Explorar Todas las Habilidades de Claude

Golden Dataset Curator

Manages the automated curation and multi-agent validation of high-quality datasets for LLM evaluation.

Alternative Agent Frameworks

Implement and compare multi-agent orchestration frameworks like CrewAI, OpenAI Agents SDK, and Microsoft Agent Framework for specialized AI workflows.

RAG Retrieval Patterns

Implements robust Retrieval-Augmented Generation (RAG) patterns to ground LLM responses with accurate, cited, and validated external data.

Unit Testing Patterns

Implements high-performance, isolated unit testing patterns using the AAA methodology across TypeScript and Python environments.

Remotion Callout Positioning

Calibrates and positions precise video annotations, arrows, and callouts within Remotion compositions using interactive debug grids.

Architecture Decision Records (ADR)

Documents significant architectural decisions using standardized Nygard templates to preserve technical context and trade-offs.

Remotion Video Composer

Compiles high-quality, programmatically generated demo videos and animations using the Remotion framework.

Golden Dataset Curator

Manages the multi-agent curation of high-quality training and testing datasets with automated quality scoring and bias detection.

Worktree Coordination

Coordinates multiple parallel Claude Code instances across Git worktrees to prevent file conflicts and synchronize architectural decisions.

Monorepo Context Manager

Optimizes multi-directory context and specialized instructions for complex monorepo structures within Claude Code.

GitHub Release Management

Automates GitHub release workflows using semantic versioning, automated changelog generation, and GitHub CLI integration.

Context Compression & Token Management

Optimizes Claude Code sessions by condensing conversation history using structured, anchored summarization to prevent token limit degradation.

Design System Starter

Implements robust, scalable design systems with standardized tokens, atomic component architecture, and full accessibility compliance.

Release Management Pro

Automates GitHub release workflows using semantic versioning and changelog generation via the gh CLI.

ElevenLabs Video Narration

Integrates ElevenLabs text-to-speech capabilities into video production pipelines for automated narration, voice selection, and synchronized timing.

RAG Reranking Patterns

Enhances search precision in RAG pipelines by re-scoring retrieved documents using high-accuracy Cross-Encoders and LLM relevance patterns.

RFC 9457 API Error Handling

Implements RFC 9457 Problem Details to provide standardized, machine-readable HTTP API error responses for modern backend services.

Database Schema Designer

Designs and optimizes SQL and NoSQL database schemas with professional-grade normalization, indexing, and migration patterns.

Clean Architecture Patterns

Implements SOLID principles, hexagonal architecture, and Domain-Driven Design (DDD) patterns for building maintainable and testable backends.

Thumbnail & First-Frame Optimizer

Optimizes video thumbnails and first-frame visibility to maximize click-through rates and viewer retention across digital platforms.

Manim Visualizer

Generates professional, animated technical visualizations to showcase agent workflows, spawning logic, and system architectures using the Manim engine.

Strawberry GraphQL Development

Builds type-safe, production-ready GraphQL APIs using the Strawberry library and FastAPI integration.

Fine-Tuning & Customization

Simplifies Large Language Model fine-tuning and alignment using parameter-efficient techniques like LoRA, QLoRA, and DPO.

Advanced TanStack Query v5

Implements high-performance data fetching, caching, and optimistic UI updates using TanStack Query v5 best practices.

High-Performance LLM Inference

Optimizes Large Language Model inference for production environments using vLLM, advanced quantization, and speculative decoding techniques.

Defense-in-Depth Security

Implements a robust 8-layer security architecture to harden AI pipelines and protect LLM integrations from end-to-end vulnerabilities.

Video Hook Formulas

Generates high-conversion opening lines and attention-grabbing intros for video content using 12 proven copywriting patterns.

E2E Testing with Playwright

Automates end-to-end browser testing using Playwright 1.58+ with AI-assisted test generation and self-healing capabilities.

LLM Evaluation & Quality Assessment

Implements automated quality gates, LLM-as-judge patterns, and RAGAS metrics to ensure reliable and grounded AI outputs.

Observability & Monitoring

Implements comprehensive observability frameworks for structured logging, Prometheus metrics, distributed tracing, and system alerting.