Explora nuestra colección completa de Habilidades de Claude que extienden las capacidades de los agentes de IA.
Implements high-performance parallel execution patterns for LangGraph workflows using fan-out, fan-in, and map-reduce strategies.
Persists and retrieves long-term semantic information across sessions to maintain technical context and project continuity.
Optimizes Claude's ability to write Nette Database queries, design typed entities, and manage schemas using MySQL 8.4+.
Provides expert guidance for creating secure, context-aware Latte templates with intuitive syntax and powerful inheritance for Nette applications.
Manages stacked pull requests and dependent branches using the Graphite (gt) command-line tool.
Automates a multi-agent design review process immediately following the creation of design documents to ensure technical and product readiness.
Eliminates flaky tests and race conditions by replacing arbitrary timeouts with smart, deterministic condition polling.
Implements high-performance real-time data streaming patterns using SSE, WebSockets, and ReadableStream APIs.
Stores architectural decisions, coding patterns, and lessons learned in a persistent knowledge graph for Claude Code.
Executes multi-step implementation plans in controlled batches with built-in review checkpoints and mandatory verification.
Automates the execution of multi-step implementation plans by dispatching fresh subagents for each task followed by iterative code reviews.
Ensures application reliability by implementing multi-layered validation patterns that make structural bugs and data corruption impossible to reproduce.
Builds complex AI workflows using decorator-based patterns for parallel execution, persistence, and human-in-the-loop interactions.
Manages multiple parallel Claude Code instances across Git worktrees to prevent file conflicts and synchronize architectural decisions.
Decomposes complex multi-concept queries into independent searchable terms to optimize retrieval accuracy and coverage in RAG pipelines.
Verifies development tasks and code changes by collecting verifiable proof including test results, build outputs, and exit codes.
Evaluates AI-generated content quality using LLM-as-judge patterns, RAGAS metrics, and automated hallucination detection.
Records and replays HTTP interactions for Python tests to create deterministic, network-independent, and cost-effective test environments.
Standardizes HTTP API error responses using the machine-readable RFC 9457 Problem Details format for FastAPI and backend services.
Aggregates and manages a persistent library of successful development patterns and anti-patterns across all your Claude Code projects.
Automates the creation of production-grade CI/CD pipelines, containerized environments, and Kubernetes-ready infrastructure.
Implements professional REST API versioning strategies and lifecycle policies to ensure backward compatibility and smooth migrations.
Implements production-grade hybrid search by combining PGVector HNSW semantic retrieval with BM25 keyword matching using Reciprocal Rank Fusion.
Refines raw ideas into technical specifications and architectural designs through iterative questioning and collaborative feedback.
Automates GitHub Issue resolution through a coordinated swarm of specialized AI agents and deterministic task tracking.
Coordinates complex multi-agent workflows using a central supervisor to route tasks among specialized LangGraph workers.
Architects robust, scalable APIs using industry-standard patterns for REST, GraphQL, and gRPC services.
Optimizes Claude's memory by compressing conversation history while preserving critical task data and session intent.
Generates detailed, step-by-step technical implementation plans for engineers with zero codebase context.
Systematically traces bugs backward through the call stack to identify and fix the original trigger rather than just the symptom.
Scroll for more results...