跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Firebase AI Logic Basics

技能 已验证 活跃
属于:Firebase

Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.

目的

To enable developers to easily integrate Google's Gemini AI models into their web and mobile applications using Firebase services, simplifying setup, usage, and security considerations.

功能

  • Firebase AI Logic (Gemini API) integration
  • Setup and initialization guidance
  • Multimodal inference (text, images, audio, video, PDF)
  • Chat session management (multi-turn)
  • Streaming response handling
  • Structured JSON output enforcement
  • Security best practices (App Check, backend provisioning)

使用场景

  • Adding generative AI features to web applications using Firebase.
  • Implementing image analysis and captioning within a mobile app.
  • Building conversational AI interfaces powered by Gemini models within Flutter apps.
  • Enforcing structured output for AI-generated content in a project.

非目标

  • Providing a backend for AI model hosting (Firebase handles this).
  • Replacing the core Firebase SDKs or CLI functionalities.
  • Implementing AI model training or fine-tuning.

先决条件

  • Node.js 16+
  • Firebase CLI
  • Firebase Project setup

Documentation

  • info:Configuration & parameter referenceWhile the SKILL.md mentions Node.js 16+ as a prerequisite and references Firebase docs for setup, it does not explicitly document all potential configuration parameters or their defaults for the AI Logic SDK itself. The core initialization is shown, but detailed parameter options are likely found in external Firebase documentation.

Practical Utility

  • info:Edge casesWhile the skill mentions prerequisites like Node.js 16+ and points to Firebase docs for unsupported platforms, it doesn't explicitly document failure modes (e.g., network issues, rate limits, invalid API keys) with specific symptoms and recovery steps. The critical safety requirement for App Check is highlighted, but other edge cases could be more detailed.

安装

请先添加 Marketplace

/plugin marketplace add firebase/agent-skills
/plugin install agent-skills@firebase

质量评分

已验证
95 /100
1 day ago 分析

信任信号

最近提交2 days ago
星标280
许可证Apache-2.0
状态
查看源代码

类似扩展

Auth0 Quickstart

99

Use when adding authentication or login to any app - detects your stack (React, Next.js, Vue, Nuxt, Angular, Express, Fastify, FastAPI, ASP.NET Core, React Native, Expo, Android, Swift), sets up an Auth0 account if needed, and routes to the correct SDK setup workflow.

技能
auth0

Trader Regime

100

Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy

技能
ruvnet

Trading Memory

100

AI交易记忆的领域知识 — 结果加权记忆 (OWM) 架构、5种记忆类型、回忆评分和行为分析。用于记录交易、回忆相似的上下文、分析性能或检查行为漂移。在 "record trade"、"remember trade"、"recall"、"similar trades"、"performance"、"behavioral"、"disposition"、"affective state"、"confidence" 时触发。

技能
mnemox-ai

TradeMemory Protocol

100

Evolution Engine 的领域知识 — 支持 LLM 从原始 OHLCV 数据中自主发现策略。涵盖生成-回测-选择-进化循环、向量化回测、样本外验证和策略梯度。在发现交易模式、运行回测、进化策略或审查进化日志时使用。由“evolve”、“discover patterns”、“backtest”、“evolution”、“strategy generation”、“candidate strategy”触发。

技能
mnemox-ai

Image Transformation API

100

Transform images with resize, crop, smart crop, upscale, remove background, and 20+ operations.

技能
iterationlayer

Azure Ai Document Intelligence Dotnet

100

Azure AI Document Intelligence SDK for .NET. Extract text, tables, and structured data from documents using prebuilt and custom models. Use for invoice processing, receipt extraction, ID document analysis, and custom document models. Triggers: "Document Intelligence", "DocumentIntelligenceClient", "form recognizer", "invoice extraction", "receipt OCR", "document analysis .NET".

技能
microsoft