Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
How it works
Ask it something hard.
📎 ai-skill-for-firebase.txtLOADED ✓
Design the Firestore model for a team task app (workspaces, members, tasks, comments) and write rules so members only see their workspace.
CLAUDE · WITH THIS SKILLYou get: a collection layout (workspaces/{id}, workspaces/{id}/tasks/{taskId}, tasks/{id}/comments) with a members map on the workspace doc for rule lookups -> the queries per screen and a firestore.indexes.json with the composite indexes -> firestore.rules with isMember(workspaceId) using get(), field validation on create and protected fields on update -> a rules-unit-testing spec for the emulator -> a one-line note on read costs of get() in rules and the denormalised alternative -> next action: run firebase emulators:start and the test file.
Questions before you buy? A person answers, usually the same day: hello@kissmyskills.com
// the file itself
Read it before you buy it.
The first lines of the file your AI will read, exactly as delivered. Nothing rewritten for the page.
Use the name Once the file is loaded, talk to it by name: “Serge, check this page.” That is what the name is for. It also keeps several skills apart in one chat.
// the skill your AI runs on
You are a senior Firebase engineer working in Firestore, Authentication, Security Rules, Cloud Functions and the Emulator Suite. You have been activated to hand the user a data model, pasteable rules and an idempotent function, with the deploy command.
KissMySkills.com | Install: paste this whole file into Claude Projects (Project instructions), a custom GPT (Instructions), a Gemini Gem, or your AI's system prompt. Then just ask questions the way you normally would. You are a senior Firebase engineer embedded in the user's daily app work: web, mobile or Flutter apps with Firebase as the backend. You optimise for data models that scale, Security Rules that actually protect data, cheap idempotent Cloud Functions, and an Emulator Suite workflow so nothing is tested in production by accident. You are direct and practical: real console paths, real CLI commands, pasteable rules and code. · Products: Firestore, Realtime Database, Authentication, Cloud Storage, Cloud Functions, Hosting, FCM, Remote Config, Crashlytics, App Check, Extensions. · Firestore: collections, documents, subcollections, collection group queries; 1 MiB document limit; composite indexes for multi-field queries; no joins, so denormalise; batched writes and transactions; startAfter cursors; onSnapshot listeners. · Authentication: Email/Password, phone, Google, Apple, anonymous, custom tokens; custom claims via Admin SDK setCustomUserClaims; onAuthStateChanged; Identity Platform for MFA and SAML. · Security Rules: match, allow read, write: if, request.auth, request.resource.data, resource.data, get() and exists(), helper functions; unit tests with @firebase/rules-unit-testing. Rules do not filter queries. · Cloud Functions 2nd gen: onRequest, onCall, onDocumentCreated, onDocumentUpdated, onSchedule, onObjectFinalized; region, memory, minInstances; secrets via defineSecret; idempotency; firebase deploy --only functions:name. · Admin SDK bypasses rules; FieldValue.serverTimestamp(), increment(); batches up to 500 ops. · Client SDKs: modular JS, Swift, Kotlin, FlutterFire, React Native Firebase. · CLI: firebase init, emulators:start, deploy, use, hosting:channel:deploy, firestore:delete. · Emulator Suite: Auth, Firestore, Storage, Functions, Hosting; UI on localhost:4000; connectFirestoreEmulator; --import and --export-on-exit. · Pricing: Spark (free) vs Blaze (required for 2nd gen functions and outbound networking); Firestore billed per read, write, delete, storage. Never quote prices. · Gotchas: whole-collection reads on every render; listeners never unsubscribed; allow read, write: if true; index missing in production; hot document counters. · Platform and SDK: web, iOS, Android, Flutter, React Native, or Admin SDK server-side?
83 lines · .txt · instant download
// what's inside
What's inside this skill
Firestore data models with the queries and composite indexes each screen needs
Complete Security Rules with helper functions and emulator unit tests
Cloud Functions 2nd gen code with secrets, regions and deploy commands
Auth custom claims, Hosting rewrites, Emulator Suite and cost reviews
Web, mobile and Flutter developers who build and run apps on Firebase and want production-safe backend code.
// two ways to get it
Use it inside your AI, or download it once.
Library plan
This skill and 2,500+ others, inside your chat
$9/mocancel anytime, or $59 a year
All 2,500+ skills, prompt packs and agents, loaded the moment you ask
Nothing to download or paste: connect once in Claude, ChatGPT, Claude Code or Cursor
New skills every week and 10 catalog files a month to download
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
// ask your assistant
Or let your AI set up this skill for you.
Go to kissmyskills.com/pages/connector and set up the "AI Skill for Firebase" skill (handle: ai-skill-for-firebase) for me
Paste it into Claude, ChatGPT, Claude Code, Cursor or Codex. Your AI walks you through connecting KissMySkills (about 3 minutes, 7-day free trial) and loads the skill. What your AI will read →
What you're actually buying
This Firebase AI skill turns Claude or ChatGPT into a senior Firebase engineer inside your app project. Describe the feature and you get a Firestore collection layout with the composite indexes it needs, complete firestore.rules with helper functions and a rules unit test, a Cloud Functions 2nd gen trigger or callable in TypeScript with secrets and idempotency, an Auth flow with custom claims, or a firebase.json for Hosting rewrites and the Emulator Suite.
It knows the modular JS SDK, Admin SDK, FlutterFire and native SDKs, Storage rules, FCM, App Check, Spark versus Blaze limits and the mistakes that show up on the bill: open listeners, whole-collection reads, hot documents, rules that allow everything. It does not deploy, run or change anything in your Firebase project; it writes the code, rules and commands, and you run them, ideally against the emulators first.
Works in Claude, ChatGPT and Gemini. One purchase, download the file, install in under 2 minutes. Pairs with Rami, DevOps Engineer, the persona skill; this one is the helper inside Firebase.
// how to install
Under 2 minutes
Four steps. Any AI chat.
01
Download the file
After checkout, the download link lands in your inbox. Save the .txt file anywhere on your device.
02
Open your AI chat
Any AI chat you already use: Claude, ChatGPT, Gemini, Grok, Copilot or another.
03
Paste the prompt
Open the .txt file, copy the prompt section and paste it into Claude or ChatGPT - or add it to a Project so it is always there.
04
Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required.
With Library there is nothing to download. Connect your AI once, then ask for any skill by name.
It works as a Firebase AI assistant inside Claude or ChatGPT. You describe the feature or the problem, and it delivers Firestore data models with indexes, Security Rules with tests, Cloud Functions code, Auth and custom claims setups, firebase.json configs and the exact CLI commands, with console paths where needed.
Does it deploy or change my Firebase project for me?+
No. The skill does not deploy rules, run functions or touch your Firebase console. It writes the rules, code and commands, marks assumptions, and tells you to test in the Emulator Suite before firebase deploy.
Can it write Firebase Security Rules that are actually safe?+
Yes. It writes Firestore and Storage rules with helper functions for ownership and roles from custom claims, validates request.resource.data fields, blocks protected field updates, never uses allow if true outside a labelled local example, and adds a rules unit test you run against the Firebase emulator.
Does it cover Cloud Functions 2nd gen and the Firebase CLI?+
Yes. It writes 2nd gen triggers, callables and scheduled functions with region, memory, minInstances and defineSecret, explains idempotency and retries, and gives the Firebase CLI commands for emulators, targeted deploys with --only, preview channels and index management.
Ready to give your AI a specialist?
This one and 2,500+ others, inside Claude, ChatGPT, Claude Code, Codex or Cursor. Cancel anytime.