- Home
- Skills
- Agents & Orchestration
- second brain android
More screenshots
Works with the AI Agents you already use
second brain android
⏺ Builds a private "second brain" Android app (Kotlin + Jetpack Compose) that captures your notifications, tracks habits with reminders, and gives you daily AI briefings, all kept on your phone.
$10
second brain android
Example session with this skill installed
Scaffold a new Android app named 'NeuroLog' (com.dev.neurolog) in ~/projects/neurolog with the ai, capture, and habits modules.
- Read your context and instructions
- Compiled the second brain android
Project NeuroLog has been scaffolded successfully. The base template was merged with the requested modules, and dependencies for AI-driven habit tracking are now mapped.
NeuroLog is ready
Built: base, ai, capture, habits at ~/projects/neurolog. ./gradlew assembleDebug testDebugUnitTest: 24 tests pass.
On the phone, once:
- Open Settings -> Notification Access and enable NeuroLog to begin capturing data.
- Enter your Groq or OpenRouter API key in the app's AI settings to enable chat.
Next steps:
- Run
./gradlew installDebugto deploy to a physical device for testing the notification listener. - Modify
AutoTagger.ktto define custom logic for how different apps are categorized in your feed. - Update the system prompt in the
reflectionmodule to change the tone of your daily AI briefings.
Later sessions: the generated CLAUDE.md holds the architecture rules, so the next session continues the same way. Utilizing the ContextSource pattern will allow you to add new data types to the AI's memory.
Connects securely to your tools. The creator never sees your data.
About this skill
Building a personal "second brain" on Android usually requires wrestling with complex background services, multi-device synchronization, and fragmented system permissions. This skill provides a tested foundation for creating private, offline-first Android applications that capture your life data and process it with local or cloud AI.
What it does
- Scaffolds Kotlin apps using a modular architecture based on Jetpack Compose, Koin, and Room.
- Captures system data by automating the collection of notifications, screen time, and Health Connect metrics.
- Integrates private AI to provide chat interfaces and automated daily briefings using Groq, OpenRouter, or local Ollama servers.
- Enables serverless sync between phones and tablets using peer-to-peer Bluetooth and Wi-Fi.
- Connects Obsidian vaults to treat local Markdown files as an active agenda within the app.
How it works
- Define the project by specifying the app name, package ID, and desired feature modules like
capture,habits, orhealth. - Run the scaffold script to generate a buildable Kotlin project with all dependencies, module bindings, and database migrations resolved.
- Verify the environment using bundled Gradle tasks to ensure the SDK, JDK, and baseline unit tests are green.
- Tailor the features by modifying the AI prompts, UI themes, or custom data sources following the architectural guidelines.
Frameworks & tools
Kotlin, Jetpack Compose, Room (SQLite), Koin (DI), WorkManager, Health Connect, and Python 3 for the scaffolding engine.
Why this beats prompting it yourself
Writing reliable background workers and notification listeners from scratch in modern Android is prone to silent failures and battery-drain issues. This skill uses a reference architecture that handles these edge cases and ensures all personal data remains strictly on-device.
Use cases
- Build a life logger that automatically tags and summarizes incoming notifications.
- Create a habit tracker that correlates screen time with fitness data from a wearable.
- Develop a private AI assistant that answers questions based on a local Obsidian vault.
- Scaffold a serverless journal that syncs across multiple Android devices.
Known limitations
Requires a local environment with Python 3 and the Android SDK. Some modules like Health Connect or Notification Access require manual permission grants on a physical device to function.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires Python 3 and Android SDK. Certain features like Health Connect or Notification Access require manual system-level permission grants on a physical device.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 23 days ago
- Accounts
Groq
Google AI
Openrouter
Gradle
- Software
- Recommended
Python
Permissions
Allowed Hosts