extension-to-functions-codebase

作者: firebase

用于将已安装的Firebase Extension(或扩展源代码)转换为独立的Cloud Functions for Firebase代码库或可发布的npm包技能,…

npx skills add https://github.com/firebase/agent-skills --skill extension-to-functions-codebase

Extension to Functions Codebase & npm Package Migration

Overview

Migrates a Firebase Extension into either:

  1. A local Cloud Functions codebase (functions/src/ for app integration).
  2. A publishable npm package (reusable open-source package exporting V2 functions).

Leverages native Cloud Functions features (declarative IAM, Parameterized Config, SDK Lifecycle Hooks) and modernizes 1st Gen triggers to 2nd Gen using the Destructuring Compatibility Shim.


Target Migration Workflows

  • Target A: Local Functions Codebase (End-User App Integration)

    • Output: Code under functions/src/. Config in .env.
    • Deployment: firebase deploy --only functions.
  • Target B: Publishable npm Package / Shareable Package

    • Output: Reusable npm package exporting V2 functions.
    • Configuration: package.json specifying exports map, engines: { "node": ">=22" }, and peerDependencies: { "firebase-functions": ">=6.0.0" }.
    • Usage: Consumers install package and re-export functions in index.ts (export * from "<package-name>").

Core Rules & Constraints

1. Declarative IAM & APIs (Zero-Local-Overhead)

Use native SDK declarations instead of manual gcloud scripts or console instructions:

  • Use requiresRole("roles/...") for required GCP IAM permissions.
  • Use requiresAPI("service.googleapis.com", "Description") for Google APIs.

2. Global Parameter Access Restriction

  • Never call .value() at top-level module load scope.
  • Initialize global SDK instances inside onInit() or lazy getters:
    import { defineString } from "firebase-functions/params";
    import { onInit } from "firebase-functions/v2";
    
    const dataset = defineString("DATASET_ID");
    let client: BigQuery;
    
    onInit(() => {
      client = new BigQuery({ datasetId: dataset.value() });
    });
    

3. V2 Concurrency & Cost Parity

V2 enables concurrency (up to 80 requests). To preserve V1 single-concurrency pricing, set cpu: "gcf_gen1".


Step-by-Step Migration Execution

Step 1: Inventory Extension Resources

  1. extension.yaml:
    • params → defineString, defineInt, defineBoolean, defineSecret.
    • apis → requiresAPI(...).
    • roles → requiresRole(...).
    • lifecycleEvents → afterFirstDeploy & afterRedeploy.
    • resources → Upgrade 1st Gen triggers to 2nd Gen (onDocumentWritten, onTaskDispatched, onRequest).
  2. Files & Scripts: Preserve devDependencies, test framework (jest), and test scripts.

Step 2: Configure package.json

  • Set name: "<package-name>", engines: { "node": ">=22" }.
  • Set peerDependencies:
    "peerDependencies": {
      "firebase-admin": "^11.0.0 || ^12.0.0",
      "firebase-functions": ">=6.0.0"
    }
    
  • Configure exports map targeting ESM/CommonJS and TypeScript declarations (lib/index.js, lib/index.d.ts).

Step 3: Upgrade Triggers from V1 to V2

  • Firestore: Use onDocumentWritten from firebase-functions/v2/firestore.
  • Tasks: Use onTaskDispatched from firebase-functions/v2/tasks. Remove EXT_INSTANCE_ID when enqueueing tasks.
  • HTTP: Use onRequest from firebase-functions/v2/https.
  • Apply Destructuring Compatibility Shim ({ change, context }, { snapshot, context }) where legacy 1st Gen handlers expect (change, context).

Step 4: Convert Lifecycle Events

Map extension lifecycle events to SDK lifecycle hooks in src/index.ts:

  • onInstall → afterFirstDeploy({ task: { function: "initTask" } })
  • onUpdate / onConfigure → afterRedeploy({ task: { function: "setupTask" } })

Step 5: Package README & Export Instructions

Generate README.md containing:

  1. Installation instructions (npm install).
  2. Re-export snippet (export * from "<package-name>").
  3. Parameterized Configuration .env reference table.
  4. What Changed (Extension vs Package) comparison table.

Reminder: NEVER execute npm publish.

来自 firebase 的更多技能

developing-genkit-dart
firebase
面向 Dart 的统一 AI SDK,支持代码生成、结构化输出、工具、流程和智能体。提供核心 API,涵盖生成、工具定义、流程编排、嵌入和流式处理,采用统一接口。包含 8 个以上插件,支持 LLM 提供商(Google Gemini、Anthropic Claude、OpenAI GPT)、Firebase AI、模型上下文协议、Chrome 浏览器集成,以及通过 Shelf 托管 HTTP 服务器。内置 CLI 和本地开发 UI,用于流程执行、追踪、模型实验等。
developing-genkit-go
firebase
使用 Go 语言中的 Genkit 开发 AI 驱动的应用程序。当用户要求使用 Genkit 在 Go 中构建 AI 功能、代理、流程或工具时使用,或在处理…
developing-genkit-js
firebase
使用Genkit流程、工具和多模型支持,构建AI驱动的Node.js/TypeScript应用程序。Genkit与提供商无关;通过插件支持Google AI、OpenAI、Anthropic、Ollama及其他LLM提供商。使用Zod定义类型安全的模式流程,执行生成请求,并在TypeScript中组合多步骤AI工作流。需要Genkit CLI v1.29.0及以上版本;近期主要API变更意味着您必须查阅genkit文档:read和common-errors.md以获取当前模式,而非依赖先前知识...
developing-genkit-python
firebase
使用 Python 中的 Genkit 开发 AI 驱动的应用程序。当用户询问关于 Genkit、AI 代理、流程或 Python 中的工具,或遇到 Genkit 相关问题时使用。
developing-genkit-tooling
firebase
编写 Genkit 工具的最佳实践,包括 CLI 命令和 MCP 服务器工具。涵盖命名约定、架构模式及一致性……
firebase-ai-logic
firebase
客户端Gemini集成,适用于网页应用,支持多模态推理、流式传输及设备端混合执行。支持纯文本和多模态输入(图像、音频、视频、PDF);超过20MB的文件通过Cloud Storage路由。包含自动历史记录的聊天会话、用于实时显示的流式响应,以及结构化JSON输出强制。通过Chrome中的Gemini Nano提供混合设备端推理,并自动回退到云端执行。生产环境需启用App Check...
firebase-ai-logic
firebase
集成 Firebase AI Logic(Firebase 中的 Gemini),为应用添加智能功能。适用于为 Firebase 应用添加 AI 能力、实现生成式 AI…
firebase-ai-logic-basics
firebase
用于将Firebase AI Logic(Gemini API)集成到Web应用程序中的官方技能。涵盖设置、多模态推理、结构化输出和安全性。