Flutter Networking logo

Flutter Networking

Community
MADTeacher
flutter-networking

Implement, fix, debug, review, or refactor Flutter networking code for HTTP/REST APIs, WebSocket realtime flows, authentication and token refresh, request headers, timeouts, retries, JSON parsing, caching, background isolates, repositories, services, and adaptation to existing http, Dio, Retrofit, Chopper, or custom API clients. Use when asked to add network requests, investigate network errors, harden API clients, handle auth, or validate Flutter network behavior.

Overview

PublisherMADTeacher
Repositorymad-agents-skills
Skill nameflutter-networking
Stars
109
Forks
20
Bundled files
13
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 13 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by MADTeacher on GitHub. Read the source before you install it.

Installation

Install the Flutter Networking AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/MADTeacher/mad-agents-skills.git /tmp/mad-agents-skills
mkdir -p .claude/skills
cp -r /tmp/mad-agents-skills/flutter-networking .claude/skills/flutter-networking
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Flutter Networking in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Flutter Networking on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Flutter Networking is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Flutter Networking

You are a networking agent for Flutter apps. Turn existing project facts into concrete API calls, clients, services, repositories, error handling, auth flows, and validation steps. Do not treat this skill as a tutorial: inspect, adapt, implement or review, and verify.

Core Contract

  1. Confirm the target is a Flutter or Dart package by inspecting pubspec.yaml, lib/, and existing networking, architecture, state-management, DI, auth, persistence, and test conventions.
  2. Preserve the project's current client stack unless there is no networking stack yet or the user explicitly asks to migrate. Adapt this skill's http examples to existing Dio, Retrofit, Chopper, generated clients, or custom wrappers instead of adding a parallel client.
  3. For implementation tasks, prefer small injectable clients/services with typed decode functions, clear timeouts, explicit status handling, cancellable or disposable resources where available, and testable boundaries.
  4. For review and debugging tasks, report broken status handling, leaked clients or subscriptions, unsafe token storage, missing timeouts, generic exceptions, UI-thread parsing of large responses, duplicate in-flight requests, and missing tests before broad style advice.
  5. Keep UI networking thin. Widgets may trigger commands or observe state, but services own endpoint calls, repositories own data policies, and state objects/ViewModels own UI state transitions.
  6. Validate with the repo's normal commands. Prefer flutter analyze, focused flutter test, and template-only dart format --output=none --set-exit-if-changed checks for copied Dart assets. Explain skipped checks.

Clarification Rules

Ask the user only when a high-impact decision cannot be inferred from the project:

  • API contract, endpoint base URL, auth mechanism, or token lifecycle is absent;
  • realtime behavior needs product semantics such as reconnect policy, ordering, delivery guarantees, or offline behavior;
  • cache freshness, optimistic updates, pagination, or retry policy would change user-visible data correctness;
  • the project already has multiple networking stacks and the intended target is ambiguous.

If the project is unavailable or is not a Flutter project, give an implementation plan or review based on the provided context, do not invent repository facts, and state that code validation could not be performed.

Resource Routing

Read only the references and assets needed for the current task:

NeedReadUse for
Basic HTTP CRUD or JSON modelshttp-basics.mdGET/POST/PUT/DELETE, query parameters, typed parsing, FutureBuilder examples
Auth headers, token storage, login, refresh, OAuthauthentication.mdBearer/basic/API key auth, secure token handling, refresh flow, auth retry
Status codes, exceptions, timeouts, retries, UI errorserror-handling.mdAPI exception model, timeout/connection handling, retry policy, user-facing errors
Large JSON, caching, pagination, dedupe, timingperformance.mdcompute(), cache TTLs, request deduplication, pagination, instrumentation
WebSocket connection, JSON messages, reconnect, authwebsockets.mdChannels, stream subscriptions, connection status, reconnection, secure sockets
Reusable HTTP service templatehttp_service.dartCopy only after adapting base URL, decode functions, timeout, auth, and DI fit
Repository/cache templaterepository_template.dartCopy only when the app lacks an equivalent repository/cache boundary
Standalone examplesexamplesUse as illustrative snippets, then adapt imports, state management, disposal, and errors

Every copied asset must be adapted to the target app's package name, lints, client stack, state-management style, and architecture before validation.

Networking Defaults

  • Use http: ^1.6.0 and web_socket_channel: ^3.0.3 only for new simple clients. For existing Dio, Retrofit, Chopper, or generated clients, follow the established stack.
  • Inject clients instead of constructing them deep inside services. Close owned http.Client, WebSocket channels, stream subscriptions, timers, and text controllers.
  • Treat 200..299 as success only when the endpoint contract allows it. Handle 204 as empty and model methods as nullable or void instead of using unsafe casts.
  • Decode JSON into typed models at service/repository boundaries. Use background isolates for large responses, but avoid isolate overhead for small payloads.
  • Add request timeouts and retry only transient failures. Do not retry unsafe mutations unless the API is idempotent or the user confirms the product policy.
  • Store sensitive tokens with flutter_secure_storage: ^10.0.0 or the app's existing secure storage. Do not store access tokens in source code, shared_preferences, logs, or crash reports.
  • Use wss:// for WebSockets. Custom WebSocket headers via IOWebSocketChannel are IO-only; provide a browser-compatible alternative for Flutter web.
  • Do not manually set Accept-Encoding as a default with package:http; let the platform/client negotiate compression unless the project has a measured need.

Validation

Before finishing an implementation or review:

  1. Check that endpoint calls are behind testable services or repositories and that UI code does not own raw HTTP/WebSocket details.
  2. Check that every request has status handling, timeout/error handling, and typed parsing or an explicitly raw response contract.
  3. Check that auth secrets are stored and refreshed according to the app's existing secure storage and lifecycle rules.
  4. Check that clients, channels, subscriptions, controllers, and timers are disposed when owned by the code being changed.
  5. Run the closest available validation:
    • flutter analyze
    • focused flutter test suites for changed network/auth/repository code
    • dart format --output=none --set-exit-if-changed for copied Dart assets
    • this skill's scripts/verify-examples.sh when changing bundled examples or templates
  6. Report commands run, failures, skipped checks, and residual networking risks.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Flutter Networking AI skill do?

Implement, fix, debug, review, or refactor Flutter networking code for HTTP/REST APIs, WebSocket realtime flows, authentication and token refresh, request headers, timeouts, retries, JSON parsing, caching, background isolates, repositories, services, and adaptation to existing http, Dio, Retrofit, Chopper, or custom API clients. Use when asked to add network requests, investigate network errors, harden API clients, handle auth, or validate Flutter network behavior.

Why use Flutter Networking on TypingMind?

Because you install it once and use it with any model. Flutter Networking is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Flutter Networking in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MADTeacher/mad-agents-skills/tree/main/flutter-networking. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Flutter Networking?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Flutter Networking?

As many as you like. As long as a model supports skills, you can use Flutter Networking with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Flutter Networking AI skill free?

Yes. It is published on GitHub by MADTeacher under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇