Agent skill

Firebase Cloud Functions

by evanca in evanca/flutter-ai-rules

A skill your agent uses when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.

MITAuto-check passedBackend & APIs

Install Firebase Cloud Functions

skills CLI
$ npx skills add evanca/flutter-ai-rules --skill firebase-cloud-functions -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install evanca/flutter-ai-rules firebase-cloud-functions --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/evanca/flutter-ai-rules.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/firebase-cloud-functions .claude/skills/firebase-cloud-functions && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
firebase-cloud-functions
GitHub stars
647
Token cost
~1.1k tokens
SKILL.md length
335 words
Files
1
Skills in repo
37
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.

  • Works in 5 steps: Setup and Configuration → Calling Functions → Error Handling → …
  • Calling callable functions (httpsCallable)
  • SKILL.md covers When to Use, 1. Setup and Configuration, 2. Calling Functions and 3. Error Handling, plus 3 more sections
  • Calls flutter

What it does

Firebase Cloud Functions is an agent skill from evanca/flutter-ai-rules. Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Backend & APIs, covering Serverless and Backend development. It works with Firebase and Flutter. The repository describes itself as: Flutter AI Skills and Rules for Claude, Codex, Cursor, and Other AI-Powered IDEs. The licence is MIT.

When your agent uses it

  • Calling callable functions (httpsCallable)
  • Passing data to server-side logic
  • Handling function errors/timeouts
  • Configuring regions

Example prompts

  • “/firebase-cloud-functions”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Setup and Configuration
  2. Calling Functions
  3. Error Handling
  4. Performance Optimization
  5. Testing and Development

What it can do on your machine

Read from SKILL.md and the folder at commit 7b9cce2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • flutter

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • firebase.google.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Firebase Cloud Functions loads about 1.1k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 335 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from evanca/flutter-ai-rules at commit 7b9cce2, republished under its MIT licence (© evanca). 335 words, ~1,125 tokens.

Download SKILL.mdSave it as .claude/skills/firebase-cloud-functions/SKILL.md (or your agent's skills folder).
name
firebase-cloud-functions
description
Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.
license
MIT

Firebase Cloud Functions Skill

This skill defines how to correctly call Firebase Cloud Functions from Flutter applications.

When to Use

Use this skill when:

  • Implementing callable Cloud Functions in a Flutter project.
  • Passing structured data to server-side functions and processing results.
  • Handling errors, timeouts, and retries for function calls.
  • Configuring region-specific function deployments.
  • Testing Cloud Functions locally with the Firebase Emulator Suite.

1. Setup and Configuration

flutter pub add cloud_functions
dart
import 'package:cloud_functions/cloud_functions.dart';

// After Firebase.initializeApp():
final functions = FirebaseFunctions.instance;
  • Initialize Firebase before using any Cloud Functions features.
  • For region-specific deployments, specify the region:
dart
final functions = FirebaseFunctions.instanceFor(region: 'europe-west1');
  • Deploy callable functions to Firebase before attempting to call them from the Flutter app.
  • Consider implementing App Check to prevent abuse of Cloud Functions.

2. Calling Functions

Use httpsCallable to reference a function, then call to invoke it:

dart
final result = await FirebaseFunctions.instance
  .httpsCallable('functionName')
  .call(data);
  • Pass data as a Map — it is automatically serialized to JSON:
dart
final result = await FirebaseFunctions.instance
  .httpsCallable('addMessage')
  .call({
    "text": messageText,
    "push": true,
  });
  • Access the result via the data property — it is automatically deserialized from JSON:
dart
final responseData = result.data;
// Cast to expected type if needed:
final message = result.data as Map<String, dynamic>;
final status = message['status'] as String;
  • Do not pass authentication tokens in function parameters — they are automatically included by the SDK.
  • Keep function names consistent between client code and server-side implementations.

3. Error Handling

Always wrap function calls in try-catch and check for FirebaseFunctionsException:

dart
try {
  final result = await FirebaseFunctions.instance
    .httpsCallable('functionName')
    .call(data);
  // Handle successful result
} on FirebaseFunctionsException catch (e) {
  switch (e.code) {
    case 'not-found':
      // Function does not exist
      break;
    case 'permission-denied':
      // User lacks permission
      break;
    case 'unavailable':
      // Service temporarily unavailable — retry
      break;
    default:
      debugPrint('Function error [${e.code}]: ${e.message}');
  }
} catch (e) {
  debugPrint('Unexpected error: $e');
}
  • Handle network connectivity issues and timeouts appropriately.
  • Provide meaningful error messages to users when function calls fail.
  • Implement retry logic with exponential backoff for transient errors (unavailable, deadline-exceeded).

4. Performance Optimization

Set a timeout appropriate to the expected execution time:

dart
final callable = FirebaseFunctions.instance.httpsCallable(
  'functionName',
  options: HttpsCallableOptions(
    timeout: const Duration(seconds: 30),
  ),
);
  • Minimize the amount of data passed to and from functions to reduce latency.
  • Use batch operations when possible to reduce the number of function calls.
  • Consider client-side caching for frequently used function results.
  • Account for cold starts for infrequently used functions.
  • Implement proper loading states in the UI while waiting for function responses.

5. Testing and Development

Use the Firebase Emulator Suite for local development and testing:

dart
FirebaseFunctions.instance.useFunctionsEmulator('localhost', 5001);
  • Test functions with both valid and invalid inputs to ensure proper validation.
  • Verify that functions handle authentication correctly.
  • Test with different user roles and permissions to ensure proper access control.
  • Implement unit tests for client-side function calling logic.

References

© evanca, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/firebase-cloud-functions of evanca/flutter-ai-rules.

Open the folder on GitHubat commit 7b9cce2

Compare with similar skills

Firebase Cloud Functions next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Firebase Cloud Functions compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Firebase Cloud Functions this skillevanca/flutter-ai-rules647—~1.1kAutomated safety check: PassMIT
Web3authWeb3Auth/web3auth-examples144—~1.4kAutomated safety check: PassMIT
Spec To Repoalirezarezvani/claude-skills28k—~2.7kAutomated safety check: NotesMIT
Retrieving Developer Knowledgegoogle/skills21k—~2kAutomated safety check: PassApache-2.0
App Buildersoftspark/ai-toolkit179—~2.2kAutomated safety check: PassApache-2.0
Arcgis To Portaljsdatopian/portaljs2.4k—~2kAutomated safety check: PassMIT

Similar skills

  • Web3auth

    Web3Auth/web3auth-examples

    Integrates MetaMask Embedded Wallets (Web3Auth) for non-custodial wallets via social login or custom JWT (Firebase, Auth0, Cognito).

    144 GitHub stars~1.4k tokensUpdated 4 days ago
    Backend & APIsAuto-check passed
  • Spec To Repo

    alirezarezvani/claude-skills

    A skill your agent uses when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I…

    28k GitHub stars~2.7k tokensUpdated 1 mo ago
    Backend & APIsAuto-check: notes
  • Official

    Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud, AI/Gemini, Android, Chrome, Web, Flutter, Go, Firebase, and other Google developer platforms.

    21k GitHub stars~2k tokensUpdated today
    Backend & APIsAuto-check passed
  • App Builder

    softspark/ai-toolkit

    App scaffolding: Next.js, Vite, Nuxt, Astro, FastAPI, Django, Laravel, RN, Flutter.

    179 GitHub stars~2.2k tokensUpdated today
    Backend & APIsAuto-check passed
  • Arcgis To Portaljs

    datopian/portaljs

    Migrate a whole ArcGIS Hub site into a PortalJS Arc portal end-to-end.

    2.4k GitHub stars~2k tokensUpdated 29 days ago
    Backend & APIsAuto-check passed
  • Nextjs Ssr

    asmyshlyaev177/test-proxy-recorder

    Tag server-side fetches with the x-test-rcrd-id session header so SSR is recorded under the correct Playwright test session.

    112 GitHub stars~4.4k tokensUpdated 3 days ago
    Backend & APIsAuto-check passed

More from evanca/flutter-ai-rules

All 37 skills in this repo
  • Code Review

    evanca/flutter-ai-rules

    A skill your agent uses when asked to review a PR, MR, branch, or diff, audit changed files, or check code quality.

    647 GitHub stars~2.4k tokensUpdated 23 days ago
    Auto-check passed
  • Developing Genkit Dart

    evanca/flutter-ai-rules

    A skill your agent uses when building AI agents in Dart, implementing Genkit flows or tools, integrating LLMs into Dart or Flutter applications, or using Genkit Dart plugins.

    647 GitHub stars~961 tokensUpdated 23 days ago
    Auto-check passed
  • Generate Images With Firebase AI

    evanca/flutter-ai-rules

    A skill your agent uses when generating or editing images from Flutter/Dart with Firebase AI Logic and a Gemini image model (Nano Banana), making the first call work, choosing Gemini Developer API…

    647 GitHub stars~2.3k tokensUpdated 23 days ago
    Auto-check passed
  • Flutter Use Column Row First

    evanca/flutter-ai-rules

    A skill your agent uses when building any Flutter screen or component to choose responsive Row, Column, Expanded, Flexible, and Spacer layouts before fixed-size or coordinate-based alternatives.

    647 GitHub stars~1.3k tokensUpdated 23 days ago
    Auto-check passed
  • Architecture Feature First

    evanca/flutter-ai-rules

    A skill your agent uses when creating a feature, designing folder structure, adding repositories/services/view models, wiring dependency injection, or deciding which layer owns logic.

    647 GitHub stars~1.9k tokensUpdated 23 days ago
    Auto-check passed
  • Bloc

    evanca/flutter-ai-rules

    A skill your agent uses when creating a Cubit or Bloc, modeling state with sealed classes or status enums, wiring BlocBuilder/BlocListener/BlocProvider, writing bloc tests, or choosing between Cubit…

    647 GitHub stars~2.8k tokensUpdated 23 days ago
    Auto-check passed

Works with

Questions about Firebase Cloud Functions

What does Firebase Cloud Functions do?

A skill your agent uses when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite. Firebase Cloud Functions is an agent skill from evanca/flutter-ai-rules. Use when calling callable functions (httpsCallable), passing data to server-side logic, handling function errors/timeouts, configuring regions, or testing with the Emulator Suite.

When should I use Firebase Cloud Functions?

Firebase Cloud Functions fits situations like: calling callable functions (httpsCallable); passing data to server-side logic; handling function errors/timeouts; configuring regions.

How do I install Firebase Cloud Functions in Claude Code?

Run `npx skills add evanca/flutter-ai-rules --skill firebase-cloud-functions -a claude-code`. Or copy the skill folder (skills/firebase-cloud-functions in evanca/flutter-ai-rules) into .claude/skills/firebase-cloud-functions in your project. Claude Code loads it when a task matches its description.

How do I install Firebase Cloud Functions in Codex?

Run `npx skills add evanca/flutter-ai-rules --skill firebase-cloud-functions -a codex`. Or copy the skill folder (skills/firebase-cloud-functions in evanca/flutter-ai-rules) into .agents/skills/firebase-cloud-functions in your project. Codex loads it when a task matches its description.

Can I use Firebase Cloud Functions in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add evanca/flutter-ai-rules --skill firebase-cloud-functions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/firebase-cloud-functions, .gemini/skills/firebase-cloud-functions, .github/skills/firebase-cloud-functions and .opencode/skills/firebase-cloud-functions in your project.

What does Firebase Cloud Functions need to run?

Going by SKILL.md and its folder, Firebase Cloud Functions needs the command-line tools its instructions call (flutter).

Does Firebase Cloud Functions access the network?

SKILL.md names 1 domain. As links in the text: firebase.google.com. This is read from the text; nothing was executed.

Is Firebase Cloud Functions safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Firebase Cloud Functions use?

Firebase Cloud Functions is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Firebase Cloud Functions use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Firebase Cloud Functions?

Skills that share tags, products or a category with Firebase Cloud Functions: Web3auth (Web3Auth/web3auth-examples, 144 stars), Spec To Repo (alirezarezvani/claude-skills, 28k stars), Retrieving Developer Knowledge (google/skills, 21k stars) and App Builder (softspark/ai-toolkit, 179 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Firebase Cloud Functions?

evanca (a GitHub user) maintains it in evanca/flutter-ai-rules, which has 647 GitHub stars. The repository holds 37 skills in this directory. The repository was last updated on September 14, 2026.

Source: evanca/flutter-ai-rules on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.