LLM & Agents

Multi-level caching strategies for LLM applications - semantic caching (Redis), prompt caching (Claude/OpenAI native), cache hierarchies, cost optimization, and Langfuse cost tracking with hierarchical trace rollup for 70-95% cost reduction

Specialized agent for line-level editing focused on clarity, concision, and style. Improves sentence structure, word choice, and rhythm. Use when user asks for "line editing", "polish", "improve clarity", or needs sentence-level improvements.

This skill should be used when Claude needs to determine what to test, design test structures, follow TDD practices, or decide when to skip tests. Trigger phrases include "write tests", "TDD approach", "test coverage", "what should I test", "testable vs non-testable".

Execute AI-generated code in secure isolated E2B cloud sandboxes with advanced monitoring, MCP gateway integration (200+ tools), and multi-language support. Use for running Python/JavaScript/TypeScript/Bash code, managing sandbox lifecycle (create, pause, resume, kill, list, connect), monitoring metrics (CPU, memory, disk), handling lifecycle events, uploading/downloading files, streaming command output, environment variable management, and integrating LLMs with code execution capabilities.

Implement Brazilian financial system integrations including Boleto generation, PIX payments, parcelamento (installments), CPF/CNPJ validation, and Banco do Brasil API integration. Use this skill when building fintech applications, payment processing systems, or any system requiring Brazilian banking compliance.

Create a new Claude Code agent skill with proper folder structure and SKILL.md format. Use when the user wants to add a model-invoked skill that Claude uses autonomously based on context. Handles skill folder creation with SKILL.md and optional reference files.

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs RAG/semantic search, or wants to start a local web UI for their docs.

Generates Nano Banana Pro prompts for original character designs. Use when user mentions "キャラクター作成", "キャラデザ", or "オリキャラ".

Testing guide for GRE projects covering pytest-django (backend) and Vitest (frontend).Use when: writing tests, debugging test failures, setting up test fixtures, mocking.Triggers: test, pytest, vitest, unittest, mock, fixture, TestCase, assert, coverage, TDD

Create new Claude Code skills with proper structure and best practices. Use when the user wants to create a new skill, extend Claude's capabilities, or needs help structuring a SKILL.md file.

This skill teaches the agent how to manage application deployments using GitOps with Flux CD. MANDATORY - You MUST read this skill before modifying deployment manifests or managing releases.

Supabase open-source Firebase alternative with Postgres, authentication, storage, and realtime subscriptions. Use when building full-stack applications requiring integrated backend services with Next.js, React, or Vue.

Use when validating Claude Code plugin conformity, checking component specifications, or auditing marketplace compliance - comprehensive plugin validation against November 2025 Anthropic specifications with progressive disclosure of detailed specs

Claude Code basics for new users. Covers essential concepts and commands. Use when: user is new to Claude Code or routed here by learning-path assessment.

Use this skill when asked to "create a plugin", "build a new plugin", "make a Claude Code plugin", "scaffold plugin", "plugin structure", "add commands/agents/skills/hooks to plugin", or when helping with plugin development.

Standards and best practices for writing effective tests including the testing pyramid, test structure patterns, and coverage guidelines

Guide for developing Tauri v2 desktop apps on macOS. Covers debugging native apps (Rust panics, Sentry integration, thread-local issues), app signing and updater setup, global shortcuts, Keychain secret storage, and Homebrew distribution. Use when building Tauri apps, debugging Rust backend issues, setting up auto-updates, handling keyboard shortcuts, or distributing macOS apps.

Redis 전문가. Lettuce(캐싱) + Redisson(분산락) 듀얼 전략. CacheAdapter(Cache-Aside, TTL 필수, KEYS 금지→SCAN 사용), LockAdapter(Pub/Sub, Watchdog, try-finally). Key Naming: {namespace}:{entity}:{id}. @Component 사용. @Transactional 금지.

Automatically applies when designing multi-agent systems. Ensures proper tool schema design with Pydantic, agent state management, error handling for tool execution, and orchestration patterns.

Enterprise Mermaid diagramming skill for Claude Code using MCP Playwright