Cometchat Android V6 Features logo

Cometchat Android V6 Features

Organization
cometchat
cometchat-android-v6-features

Add or enable a specific CometChat feature in an Android v6 app — receipts, typing, reactions, mentions, threads, search, polls, stickers, translation, link previews, AI smart replies / conversation starter / summary, AI agents, moderation, notification feed, campaigns — by resolving the ask to the feature oracle and taking the right enablement path (already-on vs Dashboard toggle vs Gradle package vs code wiring). Triggers: 'add search to my android chat', 'enable polls android', 'turn on smart replies android', 'add reactions android', 'is X supported in the android ui kit'.

Overview

Publishercometchat
Repositorycometchat-skills
Skill namecometchat-android-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 Android 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-android-v6-features .claude/skills/cometchat-android-v6-features
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cometchat Android 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 Android 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 Android 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: features.android-v6.json (the feature-existence + enablement oracle) + catalog android-v6.json + the live feature pages (core-features, extensions, ai-features, call-features, the guide-* recipes). A feature not in the oracle does NOT exist for this kit — say so; never invent one. Fetch component params from docs (corereferences/docs-map.md).

Companion skills (read first)

  • cometchat-android-v6-core — install, credentials, initFromSettings → login → render, hot-path callbacks, the fetch map. Assumed here, never repeated.
  • Deeper slices: cometchat-android-v6-extensions (the 8 Dashboard extensions in detail) · cometchat-android-v6-calls (voice/video) · cometchat-android-v6-push (FCM) · cometchat-android-v6-{kotlin,compose}-customization (styling a feature's UI).

Use this skill when

"add <feature> to my Android chat", "enable <feature>", "does the Android UI Kit support <X>?", "why isn't <feature> showing up?". The job: resolve the ask against the oracle, take the right enablement branch, wire only what needs wiring, and tell the user honestly what it needs (Dashboard? package? code?).

Prerequisites & install

Same kit + initFromSettings → login gate as core. Some features add a Gradle artifact (calls, push) or need a Dashboard toggle — the branch below says which.

Feature lookup — resolve the ask, then branch

  1. Find the id in features.android-v6.json (table below). No match ⇒ the kit has no built-in for it: check whether the Chat SDK covers it (core/references/docs-map.md → SDK section) and say plainly that there's no UI-Kit component.
  2. Read enablement and take exactly one branch:
    • auto — already ON in v6. Do NOT "add" it; confirm it's there and offer to customize it (cometchat-android-v6-{kotlin,compose}-customization). Applies to reactions, mentions, receipts, typing, presence, quoted replies, rich text, media, mark-as-unread, report.
    • dashboard-toggle / dashboard-extension — enable it in the CometChat Dashboard; the kit auto-integrates it after init+login, no client code. Your job: tell the user exactly where it will appear (composer action sheet, message list, bubble) and how to verify. Ask which are already enabled — you cannot read per-app Dashboard state.
    • gradle-package — add the artifact, then wire (calls: com.cometchat:calls-sdk-android + uiKit.enableCalling in assets/cometchat-settings.json; push: com.cometchat:push-notifications-android + Firebase). Route to the dedicated skill.
    • code-prop — the kit ships the component/affordance but the HOST wires it (a screen, a callback, a formatter). This is real work: build it, wire the round-trip, verify.
    • dashboard-only — no client code at all (moderation, campaigns); explain the effect users will see.
  3. Check needs_stitching (⚙ below) — a default-ON affordance that dead-ends until you wire a destination (or hide it). Wire it or hide it; never leave it inert.
  4. Guide-first: if the docs ship a guide-* recipe for this feature (see core/references/docs-map.md → "Task guides"), BUILD FROM the guide, then DIFF your implementation against it, then apply the hardening deltas (credentials via the settings file, init→login gate, thread targets, IME/insets sizing, listener teardown).
  5. Wire the feature's ui_components — fetch exact params for YOUR cohort from the component page's .md twin.

Feature table (BAKED from features.android-v6.json — ⚙ = needs stitching)

Feature idEnablementComponents
text-messagingautoCometChatMessageList, CometChatMessageComposer
media-file-attachmentsautoCometChatMessageComposer, CometChatMessageList
delivery-read-receiptsautoCometChatMessageList, CometChatReceipts, CometChatConversations
mark-as-unreadautoCometChatConversations
typing-indicatorsautoCometChatMessageList, CometChatConversations
user-presenceautoCometChatConversations, CometChatMessageHeader, CometChatStatusIndicator
reactionsautoCometChatMessageList
mentionsautoCometChatMessageComposer, CometChatMessageList, CometChatMentionsFormatter
rich-text-formattingautoCometChatMessageComposer, CometChatRichTextFormatter
quoted-repliesautoCometChatMessageList, CometChatMessageComposer
users-groupsautoCometChatUsers, CometChatGroups, CometChatGroupMembers
report-messageautoCometChatMessageList
threaded-repliescode-prop ⚙CometChatMessageList, CometChatThreadHeader, CometChatMessageComposer
message-searchcode-prop ⚙CometChatSearch
custom-message-typescode-propCometChatMessageList
text-formatterscode-propCometChatTextFormatter, CometChatMentionsFormatter, CometChatRichTextFormatter
notification-feedcode-propCometChatNotificationFeed
stickersdashboard-extensionCometChatMessageComposer, CometChatStickerBubble, CometChatStickerKeyboard
pollsdashboard-extensionCometChatMessageComposer, CometChatCreatePoll, CometChatPollBubble
collaborative-whiteboarddashboard-extensionCometChatMessageComposer, CometChatMessageList
collaborative-documentdashboard-extensionCometChatMessageComposer, CometChatMessageList
message-translationdashboard-extensionCometChatMessageList
link-previewdashboard-extensionCometChatMessageList
thumbnail-generationdashboard-extensionCometChatMessageList
message-shortcutsdashboard-extension ⚙CometChatTextFormatter
profanity-filterdashboard-extension LEGACYCometChatMessageList
smart-replydashboard-toggleCometChatMessageComposer
conversation-starterdashboard-toggleCometChatMessageList
conversation-summarydashboard-toggleCometChatMessageComposer
ai-assistantdashboard-toggle ⚙CometChatAIAssistantChatHistory, CometChatAIAssistantBubble, CometChatMessageList, CometChatMessageComposer
moderationdashboard-only— (dashboard rules; no client code)
campaignsdashboard-only— (authored in Dashboard)
voice-video-callsgradle-package ⚙CometChatCallButtons, CometChatIncomingCall, CometChatOutgoingCall, CometChatCallLogs, CometChatCallActivity
push-notificationsgradle-package ⚙— (SDK token registration + FCM)

Enablement rules that trip people up

  • reactions and mentions are ON BY DEFAULT in v6 (core messaging). Never offer to "add" or "enable" them — if asked, say they're already on and offer to customize them.
  • profanity-filter is LEGACY — its guide points at legacy docs; steer to moderation instead. Never suggest it as a new feature.
  • Dashboard-gated ≠ broken: if a toggled feature doesn't appear, the usual cause is the Dashboard toggle or a stale session — re-login after enabling.
  • Pinned messages / saved messages / thread subscription are NOT in the current v6 docs set (they're pending on a docs branch). Don't claim them; say they're not documented for v6 yet and offer the SDK path if one exists.
  • A feature's UI appears only after init + login succeed — a "missing feature" is often an init/login failure (core/references/troubleshooting.md).

Common pitfalls

Suggesting an auto feature as new work · hand-rolling a feature the kit auto-renders (translation, previews, stickers) · wiring a code-prop feature's entry point but no way back (dead-end) · a thread screen missing the user/group target (replies silently don't send) · assuming Dashboard state instead of asking · adding the calls/push artifact without the Dashboard side · guessing component params instead of fetching.

Verify it works

Every symbol you emitted is in the catalog (Tier-1) and the app compiles (./gradlew :app:assembleDebug # in YOUR app (npm run verify:fences:android-v6 is a pack-repo gate)). On device: the feature's UI appears where the docs say (composer action sheet / message list / bubble / its own screen); a stitched feature round-trips (open AND back); an auto feature was left alone; anything requiring the Dashboard was called out explicitly to the user with where-to-click. If it doesn't show, check init/login, then the Dashboard toggle, then re-login — in that order.

Frequently asked questions

What does the Cometchat Android V6 Features AI skill do?

Add or enable a specific CometChat feature in an Android v6 app — receipts, typing, reactions, mentions, threads, search, polls, stickers, translation, link previews, AI smart replies / conversation starter / summary, AI agents, moderation, notification feed, campaigns — by resolving the ask to the feature oracle and taking the right enablement path (already-on vs Dashboard toggle vs Gradle package vs code wiring). Triggers: 'add search to my android chat', 'enable polls android', 'turn on smart replies android', 'add reactions android', 'is X supported in the android ui kit'.

Why use Cometchat Android V6 Features on TypingMind?

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

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

Which AI models can use Cometchat Android 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 Android V6 Features?

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

Is the Cometchat Android 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 👇