backend-python

Runs formatting, linting, and tests for the backend.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search in FastAPI backends. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

**If implementing payment, billing, subscription, or financial transactions:**

backend-rust

Guide for integrating safety validation into new inference backends

Expert in secure backend coding practices specializing in input

**Philosophy: Simple, bug-free, maintainable code. Zero complexity for complexity's sake.**

Experto en FastAPI y gestión segura de credenciales multi-tenant para Platform AI Solutions.

Hono/Bun patterns and backend best practices for this project. Use when implementing API endpoints, WebSocket handlers, services, or server-side logic in packages/server.

Organizes a flat backend directory structure into a clean, modular architecture with proper Python packages and updated import paths. Transforms a flat backend structure into a modular, organized architecture following Python best practices.

Write and review backend tests with JUnit5, MockMvc, and Spring Boot Test. Use for writing controller tests, service tests, and integration tests.

Create API handoff documentation for frontend developers. Use when backend work is complete and needs to be documented for frontend integration, or user says 'create handoff', 'document API', 'frontend handoff', or 'API documentation'.

Generate OpenAPI/REST endpoints from tRPC routers. Use when you have a tRPC API but need to expose REST endpoints for third-party integrations, mobile apps, or public API documentation. Provides automatic Swagger UI and OpenAPI spec generation. Choose this when you want type-safe internal APIs (tRPC) with REST fallback for external consumers.

Type-safe API layer for TypeScript full-stack applications. Use when building APIs that need end-to-end type safety between client and server WITHOUT code generation. Ideal for Next.js, React, and Express apps where both frontend and backend are TypeScript. Choose tRPC over REST/GraphQL when you control both ends and want zero runtime overhead for type checking.

Master the uv package manager for fast Python dependency management, virtual environments, and modern Python backend project workflows. Use when setting up Python projects, managing dependencies, or optimizing Python development workflows with uv.

Fast unit testing framework for TypeScript/JavaScript. Use for testing tRPC procedures, Zod schemas, utility functions, and any TypeScript code. Built on Vite with native ESM, TypeScript support, and Jest-compatible API. Choose Vitest over Jest for modern TypeScript projects, especially with Vite-based setups.

TypeScript-first schema validation library. Use for ALL input validation in TypeScript projects — API inputs, form data, environment variables, config files. Essential companion for tRPC (required), React Hook Form, and any data boundary. Choose Zod when you need runtime validation with automatic TypeScript type inference.

พัฒนา Backend ด้วย Spring Boot, Node.js, Python อย่างมืออาชีพ

Create and manage long-running background processes with start/stop/status controls, logging, and monitoring. Use for batch processing jobs, data pipelines, continuous services, or any long-running tasks.

Run and manage long-running background tasks in the shell. Use for starting processes in background, monitoring output, listing active tasks, and killing processes. Essential for dev servers, watch modes, builds, and any non-blocking operations.

Automate backlink submission for directories, forums, and other non-blog resources using AI and browser automation

Maintain a lightweight backlog of high-value tasks discovered during work.

Expert backlog manager that prioritizes work using multi-criteria scoring, analyzes dependencies, and recommends optimal next tasks. Activates when managing backlogs, prioritizing work, adding items, or analyzing what to work on next.

Expert guidance for managing tasks using the Backlog.md CLI tool. Use this skill when working with backlog tasks, creating or editing task files, managing acceptance criteria, tracking task progress, or understanding backlog workflows and best practices. Activates when users mention backlog, tasks, acceptance criteria, task management, or backlog commands.

Expert guidance for Backlog.md CLI project management tool including task creation, editing, status management, acceptance criteria, search, and board visualization. Use this when managing project tasks, creating task lists, updating task status, or organizing project work.

Quick reference for Backlog.md CLI with critical file naming rules and workflow patterns

Bulk backlog scanner that analyzes the entire finans codebase vs CLAUDE.md, identifies ALL gaps, and generates a comprehensive, prioritized, numbered task backlog. Uses broad→narrow pattern.

Build Backstage backend plugins with createBackendPlugin and core services: DI, httpRouter, secure-by-default auth, Knex DB, routes, testing. Use for APIs and background jobs.

Build Backstage frontend plugins with the new Frontend System: createFrontendPlugin, blueprints, routes, Utility APIs, testing. Use for pages, nav, entity content, or cards.

Generate enterprise-grade web applications using Backstage Design System. Create admin dashboards, developer tools, and internal applications with modern React components, dark/light themes, and responsive design patterns based on Radix UI and Tailwind CSS.

BackstopJS visual regression testing for self-hosted visual comparison

Converting backtest visualizations from bar indices/timesteps to actual datetime axes for clearer time context

Comprehensive guidance for interpreting backtest results and detecting overfitting (project)

Implement backup strategies, disaster recovery plans, and data restoration procedures for protecting critical infrastructure and data.

Create and manage etcd backups for OpenShift control plane disaster recovery, including automated backup procedures and verification.

Create and manage database backups across environments

Create reliable disaster recovery procedures for your databases.

Designs backup and disaster recovery strategies for data and systems

Backup and restore openclaw configuration, skills, commands, and settings. Sync across devices, version control with git, automate backups, and migrate to new machines.

Multi-agent workflow for editing Claude Code skills with quality gates

Comprehensive guide to backward compatibility rules for APIs, databases, and data contracts with migration strategies and testing approaches

Create MicroPython applications for Universe 2025 (Tufty) Badge including display graphics, button handling, and MonaOS app structure. Use when building badge apps, creating interactive displays, or developing MicroPython programs.

Deployment workflows, file management, and project organization for Universe 2025 (Tufty) Badge. Use when deploying apps to MonaOS, managing files on device, syncing projects, organizing code, or setting up deployment pipelines.

System diagnostics, verification, and troubleshooting for Badger 2350. Use when checking firmware version, verifying installations, diagnosing hardware issues, troubleshooting errors, or performing system health checks on Badger 2350.

Hardware integration for Badger 2350 including GPIO, I2C sensors, SPI devices, and electronic components. Use when connecting external hardware, working with sensors, controlling LEDs, reading buttons, or interfacing with I2C/SPI devices on Badger 2350.

Complete step-by-step guide to go from zero to creating your first app for **MonaOS** on the Universe 2025 (Tufty) Badge. Perfect for absolute beginners!

Bags - The Solana launchpad for humans and AI agents. Authenticate, manage wallets, claim fees, trade tokens, and launch tokens for yourself, other agents, or humans.

Generates production-ready BAML applications from natural language requirements. Creates complete type definitions, functions, clients, tests, and framework integrations for data extraction, classification, RAG, and agent workflows. Queries official BoundaryML repositories via MCP for real-time patterns. Supports multimodal inputs (images, audio), 6 programming languages (Python, TypeScript, Ruby, Java, Go, C#), 10+ frameworks, 50-70% token optimization, and 95%+ compilation success.

Generic BAML patterns for type-safe LLM prompting. Covers schema design, DTO generation, client wrappers, and cross-language codegen. Framework-agnostic.