[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-3fa10c52-d87c-4c2a-b29d-c674cce8ec46":3,"$flMzGiV7vdiz8LyBdHTBJfUypr-o4SCeleOhYdFfMl6A":43},{"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":34},"3fa10c52-d87c-4c2a-b29d-c674cce8ec46","agent-workflow-designer","设计具有清晰模式选择（顺序、并行、分层）、交接合同、故障处理和成本\u002F上下文控制的量产级多代理工作流程。在架构多步骤代理管道、在单代理与多代理方法之间进行选择或重构因上下文膨胀或不稳定交接而受影响的LLM工作流程时使用。","cat_prod_automation","mod_productivity","alirezarezvani,productivity","---\nname: \"agent-workflow-designer\"\ndescription: \"Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost\u002Fcontext controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.\"\n---\n\n# Agent Workflow Designer\n\n**Tier:** POWERFUL  \n**Category:** Engineering  \n**Domain:** Multi-Agent Systems \u002F AI Orchestration\n\n---\n\n## Overview\n\nDesign production-grade multi-agent workflows with clear pattern choice, handoff contracts, failure handling, and cost\u002Fcontext controls.\n\n## Core Capabilities\n\n- Workflow pattern selection for multi-step agent systems\n- Skeleton config generation for fast workflow bootstrapping\n- Context and cost discipline across long-running flows\n- Error recovery and retry strategy scaffolding\n- Documentation pointers for operational pattern tradeoffs\n\n---\n\n## When to Use\n\n- A single prompt is insufficient for task complexity\n- You need specialist agents with explicit boundaries\n- You want deterministic workflow structure before implementation\n- You need validation loops for quality or safety gates\n\n---\n\n## Quick Start\n\n```bash\n# Generate a sequential workflow skeleton\npython3 scripts\u002Fworkflow_scaffolder.py sequential --name content-pipeline\n\n# Generate an orchestrator workflow and save it\npython3 scripts\u002Fworkflow_scaffolder.py orchestrator --name incident-triage --output workflows\u002Fincident-triage.json\n```\n\n---\n\n## Pattern Map\n\n- `sequential`: strict step-by-step dependency chain\n- `parallel`: fan-out\u002Ffan-in for independent subtasks\n- `router`: dispatch by intent\u002Ftype with fallback\n- `orchestrator`: planner coordinates specialists with dependencies\n- `evaluator`: generator + quality gate loop\n\nDetailed templates: `references\u002Fworkflow-patterns.md`\n\n---\n\n## Recommended Workflow\n\n1. Select pattern based on dependency shape and risk profile.\n2. Scaffold config via `scripts\u002Fworkflow_scaffolder.py`.\n3. Define handoff contract fields for every edge.\n4. Add retry\u002Ftimeouts and output validation gates.\n5. Dry-run with small context budgets before scaling.\n\n---\n\n## Common Pitfalls\n\n- Over-orchestrating tasks solvable by one well-structured prompt\n- Missing timeout\u002Fretry policies for external-model calls\n- Passing full upstream context instead of targeted artifacts\n- Ignoring per-step cost accumulation\n\n## Best Practices\n\n1. Start with the smallest pattern that can satisfy requirements.\n2. Keep handoff payloads explicit and bounded.\n3. Validate intermediate outputs before fan-in synthesis.\n4. Enforce budget and timeout limits in every step.\n","","imported","https:\u002F\u002Fgithub.com\u002Falirezarezvani\u002Fclaude-skills","user_system_seed","SkillOPIC",true,103,639,"2026-05-16 13:53:00",{"id":8,"name":21,"slug":22,"icon":23,"description":24,"sort":25,"createdAt":26},"效率工具","productivity","mdi-lightning-bolt-outline","文档处理、数据分析、自动化工作流",4,"2026-05-16 12:53:40",{"id":7,"name":28,"slug":29,"icon":30,"description":31,"moduleId":8,"sort":32,"skillCount":33,"createdAt":26},"自动化","automation","mdi-robot-outline","工作流自动化、批处理",3,101,[35],{"id":36,"skillId":4,"version":37,"fileName":38,"fileSize":39,"filePath":40,"fileHash":41,"manifest":42,"createdAt":19},"6f398371-ce7c-4d4a-ae51-b79b7f33f852","1.0.0","agent-workflow-designer.zip",3487,"uploads\u002Fskills\u002F3fa10c52-d87c-4c2a-b29d-c674cce8ec46\u002Fagent-workflow-designer.zip","848ede184c9642dc238a9366fc2b22b4f681749e76f4b3af0b689128167c1520","[{\"path\":\"SKILL.md\",\"isDirectory\":false,\"size\":2724},{\"path\":\"references\u002Fworkflow-patterns.md\",\"isDirectory\":false,\"size\":1518},{\"path\":\"scripts\u002Fworkflow_scaffolder.py\",\"isDirectory\":false,\"size\":3365}]",{"code":44,"message":45,"data":46},200,"success",{"items":47,"stats":48,"page":51},[],{"averageRating":49,"totalRatings":49,"ratingCounts":50},0,[49,49,49,49,49],{"limit":52,"offset":49,"hasMore":53,"nextOffset":52,"ratedOnly":16},15,false]