make-module-configuring
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseMake Module Configuration
Make模块配置
This skill covers configuring individual modules within a Make scenario. Once a scenario's module composition is decided (see make-scenario-building), each module must be configured: connections assigned, parameters filled, data mapped from upstream modules, and special components (webhooks, data stores, keys) wired up.
本技能涵盖Make场景中单个模块的配置工作。当场景的模块组合确定后(详见make-scenario-building),必须对每个模块进行配置:分配连接、填写参数、映射上游模块的数据,并连接特殊组件(webhook、数据存储、密钥)。
Quick Routing
快速导航
Read the reference file that matches the current task:
| Task | Reference |
|---|---|
| Configuring any module (start here) | General Principles — 5-phase workflow: read interface, resolve components, run RPCs, fill params/mapper, validate |
| Setting up or assigning a connection | Connections — credential request flow, scope checking, Extract Blueprint Components |
| Creating or assigning a webhook | Webhooks — custom vs branded, data structure definition |
| Creating or assigning a data store | Data Stores — requires data structure first |
| Defining a data structure (schema) | Data Structures — field types, nested structures |
| Provisioning keys or certificates | Keys — SSH, PEM/PFX via credential requests |
| Writing IML expressions | IML Expressions — functions, variables, operators, backtick rule |
| Mapping data between modules | Mapping — module ID references, output schema discovery |
| Adding filter conditions | Filtering — operators, AND/OR grouping, placement rules |
| Configuring an aggregator | Aggregators — feeder/target, variants, configuration order exception |
| Configuring an AI agent module | AI Agents — tools array, AI-decided fields, restore metadata |
阅读与当前任务匹配的参考文档:
| 任务 | 参考文档 |
|---|---|
| 配置任意模块(从这里开始) | 通用原则 — 五阶段工作流:读取界面、解析组件、运行RPC、填写参数/映射器、验证 |
| 设置或分配连接 | 连接 — 凭证请求流程、作用域检查、提取蓝图组件 |
| 创建或分配webhook | Webhook — 自定义与品牌化、数据结构定义 |
| 创建或分配数据存储 | 数据存储 — 需先定义数据结构 |
| 定义数据结构(Schema) | 数据结构 — 字段类型、嵌套结构 |
| 配置密钥或证书 | 密钥 — 通过凭证请求获取SSH、PEM/PFX |
| 编写IML表达式 | IML表达式 — 函数、变量、运算符、反引号规则 |
| 在模块间映射数据 | 数据映射 — 模块ID引用、输出Schema发现 |
| 添加过滤条件 | 过滤 — 运算符、AND/OR分组、放置规则 |
| 配置聚合器 | 聚合器 — 源模块/目标模块、变体、配置顺序例外 |
| 配置AI Agent模块 | AI Agent — 工具数组、AI决策字段、恢复元数据 |
Cardinal Rules
核心规则
These apply to every module configuration. Violating any of them is the most common cause of broken scenarios.
-
Read the interface first. Callwith
app-module_getbefore configuring any module. Never guess parameter names, types, or structures.outputFormat: "instructions" -
Validate every module. Callafter assembling each module's config. Do not proceed if validation returns errors — no exceptions.
validate_module_configuration -
Component creation order. Data structures, then webhooks, then connections, then keys, then data stores (dependencies flow left to right). Connections and keys require credential requests (user completes auth); webhooks, data stores, and data structures can be created directly via MCP.
-
Configure left to right. Work upstream to downstream so output schemas are available for mapping. Exception: array aggregators need their target module configured first — see Aggregators.
-
Connection selection is interactive. Always present all matching connections to the user and let them choose. Never auto-select, even if only one match exists. See Connections.
这些规则适用于所有模块配置。违反任何一条都是导致场景故障的最常见原因。
-
先读取界面。 在配置任何模块之前,调用并设置
app-module_get。绝不要猜测参数名称、类型或结构。outputFormat: "instructions" -
验证每个模块。 完成每个模块的配置后,调用。如果验证返回错误,请勿继续——没有例外。
validate_module_configuration -
组件创建顺序。 先创建数据结构,再创建webhook,接着是连接,然后是密钥,最后是数据存储(依赖关系从左到右)。连接和密钥需要凭证请求(用户完成认证);webhook、数据存储和数据结构可直接通过MCP创建。
-
从左到右配置。 按上游到下游的顺序操作,以便输出Schema可用于数据映射。例外: 数组聚合器需要先配置目标模块——详见聚合器。
-
连接选择需交互。 始终向用户展示所有匹配的连接并让他们选择。绝不要自动选择,即使只有一个匹配项。详见连接。
Official Documentation
官方文档
Related Skills
相关技能
- make-scenario-building — Which modules to use and how to compose them into flows (routing, branching, filtering, iterations, aggregations, error handling)
- make-mcp-reference — MCP server configuration, scopes, access control
- make-scenario-building — 应使用哪些模块以及如何将它们组合成工作流(路由、分支、过滤、迭代、聚合、错误处理)
- make-mcp-reference — MCP服务器配置、作用域、访问控制