すべてのClaudeスキルを閲覧
AIエージェントの能力を拡張するClaudeスキルの完全なコレクションをご覧ください。
AI Defense-in-Depth
Implements a robust 8-layer security architecture to harden AI pipelines and protect LLM integrations from end-to-end.
LLM Safety Patterns
Implements production-grade security patterns for LLM integrations to defend against prompt injection and prevent hallucinations.
LangGraph Parallel Execution
Implements high-performance parallel execution patterns for LangGraph workflows using fan-out, fan-in, and map-reduce strategies.
Release Management Pro
Automates GitHub release workflows using semantic versioning and the gh CLI to streamline production delivery.
LangGraph Human-in-the-Loop
Implements robust human-in-the-loop patterns for LangGraph workflows to enable manual review gates and approval-based agent supervision.
HyDE Semantic Retrieval
Enhances RAG retrieval accuracy by generating hypothetical answer documents to bridge vocabulary gaps in semantic search.
Observability & Monitoring
Implements comprehensive logging, metrics, distributed tracing, and alerting systems to ensure application reliability and performance.
React Server Components Framework
Builds high-performance Next.js 16+ and React 19 applications using server-first architecture and streaming SSR.
Prompt Caching & Cost Optimizer
Optimizes LLM performance and reduces API costs by implementing provider-native prompt caching for Claude and OpenAI models.
Golden Dataset Curation
Automates the curation and quality validation of high-fidelity evaluation datasets using multi-agent analysis pipelines.
Test Execution & Analysis
Executes comprehensive test suites across backend and frontend environments with automated failure analysis and coverage reporting.
Golden Dataset Curator
Curates and validates high-quality documents for golden datasets using a multi-agent evaluation workflow.
Creative QA Checklist
Verifies that creative assets meet brand, accessibility, and localization standards before publication through structured audit frameworks.
Deep Codebase Explorer
Accelerates repository onboarding and architectural understanding through parallel multi-agent codebase analysis.
Deep PR Reviewer
Conducts comprehensive pull request reviews using a swarm of specialized AI agents to ensure code quality, security, and architectural integrity.
Brand Measurement Dashboard
Establishes comprehensive KPI frameworks and reporting systems to track brand health, consistency, and business impact.
Revenue Variance Analysis
Analyzes and attributes deltas between revenue forecasts and actual results to recommend data-driven remediation strategies.
LLM Output Evaluation
Evaluates AI-generated content quality using LLM-as-judge patterns, RAGAS metrics, and automated hallucination detection.
LangGraph State Management
Implements robust state management patterns for LangGraph workflows using TypedDict, Pydantic, and custom reducers.
SkillForge Health Diagnostics
Validates SkillForge plugin configurations and performs comprehensive system health checks to ensure stable AI development environments.
System Design Interrogation
Guides architectural planning through structured questioning to ensure scalability, security, and coherence before implementation.
Nette Application Architecture
Guides the architectural design of Nette web applications using modern best practices and domain-driven organization.
Account Health Framework
Standardizes account scoring and risk assessment to drive proactive customer success and retention workflows.
Context Engineering
Optimizes LLM context windows through strategic positioning, token budgeting, and attention-aware design to maximize signal and reduce costs.
Type Safety & Validation
Implements rigorous end-to-end type safety and runtime validation using Zod, tRPC, and Prisma for robust TypeScript and Python applications.
Remember: Pattern & Decision Tracker
Stores architectural decisions, coding patterns, and lessons learned in a persistent knowledge graph for Claude Code.
Design System Starter
Architects scalable, accessible UI design systems using design tokens, atomic component patterns, and WCAG-compliant implementation guides.
Integration Testing Patterns
Implements robust integration testing patterns for APIs, databases, and complex component interactions across modern tech stacks.
LLM Cache Cost Tracking
Monitors LLM expenditures and analyzes cache efficiency using Langfuse observability for complex multi-agent systems.
Social Calendar Governance
Enforces operational controls and cadence rules for multi-channel social media publishing schedules.
Scroll for more results...