Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable. Use when shipping LLM apps fast with a "no-code to pro-code" gradient, especially when non-engineers need to co-author the flow.
.claude/skills/agentsope-agentsop-dify/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | 665% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 1156% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 441% | 0% |
| case-02 | ✓→✓ | ＝ Same ✓ | 967% | 0% |
| case-03 | ✓→✓ | ＝ Same ✓ | 968% | 0% |
> 框架定位: "An open-source platform for building agentic workflows" — visual workflow + RAG + agent + monitoring + deploy in one box, self-hostable. docs.dify.ai/en/introduction], github.com/langgenius/dify]
> "Dify is the only tool that gives you data ingestion, RAG, an API, and a polished, shareable web UI in one click." learnwithparam.com/blog/batteries-included-rag-platforms-dify-ragflow-onyx]
> Dify 的核心价值是 "把 LLM 应用工程的脚手架打平"——auth、API、UI、向量库、模型 provider、日志、版本——而不是替代 LLM 编排框架本身的表达力。
判断公式:
[Studio] ← Visual canvas (workflow / chatflow / agent / chatbot / text-gen)
↓ 编排
[Apps] ← 5 种 app 类型，全部跑在统一 Graph Engine 上
↓ 依赖
[Knowledge] ← RAG pipeline (ingest → chunk → embed → index → retrieve → rerank)
↓ + 调用
[Tools/Plugins] ← Marketplace: Models / Tools / Agent Strategies / Extensions / Bundles
↓ 观察
[Monitoring] ← 内建 logs + 外接 LangSmith / Langfuse / Arize Phoenix / Opik参考: docs.dify.ai/en/introduction], dify.ai/blog/dify-plugin-system-design-and-implementation]
| App Type | 触发模型 | 记忆 | 编排方式 | 典型场景 | |---|---|---|---|---| | Chatbot (legacy) | 多轮对话 | 内置 | 单 prompt + tools | 简单客服、FAQ bot | | Agent (legacy) | 多轮对话 | 内置 | ReAct / FC 自主决策 | 自治工具使用、多步推理 | | Text Generator (legacy) | 单次调用 | 无 | 单 prompt | 文案生成、翻译 | | Workflow | 单次调用 / 批处理 | 无 | 可视化 DAG | API 后端、批量任务、ETL | | Chatflow | 每轮对话触发整图 | 有 (conversation vars) | 可视化 DAG + 对话状态 | 复杂对话流、guided dialogue |
核心决策树:
有对话上下文需求？
├─ 是 ─→ Chatflow (复杂逻辑) 或 Chatbot/Agent (简单)
└─ 否 ─→ Workflow (复杂逻辑) 或 Text Generator (单 prompt)
需要 LLM 自主选择工具 / 多步推理？
├─ 是 ─→ Agent app 或 Workflow + Agent Node (推荐, 1.9+)
└─ 否 ─→ Workflow / Chatflow + 显式节点编排参考: docs.dify.ai/en/use-dify/getting-started/key-concepts], hellodify.com/en/docs/workflow/workflow-chatflow-difference], zediot.com/blog/dify-difference-between-agent-and-workflow]
> "Workflow behaves more like a script… each Workflow run is a completely fresh start. Chatflow… is a robot that can interact with users in a loop." hellodify.com/en/docs/workflow/workflow-chatflow-difference]
| 类别 | 节点 | 用途 | |---|---|---| | 基础 | Start, End, Answer | 入口 / 出口 | | LLM | LLM, Question Classifier, Parameter Extractor | 调模型 | | RAG | Knowledge Retrieval | 查知识库 | | 逻辑 | IF/ELSE, Iteration, Loop, Variable Assigner, Variable Aggregator | 控制流 | | 代码 | Code (Python/Node.js), Template (Jinja2) | 自定义逻辑 | | 外部 | HTTP Request, Tool, Agent Node | 调外部 / 子 agent | | 数据 | List Operator, Document Extractor | 处理结构化数据 |
> "Dify's canvas includes LLM calls, knowledge retrieval, conditionals, HTTP requests, code nodes (Python/Node), Jinja transforms, iterators/loops, and aggregators." legacy-docs.dify.ai/guides/workflow/node]
v1.0+ 引入插件系统，从 monolith → marketplace。 dify.ai/blog/introducing-dify-plugins]
| 类型 | 用途 | 何时选它 | |---|---|---| | Models | 接入新模型 provider | 内置不支持的模型 | | Tools | 给 agent / workflow 加能力 | 需要复用的领域工具 (Slack, Notion, 自家 API) | | Agent Strategies | 自定义 reasoning loop | 想用 ToT / GoT / 自研推理 | | Extensions | 轻量 HTTP webhook | 简单 API 接入，不需打包 | | Bundles | 多插件打包 | 整套行业解决方案 |
决策: 一次性 = HTTP Request 节点；可复用 = Tool plugin；逻辑深 = Agent Strategy plugin。
RAG 流程: Ingest → Extract → Clean → Chunk → Embed → Index → Retrieve → Rerank → Augment docs.dify.ai/en/guides/knowledge-base/readme]
三种构建方式:
向量库支持: 13+ (Qdrant 默认推荐, Weaviate, Milvus, Pinecone, PGVector, TiDB, Chroma…) deepwiki.com/langgenius/dify-docs/8.3-vector-database-configuration]
检索策略:
> 官方建议: "Workflow/Chatflow are recommended for most use cases. Use the legacy basic types (Chatbot/Agent/Text Generator) only if preferring simplified interfaces over advanced features." docs.dify.ai/en/use-dify/getting-started/key-concepts]
Cloud (推荐起步):
Self-host (Docker Compose) — 最常用:
bashgit clone https://github.com/langgenius/dify cd dify/docker cp .env.example .env docker compose up -d
关键环境变量:
VECTOR_STORE — 选 Qdrant / Weaviate / Milvus / Pinecone…PLUGIN_DAEMON_TIMEOUT=300 — 插件超时WORKFLOW_MAX_EXECUTION_TIME / HTTP_REQUEST_MAX_READ_TIMEOUT — 长链路必调{{var}} 抽出来——后续会成为 workflow 输入> "Dify provides a comprehensive RAG pipeline handling the full lifecycle from raw file upload through extraction, cleaning, segmentation, embedding, indexing, retrieval, and reranking." pyshine.com/2026/04/20/Dify-Open-Source-LLM-App-Development-Platform]
构建顺序 (反直觉但重要):
反模式: 一上来就画 30+ 节点的复杂图。先线性跑通，再分支。
yaml# 一个典型 Dify workflow 的 building blocks inputs: # Start 节点变量 (text / number / file / select) nodes: - llm: # 调模型 model: gpt-4-turbo prompt: "..." memory: false # workflow 永远是 false - knowledge_retrieval: # 查知识库 datasets: [kb_id_1, kb_id_2] mode: hybrid rerank: bge-rerank - if_else: # 分支 conditions: [...] - iteration: # 批处理列表 iterator: {{node.output}} sub_workflow: [...] - code: # Python/Node code: "def main(x): return ..." - http_request: # 调外部 method: POST url: "..." - agent: # 自主决策子节点 (1.9+) strategy: react / function_calling / custom tools: [...] max_iterations: 5 outputs: # End / Answer 节点
{{node_id.var}} 跨节点引用sys.user_id, sys.conversation_id 等症状:
决策树:
节点数 < 20 且分支扁平
→ 留在 Dify, 优化命名 + 加 Note
节点数 20-40, 有可复用子流程
→ 拆 sub-workflow (打包成 Tool 给主流程调用)
节点数 > 40 或 大量 Code 节点
→ 信号: 业务逻辑已超出可视化优势
→ 把核心逻辑改写为 Python 服务, Dify 只做编排前端 + RAG实操:
反模式: 在 Code 节点里写 200 行 Python——这是 "Dify 已不合适" 的信号。
症状:
判断公式: | 信号 | 留 Dify | 切代码 | |---|---|---| | 团队非 100% 工程师 | ✅ | ❌ | | 需要快速 UI / API / 认证 | ✅ | ❌ (得自己搭) | | pause-and-wait | ❌ | ✅ (LangGraph 原生) | | QPS > 10 / pod | ❌ | ✅ | | 复杂状态 + 回滚 | ❌ | ✅ | | RAG + 简单编排 | ✅ | — |
混合方案 (推荐): Dify 做前端 / RAG / 用户管理 / 监控；核心 agent 逻辑跑在 LangGraph 服务后端，Dify HTTP Request 节点调用。
> "Dify wins when you're building an LLM-powered SaaS, an internal product with multiple teams… Langflow is for teams that need power now and will need more later." blog.elest.io/dify-vs-langflow-vs-flowise]
症状:
决策矩阵 architjn.com/blog/dify-cloud-pricing-plans-free-tier-when-to-self-host]:
| 条件 | 选 Cloud | 选 Self-host | |---|---|---| | 团队 ≤ 3 人, 用量小 | ✅ ($59-159/mo 比养 DevOps 便宜) | ❌ | | 合规 / 数据驻留 (金融、医疗) | ❌ | ✅ | | 用量大 (millions of API calls) | ❌ (订阅成本超过 infra) | ✅ | | Air-gapped / 内网部署 | ❌ | ✅ | | 自定义 vector store / 模型 | 部分支持 | ✅ 完全控制 | | 不想管 backup / scaling | ✅ | ❌ |
实操要点:
症状:
决策: | 场景 | 用 Dify 内建 Knowledge | 用 External Knowledge | |---|---|---| | 单个 app 单个数据集 | ✅ 一键搞定 | ❌ over-kill | | 多 app 共享同一份 KB | ✅ Dify KB 可被多 app 引用 | — | | 极致 chunking / 实验性 retrieval | ❌ Dify 抽象有限 | ✅ | | 已有自建 RAG 服务 | ❌ | ✅ Dify HTTP/External KB 接入 | | 数据量 > 100M chunks | ❌ Dify 有 memory leak 风险 memo.d.foundation/breakdown/dify] | ✅ | | 需要 KG-RAG / hybrid + late interaction | ❌ | ✅ 或换 RAGFlow |
混合: Dify Knowledge 管常规文档；External Knowledge API 接你的自有 RAG 服务做长尾。
症状: 同一个需求，三种实现方式纠结。
决策原则 zediot.com/blog/dify-difference-between-agent-and-workflow], dify.ai/blog/dify-agent-node-introduction-when-workflows-learn-autonomous-reasoning]:
任务路径可预测、调试性优先
→ 显式 Workflow (写死分支)
任务路径不可预测、需 LLM 选工具
→ Workflow + Agent Node (1.9+)
[推荐!! 比纯 Agent app 更可控, 既享受自主性又有 workflow 外壳]
纯对话 + 工具调用、不需要复杂编排
→ Agent app (legacy)
混合: 主流程显式, 局部不确定路径
→ Workflow 主图 + 不确定段塞 Agent Node> "The best systems combine both — workflows as orchestrators that delegate reasoning tasks to agents. This hybrid model provides both predictability and intelligence." zediot.com/blog/dify-difference-between-agent-and-workflow]
反模式:
| 反模式 | 症状 | 修法 | |---|---|---| | 30+ 节点单图 | 卡顿 + 难调 issue #28245] | 拆 sub-workflow / Tool | | Code 节点写业务核心 | Code 节点 200+ 行 Python | 抽到外部微服务, Dify 用 HTTP 调用 | | 不上 Knowledge Pipeline | 文档质量飘忽 | 用 1.9+ 的 pipeline 自定义 ingest | | 没接 LLMOps | 上线后看不见 bad case | 接 Langfuse / Phoenix | | DSL 不入 git | 改飞了无法回滚 | 导出 DSL → git, 用 dify-dsl-exporter 批量化 github.com/linhai0872/dify-dsl-exporter] | | legacy Chatbot/Agent app 长期演进 | 无法表达分支 / 后期被迫迁移 | 直接上 Chatflow / Workflow | | workspace 共用 API key | 不同 app 计费混乱 | 已知限制, 暂用多 workspace 规避 | | 不做 retrieval testing | RAG 召回质量差还不自知 | 上传后立刻用真实 query 在 Retrieval Testing 里跑 | | stream 长任务 > 120s 不调超时 | Agent node 突然断开 issue #27053] | 调 WORKFLOW_MAX_EXECUTION_TIME + 反代超时 |
PLUGIN_DAEMON_TIMEOUT| 框架 | 抽象层 | 上手 | 天花板 | 选它的硬触发 | |---|---|---|---|---| | Dify | 平台 (UI+API+RAG+Auth) | 几小时 | 中等 (DB-bound, 单图复杂度) | 全栈 + 多角色协作 + 快速上线 | | Flowise | 节点编辑器 (薄层) | 几小时 | 低 (chatbot+RAG 为主) | 1GB RAM 最小部署、纯 chatbot | | LangFlow | LangChain 可视化包 | 半天 | 高 (可导出代码) | 已用 LangChain，想加 UI | | Coze (扣子) | 字节托管平台 | 小时 | 中等 (国内生态) | 国内市场 / 飞书集成 / 不要 self-host | | RAGFlow | 专精 RAG 引擎 | 半天 | RAG 维度极高 | 文档解析 + KG-RAG 是核心 | | n8n | 通用 workflow | 半天 | LLM 是 plugin | 400+ 非 AI 集成 + AI 是辅助 | | LangGraph | 代码框架 | 几天 | 极高 | 需要状态机 / 中断 / 时间旅行 | | LlamaIndex | RAG 框架 | 几天 | 极高 (数据侧) | RAG 是 P0 + 工程团队 | | CrewAI | 多 agent 代码 | 半天 | 中 (角色编排) | 2-5 个角色协作 pipeline |
参考: blog.elest.io/dify-vs-langflow-vs-flowise], jimmysong.io/blog/open-source-ai-agent-workflow-comparison], toolhalla.ai/blog/dify-vs-flowise-vs-langflow-2026]
此时: Dify 退到 "前端 + 监控 + RAG 仓库"，核心逻辑切到 LangGraph / 自研代码服务。
yaml# 一个 "知识库问答 + 工具调用" 的最小 chatflow 骨架 app: name: support-copilot mode: advanced-chat # = chatflow graph: nodes: - start: { variables: [{name: query, type: text}] } - knowledge_retrieval: dataset_ids: [kb_docs] retrieval_mode: hybrid top_k: 5 rerank_model: bge-reranker-v2 - llm: model: gpt-4-turbo prompt: - role: system content: "You are a support agent. Use the context to answer." - role: user content: "Context: {{knowledge_retrieval.result}}\n\nQ: {{start.query}}" memory: { enabled: true, window: 10 } # chatflow 才有 - answer: { stream: true, content: "{{llm.text}}" } features: - annotation_reply: true - moderation: openai-moderation - conversation_variables: [user_tier]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 11,011 | 15,227 | +38% | 1 | 1 | 0% | 1,930 | 10,433 | +441% | 0 | 0 | — |
case-02 | pass→pass | 5,266 | 5,591 | +6% | 1 | 1 | 0% | 856 | 9,131 | +967% | 0 | 0 | — |
case-03 | pass→pass | 6,291 | 7,081 | +13% | 1 | 1 | 0% | 871 | 9,304 | +968% | 0 | 0 | — |
case-04 | pass→pass | 11,462 | 10,649 | -7% | 1 | 1 | 0% | 1,891 | 9,922 | +425% | 0 | 0 | — |
case-05 | fail→fail | 19,797 | 23,716 | +20% | 1 | 1 | 0% | 3,154 | 11,954 | +279% | 0 | 0 | — |
case-06 | fail→pass | 27,033 | 7,938 | -71% | 1 | 1 | 0% | 1,245 | 9,529 | +665% | 0 | 0 | — |
case-07 | pass→pass | 5,677 | 8,031 | +41% | 1 | 1 | 0% | 896 | 9,538 | +965% | 0 | 0 | — |
case-08 | pass→pass | 13,036 | 18,155 | +39% | 1 | 1 | 0% | 2,120 | 11,045 | +421% | 0 | 0 | — |
case-09 | pass→pass | 12,530 | 10,933 | -13% | 1 | 1 | 0% | 2,169 | 9,898 | +356% | 0 | 0 | — |
case-10 | pass→pass | 13,181 | 15,499 | +18% | 1 | 1 | 0% | 2,194 | 10,746 | +390% | 0 | 0 | — |
case-11 | pass→pass | 12,269 | 10,294 | -16% | 1 | 1 | 0% | 1,870 | 9,840 | +426% | 0 | 0 | — |
case-12 | pass→pass | 11,969 | 5,267 | -56% | 1 | 1 | 0% | 2,058 | 9,147 | +344% | 0 | 0 | — |
case-13 | pass→pass | 8,084 | 9,480 | +17% | 1 | 1 | 0% | 1,351 | 9,708 | +619% | 0 | 0 | — |
case-14 | fail→pass | 4,251 | 2,816 | -34% | 1 | 1 | 0% | 691 | 8,677 | +1156% | 0 | 0 | — |
case-15 | pass→pass | 8,722 | 6,108 | -30% | 1 | 1 | 0% | 1,404 | 9,168 | +553% | 0 | 0 | — |
case-16 | pass→pass | 4,572 | 8,727 | +91% | 1 | 1 | 0% | 730 | 9,662 | +1224% | 0 | 0 | — |
case-17 | pass→pass | 4,341 | 6,933 | +60% | 1 | 1 | 0% | 644 | 9,239 | +1335% | 0 | 0 | — |
case-18 | pass→pass | 15,460 | 15,609 | +1% | 1 | 1 | 0% | 2,235 | 10,659 | +377% | 0 | 0 | — |
case-19 | pass→pass | 14,757 | 14,375 | -3% | 1 | 1 | 0% | 2,298 | 10,410 | +353% | 0 | 0 | — |
case-20 | pass→pass | 8,485 | 12,003 | +41% | 1 | 1 | 0% | 1,272 | 10,012 | +687% | 0 | 0 | — |
case-21 | pass→pass | 12,486 | 9,940 | -20% | 1 | 1 | 0% | 2,002 | 9,707 | +385% | 0 | 0 | — |
case-22 | pass→pass | 8,748 | 8,497 | -3% | 1 | 1 | 0% | 1,594 | 9,684 | +508% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +9 percentage points is the difference between those two pass rates over the 21 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.