Summary
This gets you up and running with Firebase AI Logic, which lets you call Gemini models directly from client apps without managing a backend. It covers the full setup flow including the critical npx firebase-tools init ailogic command that actually provisions the service, multimodal input handling for images and PDFs, structured JSON output, and streaming responses. The docs are clear about App Check being mandatory for production to prevent quota abuse, and they emphasize using the Gemini Developer API by default since it has a free tier. One nice touch is the hybrid on-device mode for web that automatically falls back to cloud when Gemini Nano isn't available locally.
Install to Claude Code
npx -y skills add firebase/agent-skills --skill firebase-ai-logic-basics --agent claude-codeInstalls into .claude/skills of the current project.
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Files
SKILL.md
Select a file.
Featured
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
