Agent skill · Audited from source

Firebase

skill · alinaqi/claude-bootstrapMIT licenceAudited 14 Oct 2026 · source ea59a0c53d79

★ 707pushed today
✓SAFEGrade B · 89/100 · 14 Oct 2026 · ea59a0c
707repo stars · whole alinaqi/claude-bootstrap

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit ea59a0c53d79 and found no filesystem, network or shell access and no hard-coded secrets. What it does: Firebase Firestore, Auth, Storage, real-time listeners, security rules

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Firebase (alinaqi/claude-bootstrap)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/alinaqi/firebase

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium0 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS0
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (0)

No findings at any severity. We re-audit when the source changes.

Audit 0.4.1 · source sha ea59a0c53d79 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisheralinaqi GitHub userOwner of the repository this skill is read from
  • Source folderalinaqi/claude-bootstrap/skills/firebaseThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdictea59a0c53d79A new audit runs when the source changes
  • Repository statusNot archivedPushed today
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Firebase Firestore, Auth, Storage, real-time listeners, security rules

---
name: firebase
description: Firebase Firestore, Auth, Storage, real-time listeners, security rules
when-to-use: When working with Firebase services
user-invocable: false
paths: ["**/firebase*", "firestore.rules", "storage.rules", "firebase.json"]
effort: medium
---

# Firebase Skill


Firebase/Firestore patterns for web and mobile applications with real-time data, offline support, and security rules.

**Sources:** [Firebase Docs](https://firebase.google.com/docs) | [Firestore Best Practices](https://firebase.google.com/docs/firestore/best-practices) | [Security Rules](https://firebase.google.com/docs/rules)

---

## Core Principle

**Denormalize with purpose, secure with rules, scale horizontally.**

Firestore is a document database - embrace denormalization for read efficiency. Security rules are your server-side validation. Design for your access patterns.

---

## Firebase Stack

| Service | Purpose |
|---------|---------|
| **Firestore** | NoSQL document database with real-time sync |
| **Authentication** | User auth, OAuth, anonymous sessions |
| **Storage** | File uploads with security rules |
| **Functions** | Serverless backend (Node.js) |
| **Hosting** | Static site + CDN |
| **Extensions** | Pre-built solutions (Stripe, Algolia, etc.) |

---

## Project Setup

### Install Firebase CLI
```bash
# Install globally
npm install -g firebase-tools

# Login
firebase login

# Initialize in project
firebase init
```

### Initialize with Emulators
```bash
firebase init emulators

# Start local development
firebase emulators:start
```

### Project Structure
```
project/
├── firebase.json           # Firebase config
├── firestore.rules         # Security rules
├── firestore.indexes.json  # Composite indexes
├── storage.rules           # Storage security rules
└── functions/              # Cloud Functions
    ├── src/
    ├── package.json
    └── tsconfig.json
```

---

## Firestore Data Modeling

### Document Structure
```typescript
// Good: Flat documents with all needed data
interface Post {
  id: string;
  title: string;
  content: string;
  authorId: string;
  authorName: string;      // Denormalized for display
  authorAvatar: string;    // Denormalized
  tags: string[];
  likeCount: number;       // Aggregated counter
  createdAt: Timestamp;
  updatedAt: Timestamp;
}

// Collection: posts/{postId}
```

### When to Use Subcollections
```typescript
// Use subcollections for:
// 1. Unbounded lists (comments, messages)
// 2. Data with different access patterns
// 3. Data that grows independently

// posts/{postId}/comments/{commentId}
interface Comment {
  id: string;
  text: string;
  authorId: string;
  authorName: string;
  createdAt: Timestamp;
}
```

### Data Model Patterns

```typescript
// Pattern 1: Embedded data (bounded, always needed)
interface User {
  id: string;
  email: string;
  profile: {
    displayName: string;
    bio: string;
    avatar: string;
  };
  settings: {
    notifications: boolean;
    theme: 'light' | 'dark';
  };
}

// Pattern 2: Reference with denormalization
interface Order {
  id: string;
  userId: string;
  userEmail: string;  // Denormalized for display
  items: OrderItem[]; // Embedded (bounded)
  total: number;
  status: 'pending' | 'paid' | 'shipped';
}

// Pattern 3: Aggregation documents
// Keep counters in parent document
interface Channel {
  id: string;
  name: string;
  memberCount: number;  // Updated via Cloud Function
  messageCount: number;
}
```

---

## TypeScript SDK (Modular v9+)

### Initialize Firebase
```typescript
// lib/firebase.ts
import { initializeApp, getApps } from 'firebase/app';
import { getFirestore, connectFirestoreEmulator } from 'firebase/firestore';
import { getAuth, connectAuthEmulator } from 'firebase/auth';
import { getStorage, connectStorageEmulator } from 'firebase/storage';

const firebaseConfig = {
  apiKey: process.env.NEXT_PUBLIC_FIREBASE_API_KEY,
  authDomain: process.env.NEXT_PUBLIC_FIREBASE_AUTH_DOMAIN,
  projectId: process.env.NEXT_PUBLIC_FIREBASE_PROJECT_ID,
  storageBucket: process.env.NEXT_PUBLIC_FIREBASE_STORAGE_BUCKET,
  messagingSenderId: process.env.NEXT_PUBLIC_FIREBASE_MESSAGING_SENDER_ID,
  appId: process.env.NEXT_PUBLIC_FIREBASE_APP_ID
};

// Initialize only once
const app = getApps().length === 0 ? initializeApp(firebaseConfig) : getApps()[0];

export const db = getFirestore(app);
export const auth = getAuth(app);
export const storage = getStorage(app);

// Connect to emulators in development
if (process.env.NODE_ENV === 'development') {
  connectFirestoreEmulator(db, 'localhost', 8080);
  connectAuthEmulator(auth, 'http://localhost:9099');
  connectStorageEmulator(storage, 'localhost', 9199);
}
```

### CRUD Operations
```typescript
import {
  collection,
  doc,
  getDoc,
  getDocs,
  addDoc,
  setDoc,
  updateDoc,
  deleteDoc,
  query,
  where,
  orderBy,
  limit,
  startAfter,
  serverTimestamp,
  Timestamp
} from 'firebase/firestore';
import { db } from './firebase';

// Create
async function createPost(data: Omit<Post, 'id' | 'createdAt' | 'updatedAt'>) {
  const docRef = await addDoc(collection(db, 'posts'), {
    ...data,
    createdAt: serverTimestamp(),
    updatedAt: serverTimestamp()
  });
  return docRef.id;
}

// Read single document
async function getPost(postId: string): Promise<Post | null> {
  const docSnap = await getDoc(doc(db, 'posts', postId));
  if (!docSnap.exists()) return null;
  return { id: docSnap.id, ...docSnap.data() } as Post;
}

// Query with filters
async function getPostsByAuthor(authorId: string, pageSize = 10) {
  const q = query(
    collection(db, 'posts'),
    where('authorId', '==', authorId),
    orderBy('createdAt', 'desc'),
    limit(pageSize)
  );
  const snapshot = await getDocs(q);
  return snapshot.docs.map(doc => ({ id: doc.id, ...doc.data() } as Post));
}

// Pagination
async function getNextPage(lastDoc: Post, pageSize = 10) {
  const q = query(
    collection(db, 'posts'),
    orderBy('createdAt', 'desc'),
    startAfter(lastDoc.createdAt),

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit ea59a0c

Download folder ↗
npm install -g firebase-tools

Commands as the repository documents them: shown, never run by us. Our verdict covers commit ea59a0c53d79 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source ea59a0c53d79

README badge

For maintainers · shows the latest audit

ModelsAtlas: SAFE BMODELSATLASSAFE · B
[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/alinaqi/firebase/badge.svg)](https://modelsatlas.com/skills/alinaqi/firebase/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Add this badge to your README

[![ModelsAtlas: SAFE B](https://modelsatlas.com/skills/alinaqi/firebase/badge.svg)](https://modelsatlas.com/skills/alinaqi/firebase/)

Questions about Firebase

What does the Firebase skill do?
What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center
Is Firebase safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Firebase access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (ea59a0c53d79), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.