Official skill for integrating Firebase AI Logic (Gemini API) into web applications. Covers setup, multimodal inference, structured output, and security.
56
33%
Does it follow best practices?
Impact
100%
1.42xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/firebase-ai-logic-basics/SKILL.mdWeb SDK setup and streaming initialization
Init ailogic CLI command
16%
100%
Projects list command
0%
100%
Apps list command
62%
100%
Firebase SDK install command
100%
100%
GoogleAIBackend initialization
100%
100%
getAI after initializeApp
100%
100%
Correct model name
0%
100%
Does NOT use gemini-1.5-flash
100%
100%
Streaming via generateContentStream
100%
100%
Gemini Developer API chosen
100%
100%
No hardcoded model alternative note
0%
100%
Flutter setup with correct provisioning and security
CLI provisioning step
0%
100%
flutterfire configure scope
50%
100%
firebase_ai package (not firebase_vertexai)
100%
100%
firebase_core and firebase_auth included
50%
100%
Correct model name in Dart
0%
100%
FirebaseAI.googleAI usage
100%
100%
startChat for multi-turn
100%
100%
Firebase init before AI usage
100%
100%
Anonymous or authenticated sign-in
0%
100%
App Check mentioned
100%
100%
App Check purpose explained
100%
100%
Multimodal structured output with large file handling
GoogleAIBackend initialization
100%
100%
Correct model name
0%
100%
Does NOT use gemini-1.5-flash
100%
100%
responseMimeType JSON config
100%
100%
Schema used for structured output
100%
100%
Inline data for image input
100%
100%
20MB threshold for large files
100%
100%
Cloud Storage fallback noted
100%
100%
Gemini Developer API chosen
75%
100%
Gemini model chosen for image analysis
100%
100%
JSON.parse on response
100%
100%
c3bb9d5
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.