sickn33/antigravity-awesome-skills/earllm-build

Trust tier 2
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Build, maintain, and extend the EarLLM One Android project — a Kotlin/Compose app that connects Bluetooth earbuds to an LLM via voice pipeline.

Install

npx vskill@latest install sickn33/antigravity-awesome-skills/earllm-build

SKILL.md

EarLLM One — Build & Maintain

Overview

Build, maintain, and extend the EarLLM One Android project — a Kotlin/Compose app that connects Bluetooth earbuds to an LLM via voice pipeline.

When to Use This Skill

  • When the user mentions "earllm" or related topics
  • When the user mentions "earbudllm" or related topics
  • When the user mentions "earbud app" or related topics
  • When the user mentions "voice pipeline kotlin" or related topics
  • When the user mentions "bluetooth audio android" or related topics
  • When the user mentions "sco microphone" or related topics

Do Not Use This Skill When

  • The task is unrelated to earllm build
  • A simpler, more specific tool can handle the request
  • The user needs general-purpose assistance without domain expertise

How It Works

EarLLM One is a multi-module Android app (Kotlin + Jetpack Compose) that captures voice from Bluetooth earbuds, transcribes it, sends it to an LLM, and speaks the response back.

Project Location

C:\Users\renat\earbudllm

Module Dependency Graph

app ──→ voice ──→ audio ──→ core-logging
│ │
├──→ bluetooth ──→ core-logging
└──→ llm ──→ core-logging

Modules And Key Files

ModulePurposeKey Files
core-loggingStructured logging, performance trackingEarLogger.kt, PerformanceTracker.kt
bluetoothBT discovery, pairing, A2DP/HFP profilesBluetoothController.kt, BluetoothState.kt, BluetoothPermissions.kt
audioAudio routing (SCO/BLE), capture, headset buttonsAudioRouteController.kt, VoiceCaptureController.kt, HeadsetButtonController.kt
voiceSTT (SpeechRecognizer + Vosk stub), TTS, pipelineSpeechToTextController.kt, TextToSpeechController.kt, VoicePipeline.kt
llmLLM interface, stub, OpenAI-compatible clientLlmClient.kt, StubLlmClient.kt, RealLlmClient.kt, SecureTokenStore.kt
appUI, ViewModel, Service, Settings, all screensMainViewModel.kt, EarLlmForegroundService.kt, 6 Compose screens

Build Configuration

  • SDK: minSdk 26, targetSdk 34, compileSdk 34
  • Build tools: AGP 8.2.2, Kotlin 1.9.22, Gradle 8.5
  • Compose BOM: 2024.02.00
  • Key deps: OkHttp, AndroidX Security (EncryptedSharedPreferences), DataStore, Media

Target Hardware

DeviceModelKey Details
PhoneSamsung Galaxy S24 UltraAndroid 14, One UI 6.1, Snapdragon 8 Gen 3
EarbudsXiaomi Redmi Buds 6 ProBT 5.3, A2DP/HFP/AVRCP, ANC, LDAC

Critical Technical Facts

These are verified facts from official documentation and device testing. Treat them as ground truth when making decisions:

  1. Bluetooth SCO is limited to 8kHz mono input on most devices. Some support 16kHz mSBC. BLE Audio (Android 12+, TYPE_BLE_HEADSET = 26) supports up to 32kHz stereo. Always prefer BLE Audio when available.
  1. `startBluetoothSco()` is deprecated in API 34; `setCommunicationDevice` was added in API 31. Use AudioManager.setCommunicationDevice(AudioDeviceInfo) and clearCommunicationDevice() instead. The project already implements both paths in AudioRouteController.kt.
  1. Samsung One UI 7/8 has a known HFP corruption bug where A2DP playback corrupts the SCO link. The app handles this with silence detection and automatic fallback to the phone's built-in mic.
  1. Redmi Buds 6 Pro tap controls must be set to "Default" (Play/Pause) in the Xiaomi Earbuds companion app. If set to ANC or custom functions, events are handled internally by the earbuds and never reach Android.
  1. Android 14+ requires `FOREGROUND_SERVICE_MICROPHONE` permission and foregroundServiceType="microphone" in the service declaration. RECORD_AUDIO must be granted before startForeground().
  1. `VOICE_COMMUNICATION` audio source enables AEC (Acoustic Echo Cancellation), which is critical to prevent TTS audio output from feeding back into the STT microphone input. Never change this source without understanding the echo implications.
  1. Never play TTS (A2DP) while simultaneously recording via SCO. The correct sequence is: stop playback → switch to HFP → record → switch to A2DP → play response.

Data Flow

Headset button tap
→ MediaSession (HeadsetButtonController)
→ TapAction.RECORD_TOGGLE
→ VoicePipeline.toggleRecording()
→ VoiceCaptureController captures PCM (16kHz mono)
→ stopRecording() returns ByteArray
→ SpeechToTextController.transcribe(pcmData)
→ LlmClient.chat(messages)
→ TextToSpeechController.speak(response)
→ Audio output via A2DP to earbuds

Adding A New Feature

  1. Identify which module(s) are affected
  2. Read existing code in those modules first
  3. Follow the StateFlow pattern — expose state via MutableStateFlow / StateFlow
  4. Update MainViewModel.kt if the feature needs UI integration
  5. Add unit tests in the module's src/test/ directory
  6. Update docs if the feature changes behavior

Modifying Audio Capture

  • VoiceCaptureController.kt handles PCM recording at 16kHz mono
  • WAV headers use hex byte values (not char literals) to avoid shell quoting issues
  • VU meter: RMS calculation → dB conversion → normalized 0-1 range
  • Buffer size: getMinBufferSize().coerceAtLeast(4096)

Changing Bluetooth Behavior

  • BluetoothController.kt manages discovery, pairing, profile proxies
  • Earbuds detection uses name heuristics: "buds", "earbuds", "tws", "pods", "ear"
  • Always handle both Bluetooth Classic and BLE Audio paths

Modifying The Llm Integration

  • LlmClient.kt defines the interface — keep it generic
  • StubLlmClient.kt for offline testing (500ms simulated delay)
  • RealLlmClient.kt uses OkHttp to call OpenAI-compatible APIs
  • API keys stored in SecureTokenStore.kt (EncryptedSharedPreferences)

Generating A Build Artifact

After code changes, regenerate the ZIP:

powershell
## From Project Root
powershell -Command "Remove-Item 'EarLLM_One_v1.0.zip' -Force -ErrorAction SilentlyContinue; Compress-Archive -Path (Get-ChildItem -Exclude '*.zip','_zip_verify','.git') -DestinationPath 'EarLLM_One_v1.0.zip' -Force"

Running Tests

bash
./gradlew test --stacktrace # Unit tests
./gradlew connectedAndroidTest # Instrumented tests (device required)

Phase 2 Roadmap

  • Real-time streaming voice conversation with LLM through earbuds
  • Smart assistant: categorize speech into meetings, shopping lists, memos, emails
  • Vosk offline STT integration (currently stubbed)
  • Wake-word detection to avoid keeping SCO open continuously
  • Streaming TTS (Android built-in TTS does NOT support streaming)

Stt Engine Reference

EngineSizeWERStreamingBest For
Vosk small-en40 MB~10%YesReal-time mobile
Vosk lgraph128 MB~8%YesBetter accuracy
Whisper tiny40 MB~10-12%No (batch)Post-utterance polish
Android SpeechRecognizer0 MBvariesYesOnline, no extra deps

Best Practices

  • Provide clear, specific context about your project and requirements
  • Review all suggestions before applying them to production code
  • Combine with other complementary skills for comprehensive analysis

Common Pitfalls

  • Using this skill for tasks outside its domain expertise
  • Applying recommendations without understanding your specific context
  • Not providing enough project context for accurate analysis

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.

Treat the named personal checkout, file paths and past build outcomes as upstream historical context; locate and inspect the user’s current project before claiming they exist or work. Bluetooth sample-rate/routing capability depends on device, OS and codec; negotiate/verify supported formats instead of promising universal 16/24 kHz support. Before ZIP export, use an explicit source-file allowlist excluding secrets, .env, signing keys, credentials, recordings, logs and build caches. Audio/cloud processing needs consent. See Android AudioManager).

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
25,475
Repository forks
4,359
Repository npm downloads, 7 days
11,772
7-day trend score
72

Stars and forks are for the whole GitHub repository, not this skill alone. Downloads are for the repository's npm package. Refreshed 19 Mar 2026, 7 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/sickn33/antigravity-awesome-skills/earllm-build/badge)](https://verified-skill.com/skills/sickn33/antigravity-awesome-skills/earllm-build)

Something wrong with this skill or its page? Tell us.