Developing ML pipelines\n- Adding AI features to applications\n- Setting up AI observability\n\n## Workflow Phases\n\n### Phase 1: AI Application Design\n\n#### Skills to Invoke\n- `ai-product` - AI product development\n- `ai-engineer` - AI engineering\n- `ai-agents-architect` - Agent architecture\n- `llm-app-patterns` - LLM patterns\n\n#### Actions\n1. Define AI use cases\n2. Choose appropriate models\n3. Design system architecture\n4. Plan data flows\n5. Define success metrics\n\n#### Copy-Paste Prompts\n```\nUse @ai-product to design AI-powered features\n```\n\n```\nUse @ai-agents-architect to design multi-agent system\n```\n\n### Phase 2: LLM Integration\n\n#### Skills to Invoke\n- `llm-application-dev-ai-assistant` - AI assistant development\n- `llm-application-dev-langchain-agent` - LangChain agents\n- `llm-application-dev-prompt-optimize` - Prompt engineering\n- `gemini-api-dev` - Gemini API\n\n#### Actions\n1. Select LLM provider\n2. Set up API access\n3. Implement prompt templates\n4. Configure model parameters\n5. Add streaming support\n6. Implement error handling\n\n#### Copy-Paste Prompts\n```\nUse @llm-application-dev-ai-assistant to build conversational AI\n```\n\n```\nUse @llm-application-dev-langchain-agent to create LangChain agents\n```\n\n```\nUse @llm-application-dev-prompt-optimize to optimize prompts\n```\n\n### Phase 3: RAG Implementation\n\n#### Skills to Invoke\n- `rag-engineer` - RAG engineering\n- `rag-implementation` - RAG implementation\n- `embedding-strategies` - Embedding selection\n- `vector-database-engineer` - Vector databases\n- `similarity-search-patterns` - Similarity search\n- `hybrid-search-implementation` - Hybrid search\n\n#### Actions\n1. Design data pipeline\n2. Choose embedding model\n3. Set up vector database\n4. Implement chunking strategy\n5. Configure retrieval\n6. Add reranking\n7. Implement caching\n\n#### Copy-Paste Prompts\n```\nUse @rag-engineer to design RAG pipeline\n```\n\n```\nUse @vector-database-engineer to set up vector search\n```\n\n```\nUse @embedding-strategies to select optimal embeddings\n```\n\n### Phase 4: AI Agent Development\n\n#### Skills to Invoke\n- `autonomous-agents` - Autonomous agent patterns\n- `autonomous-agent-patterns` - Agent patterns\n- `crewai` - CrewAI framework\n- `langgraph` - LangGraph\n- `multi-agent-patterns` - Multi-agent systems\n- `computer-use-agents` - Computer use agents\n\n#### Actions\n1. Design agent architecture\n2. Define agent roles\n3. Implement tool integration\n4. Set up memory systems\n5. Configure orchestration\n6. Add human-in-the-loop\n\n#### Copy-Paste Prompts\n```\nUse @crewai to build role-based multi-agent system\n```\n\n```\nUse @langgraph to create stateful AI workflows\n```\n\n```\nUse @autonomous-agents to design autonomous agent\n```\n\n### Phase 5: ML Pipeline Development\n\n#### Skills to Invoke\n- `ml-engineer` - ML engineering\n- `mlops-engineer` - MLOps\n- `machine-learning-ops-ml-pipeline` - ML pipelines\n- `ml-pipeline-workflow` - ML workflows\n- `data-engineer` - Data engineering\n\n#### Actions\n1. Design ML pipeline\n2. Set up data processing\n3. Implement model training\n4. Configure evaluation\n5. Set up model registry\n6. Deploy models\n\n#### Copy-Paste Prompts\n```\nUse @ml-engineer to build machine learning pipeline\n```\n\n```\nUse @mlops-engineer to set up MLOps infrastructure\n```\n\n### Phase 6: AI Observability\n\n#### Skills to Invoke\n- `langfuse` - Langfuse observability\n- `manifest` - Manifest telemetry\n- `evaluation` - AI evaluation\n- `llm-evaluation` - LLM evaluation\n\n#### Actions\n1. Set up tracing\n2. Configure logging\n3. Implement evaluation\n4. Monitor performance\n5. Track costs\n6. Set up alerts\n\n#### Copy-Paste Prompts\n```\nUse @langfuse to set up LLM observability\n```\n\n```\nUse @evaluation to create evaluation framework\n```\n\n### Phase 7: AI Security\n\n#### Skills to Invoke\n- `prompt-engineering` - Prompt security\n- `security-scanning-security-sast` - Security scanning\n\n#### Actions\n1. Implement input validation\n2. Add output filtering\n3. Configure rate limiting\n4. Set up access controls\n5. Monitor for abuse\n6. Implement audit logging\n\n## AI Development Checklist\n\n### LLM Integration\n- [ ] API keys secured\n- [ ] Rate limiting configured\n- [ ] Error handling implemented\n- [ ] Streaming enabled\n- [ ] Token usage tracked\n\n### RAG System\n- [ ] Data pipeline working\n- [ ] Embeddings generated\n- [ ] Vector search optimized\n- [ ] Retrieval accuracy tested\n- [ ] Caching implemented\n\n### AI Agents\n- [ ] Agent roles defined\n- [ ] Tools integrated\n- [ ] Memory working\n- [ ] Orchestration tested\n- [ ] Error handling robust\n\n### Observability\n- [ ] Tracing enabled\n- [ ] Metrics collected\n- [ ] Evaluation running\n- [ ] Alerts configured\n- [ ] Dashboards created\n\n## Quality Gates\n\n- [ ] All AI features tested\n- [ ] Performance benchmarks met\n- [ ] Security measures in place\n- [ ] Observability configured\n- [ ] Documentation complete\n\n## Related Workflow Bundles\n\n- `development` - Application development\n- `database` - Data management\n- `cloud-devops` - Infrastructure\n- `testing-qa` - AI testing\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","","imported","https:\u002F\u002Fgithub.com\u002Fsickn33\u002Fantigravity-awesome-skills","user_system_seed","SkillOPIC",true,89,1322,"2026-05-16 13:02:07",{"id":8,"name":21,"slug":22,"icon":23,"description":24,"sort":25,"createdAt":26},"编程开发","coding","mdi-code-braces","代码生成、调试、审查，提升开发效率",2,"2026-05-16 12:53:40",{"id":7,"name":28,"slug":29,"icon":30,"description":31,"moduleId":8,"sort":25,"skillCount":32,"createdAt":26},"后端开发","backend","mdi-server","API、数据库、服务端架构",296,[34],{"id":35,"skillId":4,"version":36,"fileName":37,"fileSize":38,"filePath":39,"fileHash":40,"manifest":41,"createdAt":19},"2de00ca9-a160-42a0-81bc-6b0e2431c34e","1.0.0","ai-ml.zip",2208,"uploads\u002Fskills\u002F10347310-a14c-4ad7-a10f-720ea312327e\u002Fai-ml.zip","3bdd9e6f45a686b812ea7cbb46a818d361b33a436aac7a1aab4fe39a76ee7fe4","[{\"path\":\"SKILL.md\",\"isDirectory\":false,\"size\":5966}]",{"code":43,"message":44,"data":45},200,"success",{"items":46,"stats":47,"page":50},[],{"averageRating":48,"totalRatings":48,"ratingCounts":49},0,[48,48,48,48,48],{"limit":51,"offset":48,"hasMore":52,"nextOffset":51,"ratedOnly":16},15,false]