stitch-sdk-domain-design

為 Stitch SDK 設計領域模型。用於將 MCP 工具映射到 domain-map.json 中的領域類別與綁定。這是生成流程的第二階段…

npx skills add https://github.com/google-labs-code/stitch-sdk --skill stitch-sdk-domain-design

Stitch SDK Domain Design

This skill teaches you how to perform Stage 2 of the generation pipeline: reading tool schemas and producing domain-map.json — the intermediate representation that drives codegen.


Your Inputs

  1. tools-manifest.json — raw MCP tool schemas captured from the server (includes outputSchema)
  2. ir-schema.ts — Zod schema defining valid domain-map structure (the canonical contract)
  3. Existing domain-map.json — the current IR (if extending, not starting fresh)
  4. The stitch-sdk-development skill — for understanding the pipeline context

Your Output

A valid domain-map.json with two sections: classes and bindings, validated by ir-schema.ts.

[!IMPORTANT] Your output is validated twice by the codegen: structurally (Zod IR schema) and semantically (projection steps verified against outputSchema from the tools-manifest).


Designing Classes

Each class represents a domain entity. Ask: "What noun does the user interact with?"

{
  "Stitch": {
    "description": "Main entry point. Manages projects.",
    "constructorParams": [],
    "isRoot": true,
    "factories": [
      {
        "method": "project",
        "returns": "Project",
        "description": "Create a Project handle from an ID."
      }
    ]
  }
}

Key decisions:

FieldPurposeExample
constructorParamsFields stored on the instance["projectId", "screenId"]
fieldMappingPer-field data source mapping with optional stripPrefixSee below
parentFieldWhich param is injected from a parent class"projectId"
idFieldWhich param the .id getter aliases"screenId"
factoriesLocal factory methods (no API call)[{ "method": "project", "returns": "Project" }]

Field Mapping

Use fieldMapping when a param needs a different source field, prefix stripping, or a fallback:

{
  "constructorParams": ["projectId", "screenId"],
  "fieldMapping": {
    "projectId": { "from": "name", "stripPrefix": "projects/" },
    "screenId": {
      "from": "id",
      "fallback": { "field": "name", "splitOn": "/screens/" }
    }
  }
}
  • stripPrefix: Removes a resource name prefix from the value
  • fallback: If the primary field is missing, splits an alternate field on a delimiter

Designing Bindings

Each binding maps one MCP tool to one class method. Ask: "Who owns this action?"

Arg routing

TypeMeaningCode generated
selfFrom this.fieldprojectId: this.projectId
paramFrom method parameterprompt: prompt
computedTemplate interpolationname: \projects/${this.projectId}/screens/${screenId}``
selfArrayWrap self field as arrayselectedScreenIds: [this.screenId]

Optional params use "optional": true. Renamed params use "rename": "newName".

Response Projections

The returns.projection array tells codegen how to navigate the API response. Each step is a ProjectionStep:

{ prop: string; index?: number; each?: boolean; fallback?: string }
ProjectionGenerated codeUse when
[] (empty)rawDirect return (whole response)
[{ "prop": "projects" }]raw.projectsArray inside object
[{ "prop": "outputComponents", "index": 0 }, { "prop": "design" }, { "prop": "screens", "index": 0 }]raw.outputComponents[0].design.screens[0]Deeply nested single item
[{ "prop": "outputComponents", "each": true }, { "prop": "design" }, { "prop": "screens", "each": true }]flatMap chainCollect all items across arrays
[{ "prop": "screenshot" }, { "prop": "downloadUrl" }]raw.screenshot.downloadUrlNavigate nested properties

Decision: Use "index": 0 when extracting a single item. Use "each": true when collecting all items (array result). You cannot use both on the same step.

[!TIP] Every prop in a projection is validated against the tool's outputSchema at codegen time. If you typo a property name, codegen will fail with a diagnostic listing the available properties.

Return class wrapping

When returns.class is set, the extracted data is wrapped in a domain class constructor:

{
  "returns": {
    "class": "Screen",
    "projection": [{ "prop": "screens" }],
    "array": true
  }
}

The codegen automatically spreads parentField into the data if the child class declares one.

Cache-aware methods

Add a cache field with a structured projection to check this.data before calling the API:

{
  "cache": {
    "projection": [{ "prop": "htmlCode" }, { "prop": "downloadUrl" }],
    "description": "Use cached HTML download URL from generation response if available"
  }
}

When the cached property is a nested object (like File with a downloadUrl), use multiple projection steps to drill into it.

Generated code:

if (this.data?.htmlCode?.downloadUrl) return this.data?.htmlCode?.downloadUrl;
// ... else call API

Decision Framework

When mapping a new tool, answer these questions:

  1. Which class? Look at which fields the tool requires. If it needs projectId from self, it belongs on Project or Screen. If it needs nothing from self, it belongs on Stitch.

  2. Which method name? Use the verb from the tool name, simplified. generate_screen_from_textgenerate. edit_screensedit.

  3. Arguments from self or param? If the caller already has the data (because they're calling a method on themselves), use self. If they need to provide it, use param.

  4. How deep is the return? Check the tool's outputSchema in tools-manifest.json. Build the projection array step-by-step to navigate to the useful data.

  5. Should it cache? If the data is available from a previous response (like generation), add a cache field with the projection path.


Validation

After editing domain-map.json:

bun scripts/generate-sdk.ts     # Validates IR + projections, then generates
npx tsc --noEmit                 # Type check
npx vitest run                   # Unit tests
bun scripts/e2e-test.ts          # E2E tests
bun scripts/validate-generated.ts  # Lock integrity

If a projection is invalid, you'll see:

❌ Binding "Project.generate" projection step 2:
   property "screenz" not found in outputSchema.
   Available properties: screens, components, metadata

來自 google-labs-code 的更多技能

remotion
google-labs-code
使用 Remotion 從 Stitch 應用程式設計中建立專業的逐步解說影片,包含流暢的轉場與文字疊加。從 Stitch 專案中擷取畫面,並將其編排成 Remotion 影片組合,支援縮放效果、淡入淡出轉場及情境文字疊加。支援模組化元件架構,包含 ScreenSlide 與 WalkthroughComposition 元件,以及互動式熱點與旁白整合等進階功能。產生畫面清單、下載...
official
ink
google-labs-code
用於 json-render 的 Ink 終端渲染器,可將 JSON 規格轉換為互動式終端 UI。適用於使用 @json-render/ink 從…構建終端 UI 時。
official
stitch-sdk-pipeline
google-labs-code
執行完整的 Stitch SDK 生成管線。當新增工具或需要從頭到尾重新生成 SDK 時使用。
official
stitch-sdk-readme
google-labs-code
為 Stitch SDK 產生或更新 README。使用 Bookstore Test 結構,並從程式碼庫中取得當前 API。當 README 需要…時使用。
official
typed-service-contracts
google-labs-code
Architecture standard for building robust, type-safe TypeScript services using the "Spec and Handler" pattern. Use when building CLIs, libraries, or complex…
official
agent-dx-cli-scale
google-labs-code
一種評分量表,用於評估命令列介面針對AI代理的設計優劣,依據「Rewrite Your CLI for AI Agents」原則制定。
official
ink
google-labs-code
Ink 終端渲染器,用於 json-render,可將 JSON 規格轉換為互動式終端 UI。在處理 @json-render/ink、從……建置終端 UI 時使用。
official
stitch-sdk-bug-bash
google-labs-code
Find bugs in the Stitch SDK using a real API key. Covers standard functional edges and tricky situations.
official