Firebase ai logic

Skill GDvega/super-android-kotlin-firebase-skill/skills/firebase-ai-logic

A modular Agent Skills repository for Android, Kotlin, Jetpack Compose and Firebase development.

Install

npx -y skills add GDvega/super-android-kotlin-firebase-skill --skill firebase-ai-logic

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use for Firebase AI Logic and Gemini integration in Android, safe prompts, privacy boundaries, model selection, fallback behavior and not exposing private keys.

SKILL.md

2.7 KB, as published. Nobody here has run it

Purpose

Add Gemini/AI features to Android apps safely, with clear privacy and fallback behavior.

When to use

Adding Firebase AI Logic or Gemini features.
Designing prompts or multimodal input.
Choosing cloud vs on-device AI.
Handling model errors, limits and fallback UX.

Inputs to inspect

AI use case and user value.
Data sent to model and privacy classification.
Firebase/Google AI provider choice.
Fallback and human review requirements.

Required workflow

Classify data and decide if AI is appropriate.
Choose Firebase AI Logic, backend proxy or on-device path.
Design prompts and output validation.
Handle rate limits, safety and offline fallback.
Add fakes/tests for AI boundaries.

Rules

Do not expose private API keys in the client.
Minimize sensitive data sent to models.
Do not rely on AI for critical irreversible decisions without review.
Validate structured outputs.
Provide deterministic fallback.

Related existing skills

Local skills to invoke

firebase-core
security-privacy
networking-retrofit-ktor
ui-state-design
testing

External companion skills to use when installed

Do not assume these companion skills are installed. Prefer the local skills above first, then consult Companion Skills for install and verification commands.

firebase/agent-skills — use for deeper Firebase product, Firestore, Security Rules or emulator workflow guidance when installed.

Files commonly touched

AI repository/service
prompt templates
ViewModel state
Firebase setup
tests/fakes

Commands to validate

./gradlew test
./gradlew assembleDebug
firebase emulators:start

Common mistakes to avoid

Hardcoding secret keys.
Sending unnecessary PII.
Trusting AI output without validation.
No fallback or error UX.

Checklist

Privacy reviewed.
Provider chosen.
Prompt/output validated.
Fallback exists.
Tests/fakes included.

Example prompts

Use $super-android-kotlin-firebase to add Gemini summaries for user notes.
Use $super-android-kotlin-firebase to review this AI feature for privacy.

Expected response style

Respond with: brief diagnosis, change plan, affected files, code or diff summary, validation commands, tests added or recommended, risks, and next step. For review tasks, lead with findings ordered by severity.

References

../../docs/audits/FUENTES_LOCALES.md
references/firebase-ai-logic-android.md
templates/ai-feature-boundary-template.md