alinaqi/maggy

AI Engine Optimization helps shape pages for AI search engines and chat answers. It uses semantic triples, page templates, and content clusters to improve how content is cited in generated responses.

AI Models Reference lists current Claude, OpenAI, Gemini, Eleven Labs, Replicate, and related model choices with example APIs. Use it when you need to pick a model for reasoning, code, vision, embeddings, voice, or image generation.

AWS Aurora covers serverless v2, RDS Proxy, Data API, and connection pooling for MySQL- and PostgreSQL-compatible workloads. Use it when setting up Aurora-backed apps, especially Lambda and other serverless services.

AWS DynamoDB covers single-table design, access-pattern modeling, and GSI patterns for building queries around how data is read. Use it when designing DynamoDB schemas or implementing SDK v3 access in TypeScript or Python.

Agent Teams coordinates a default roster of Claude Code agents for feature work. It enforces a fixed TDD pipeline from spec and tests through review, security checks, and PR creation.

Agentic Development builds autonomous AI agents that plan, use tools, and verify multi-step tasks. It uses Pydantic AI for Python and Claude Agent SDK for Node.js/Next.js projects.

Android Java builds Android app code with MVVM, ViewBinding, repositories, and instrumentation tests. Use it when structuring Java-based Android screens, data flow, and UI tests.

Android Kotlin covers Android app development with Coroutines, Jetpack Compose, Hilt, Room, and MockK. Use it for building feature screens, stateful ViewModels, repositories, and tests in Kotlin.

Autonomous Testing generates, runs, evaluates, and fixes tests for a codebase by scanning for coverage gaps and using AI to classify failures. Use it for automated test creation, regression checks, and repair loops across Python, TypeScript, API, and web projects.

Azure Cosmos DB explains partition key design, consistency tradeoffs, change feed, and SDK usage for NoSQL workloads. Use it when modeling data or writing TypeScript access code for Cosmos DB.

Base defines universal coding constraints, architectural patterns, and TDD rules for writing simple, maintainable code. Use it when setting project standards, organizing specs, or tracking atomic todos.

Build In Public helps you write and time posts about what you shipped, learned, and changed. Use it when sharing engineering decisions, failures, and launch updates without exposing sensitive details.

CPG Analysis uses Joern and CodeQL for deep control-flow, data-flow, and taint analysis. Use it for security audits, vulnerability detection, dead code checks, and cross-function impact analysis.

Cloudflare D1 helps you set up and use Cloudflare’s SQLite database with Workers, Drizzle ORM, and migrations. Use it when building edge apps that need typed database access and versioned schema changes.

Code Deduplication prevents semantic code duplication by checking a code index before adding new functions. It is used to reuse or extend existing capabilities and keep the codebase from growing redundant implementations.

Code Graph uses an AST-based code graph to find symbols, trace dependencies, and assess blast radius before reading files. Use it for planning and navigating codebases in Claude Code via MCP.

Code Review enforces automated reviews before commits and deployments, with ADR gate checks for architectural compliance. Use it to run Claude, Codex, Gemini, or multiple engines on the same change.

Codex Review uses OpenAI Codex CLI to review code for bugs, security flaws, and quality issues. Use it in the terminal, PR comments, or CI for automated review of changes.

Commit Hygiene keeps commits atomic and pull requests small enough to review. Use it when you need to decide whether to commit, split changes, or stack work into cleaner steps.

Council Review validates plans, architecture changes, and PRs with a multi-model panel before execution. Use it when you want independent review through validate-plan or review workflows.

Credentials Management loads API keys from a centralized access file and maps them to project environment variables. Use it when a project needs secure setup for services like OpenAI, Anthropic, Stripe, or Supabase.

Cross-Agent Delegation routes coding tasks between Claude, Kimi, and Codex using iCPG signals and mnemos checkpoints. Use it when you want automated delegation, scoring, and post-change review in Claude Code.

Database Schema Awareness reads the schema before database work so you verify columns, types, and relationships before writing queries or models. Use it to prevent column-name and type mismatches and to guide generated types.

Existing Repository analyzes an established codebase to identify its structure, conventions, and tooling before changes are made. Use it when joining a repo to add guardrails without disrupting existing patterns.

External Model Delegation routes each user prompt to a chosen model or CLI based on cost and task type. Use it to delegate simple, medium, or complex requests to local or external models from a Claude Code hook.