後端開發

Comprehensive web research via Parallel Search API. Use when user requests parallel search for deep multi-source research, technical analysis, learning new topics, current events, or comparative studies. Returns LLM-ready ranked URLs with extended excerpts (up to 30K chars). Single API call handles multiple query angles with automatic deduplication.

Testing patterns for litefs-py and litefs-django. Use when writing tests, setting up fixtures, understanding test organization, or configuring pytest marks. Triggers: test, pytest, unit test, integration test, property-based testing, hypothesis, fixtures, in-memory adapters.

Runtime security validation including secret scanning, PII detection, prompt injection defense, audit logging, and output validation for AI agents. Use when validating user input, scanning for secrets, detecting PII, preventing data exfiltration, or implementing security guardrails.

Deploy the shot-elixir Elixir/Phoenix application to Fly.io. Use this skill when deploying backend changes, updating environment variables, or releasing new versions to production.

Comprehensive guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Covers both Python (FastMCP) and Node/TypeScript (MCP SDK) implementations.

WebRecon - reconnaissance tool using parallel Chrome instances for competitive analysis, design extraction, and API discovery

Query and interact with Supabase databases using real-time subscriptions and PostgreSQL-compatible queries. Supports SELECT operations with Row Level Security (RLS), filtering, ordering, and pagination. Activated when users mention "supabase", "realtime database", or need Supabase backend features.

Use this skill whenever the user wants to set up, write, or refactor tests for a NestJS TypeScript backend, including unit tests, integration tests, and e2e tests with Jest, TestingModule, and Supertest.

Use when refactoring fat Rails models with repetitive prefixes like entropy_*, notification_*, or multi-association coordination. Extracts PORO wrappers that group operations around nouns/concepts.

Detect code smells including long methods, large classes, duplicated code, and deep nesting. Use when identifying code quality issues or planning refactoring.

Comprehensive systematic debugging agent for hunting down complex bugs, root causes, and error propagation across full stack (frontend, backend, APIs, databases). Use when diagnosing errors, troubleshooting issues, analyzing stack traces, investigating bugs, examining logs, debugging performance problems, or tracking down error causes. Also use when users mention debugging, errors, bugs, failures, crashes, exceptions, or unexpected behavior.

Rust code refactoring with API compatibility preservation. Use when improving code structure, eliminating duplication, optimizing, or restructuring modules.

Reading from node_modules or dependency folders

Format trading proposals with timestamped headers and disciplined bullet structure. Use when a persona must deliver a single consolidated proposal with Schwab timestamps, bold parent bullets, and one-metric-per-line nested bullets.

Park Golf Platform NestJS 코딩 컨벤션. 모듈 구조, 서비스/컨트롤러 작성 규칙, DTO/Entity 패턴, 의존성 주입 방법 안내. "NestJS", "컨벤션", "코딩 스타일", "모듈", "서비스" 관련 질문 시 사용합니다.

Comprehensive unified BaaS (Backend-as-a-Service) integration hub for 9 major providers: Auth0, Clerk, Firebase Auth, Supabase, Neon, Convex, Firebase Firestore, Vercel, and Railway with AI-powered provider selection, cross-provider patterns, and migration guides.

Run in-session task loops via the codex-taskloop-plugin MCP server and stop hook.

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development for FastAPI applications. Use when writing Python tests, setting up test suites, or implementing testing best practices.

Automatically detects, installs, and configures Language Server Protocol (LSP) servers for enhanced code intelligence. Provides go-to-definition, find-references, hover docs, and symbol navigation.TRIGGERS - Keywords: lsp, language server, code intelligence, go to definition, find references, hover, symbols, diagnostics, autocomplete, intellisense, code navigation, jump to definition, find usages, type info.TRIGGERS - Phrases: "set up lsp", "install language server", "enable code intelligence", "configure lsp", "go to definition not working", "find references", "show type", "navigate to symbol", "code navigation".TRIGGERS - Automatic: After tech-detection completes, when opening new file types, when LSP operations fail.

Creates, analyzes, updates, and evaluates Model Context Protocol (MCP) servers including architecture assessment, security validation, and connection configuration. Use when user asks if current context or logic should be MCP, requests MCP creation/improvement/update, mentions MCP is outdated, or asks how MCPs work, what MCPs are, explaining MCP concepts, understanding MCP architecture, protocol specification, server implementation, client integration, or connecting MCP servers to Claude Code.