Cometchat Flutter V6 Features logo

Cometchat Flutter V6 Features

Organization
cometchat
cometchat-flutter-v6-features

Enable a specific CometChat feature in a Flutter v6 app — polls, stickers, collaborative whiteboard/document, translation, link preview, AI smart replies, moderation, calls, push. Looks the feature up in the features oracle, then wires only what the kit does not already do. Triggers: 'add polls in flutter', 'enable stickers', 'turn on smart replies in flutter', 'enable message translation in flutter', 'add moderation', 'enable an extension in flutter'.

Overview

Publishercometchat
Repositorycometchat-skills
Skill namecometchat-flutter-v6-features
Stars
109
Forks
2
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Cometchat Flutter V6 Features 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/cometchat/cometchat-skills.git /tmp/cometchat-skills
mkdir -p .claude/skills
cp -r /tmp/cometchat-skills/skills/cometchat-flutter-v6-features .claude/skills/cometchat-flutter-v6-features
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cometchat Flutter V6 Features 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 Cometchat Flutter V6 Features 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 Cometchat Flutter V6 Features 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.

Ground truth: the feature-existence oracle is features.flutter-v6.json (pack root). A feature the user asks for MUST be an id there — if it is not listed, it does not exist; do not invent it. Exact dashboard steps come from the feature's docs_topic (dashboard paths rot — FETCH them). Widget names come from catalogs/flutter-v6.json.

Companion skills (read first)

  • cometchat-flutter-v6-core — install, credentials, init→login→render. This skill ASSUMES it.
  • cometchat-flutter-v6-components — the widget catalog features render through.

Use this skill when

The user wants to turn ON a capability: "add polls", "enable stickers", "turn on translation", "add smart replies", "add moderation", "enable an extension".

Prerequisites & install

Core done. Most features add NO package; voice-video-calls adds one (→ -calls), push adds Firebase (→ -push).

THE v6 RULE THAT CHANGES EVERYTHING

v6 deleted the entire v5 extension architecture. There is no UIKitSettings.extensions, no CometChatUIKitChatExtensions, no DataSource, no ChatConfigurator, no *ExtensionDecorator, no CometChatUIKit.getDataSource(). A dashboard-enabled extension surfaces automatically through MessageTemplateUtils — composer action sheet, message bubbles — with zero client registration code.

So for most extensions the correct answer is: flip the Dashboard toggle and write NO code. Emitting v5-style registration into a v6 app is a defect, not a harmless no-op. If the user already has such code, that is a migration problem (→ -migration).

Enable a feature (the oracle-driven flow)

  1. Look it up in features.flutter-v6.json. Match the request to an id. Not listed → say so; don't invent one.
  2. Branch on category + enablement:
    • default / auto → already on. Check needs_stitching: if true, the kit renders an affordance that is inert until the host navigates somewhere (thread indicator, search field) — wire it or hide it, never dead-end. Otherwise there is nothing to do; point at the ui_components if they want to restyle it (→ -customization).
    • extension / dashboard-extensionDashboard toggle only. Confirm it's on, then verify it appears (composer action sheet for polls/stickers/collaborative; bubbles for link-preview/translation/thumbnails). Write no registration code. Entries carry auto_rendered_ui: true — their widgets exist for styling, not for you to mount.
    • ai → Dashboard toggle (AI features may need an OpenAI key on the app) and the view must be surfaced. VERIFY per feature whether v6 auto-renders it or the host places CometChatAISmartRepliesView / CometChatAIConversationStarterView / CometChatAIConversationSummaryView. Plan-gating is often unknown — verify, don't assert.
    • package-install → calls (→ -calls) or push (→ -push). Do not re-derive those here.
    • dashboard-only (moderation) → configured ENTIRELY in the Dashboard; emit ZERO moderation UI. CometChatMessageList already renders blocked/moderated content and already ships a built-in "Report message" action. Hand-rolling either duplicates the built-in.
    • sdk-only (campaigns, AI agents, advanced moderation) → no kit widget; call the Chat SDK directly, looking the method up in ../cometchat-flutter-v6-core/references/docs-map.md → SDK docs. UI-Kit-first, SDK-fallback.

Announce anything you send via the SDK. The v6 Flutter events page now enumerates the ccMessage* events (DOCS-BACKLOG F6 corrected upstream — verified against cometchat/docs@2ebb1db, 2026-09-09); the guidance below matches both the page and the installed kit 6.1.0.

A message sent with CometChat.send*Message instead of CometChatMessageComposer does not reach kit widgets on its own — CometChat does not echo your own sends back through the realtime listener, so an on-screen CometChatMessageList only learns about it on its next fetch (which looks like "it works" if the list is opened fresh each time, and "nothing happens" if it is always mounted). Emit the event yourself in onSuccess:

dart
import 'package:cometchat_chat_uikit/cometchat_chat_uikit.dart';
// The barrel exports TWO enums named MessageStatus; ccMessageSent wants the core
// one, so import it under a prefix exactly as the kit's own composer does.
import 'package:cometchat_chat_uikit/shared_ui/src/clean_architecture/core/constants/enums.dart'
    as core_enums;

Future<void> post(CustomMessage msg) => CometChat.sendCustomMessage(
      msg,
      onSuccess: (sent) =>
          CometChatMessageEvents.ccMessageSent(sent, core_enums.MessageStatus.sent),
      onError: (e) {},
    );
  1. Wire only the ui_components the entry names, fetching props from the widget's .md twin.
  2. Respect VERIFY notes — any entry marked VERIFY (AI, notification-feed, campaigns, search dashboard-gating) must be confirmed against live docs before you state enablement steps.

Already ON by default in v6 — never offer these as "add a feature"

reactions · mentions (incl. @all) · quoted reply · threaded replies · read receipts · typing indicators · presence · mark-as-unread · report message · media sharing · voice notes. They are core messaging, not extensions. If asked, say they're already on and offer to customize them. (Their legacy extension pages exist but are marked deprecated — the oracle flags them.)

Deprecated — never suggest

email-replies, e2e-encryption: absent from the Flutter v6 extensions page and legacy docs-wide. Flagged deprecated: true in the oracle.

Common pitfalls (BAKED)

  • Writing v5 extension-registration code — the #1 v6 error (see above).
  • Mounting an auto_rendered_ui widget yourself (moderation view, flag dialog, sticker keyboard) — duplicates the built-in.
  • Claiming a feature that isn't in the oracle — the #1 hallucination.
  • Baking a dashboard nav path — it rots; FETCH it.
  • Offering reactions/mentions/threads as add-ons — already on.
  • Rendering a feature's widget without the Dashboard toggle → renders empty and looks broken.
  • Assuming an AI feature is on every plan — plan-gated; verify.

Verify it works

The feature actually works in the running app (a poll sends, a sticker appears, translation shows in the action sheet), and any Dashboard toggle it needs is ON. Renders empty ⇒ the toggle is off, not a code problem.

Close (after it builds): end with the shared 3-option selectable menu and WAIT — ① add another feature · ② customize theming · ③ test it manually (RULES.md §19).

Frequently asked questions

What does the Cometchat Flutter V6 Features AI skill do?

Enable a specific CometChat feature in a Flutter v6 app — polls, stickers, collaborative whiteboard/document, translation, link preview, AI smart replies, moderation, calls, push. Looks the feature up in the features oracle, then wires only what the kit does not already do. Triggers: 'add polls in flutter', 'enable stickers', 'turn on smart replies in flutter', 'enable message translation in flutter', 'add moderation', 'enable an extension in flutter'.

Why use Cometchat Flutter V6 Features on TypingMind?

Because you install it once and use it with any model. Cometchat Flutter V6 Features 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 Cometchat Flutter V6 Features in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cometchat/cometchat-skills/tree/main/skills/cometchat-flutter-v6-features. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cometchat Flutter V6 Features?

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 Cometchat Flutter V6 Features?

As many as you like. As long as a model supports skills, you can use Cometchat Flutter V6 Features with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cometchat Flutter V6 Features AI skill free?

Yes. It is published on GitHub by cometchat 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 👇