Skill Creator
joaopelegrino
24 published skills · 0 GitHub stars across the catalog. View on GitHub ↗
breadcrumb-impl
Guia implementação de breadcrumb de navegação hierárquica seguindo padrões de acessibilidade WCAG e design system do Plataforma B2B de treinamento técnico corporativo
clientecriar-a-partir-video
Skill especializada para USUÁRIOS FINAIS (clientes) que desejam criar cursos naplataforma Plataforma B2B de treinamento técnico corporativo a partir de vídeos do YouTube. Esta skill utiliza um FLUXODE DIAGNÓSTICO INTERATIVO para adaptar a estrutura às características do conteúdo.IMPORTANTE: A estrutura do curso é FLEXÍVEL e determinada pelo diagnóstico inicial.Não há número fixo de seções, módulos ou formato predefinido. A skill analisa oinput do usuário (vídeo único, playlist, série de vídeos) e propõe estrutura adequada.O processo é COLABORATIVO: após análise inicial, Claude apresenta proposta deestrutura e solicita validação/ajustes do usuário antes de prosseguir. Isso garanteque cursos curtos (1h) e longos (100h+) sejam tratados apropriadamente.Formatos de entrada suportados: vídeo único curto (<1h), vídeo único longo (1-10h),playlist do YouTube, múltiplos vídeos avulsos, série de vídeos relacionados,webinars gravados, lives arquivadas, tutoriais sequenciais.A skill guia desde a extração d
component-refactor
Guia refatoração de componentes React seguindo padrões do Plataforma B2B de treinamento técnico corporativo, reduzindo duplicação e criando componentes genéricos reutilizáveis
learning-path-patterns
Comprehensive guide to Learning Path patterns for the Plataforma B2B de treinamento técnico corporativo educational platform. This skill covers the conceptual difference between Study Areas (courses) and Proposed Paths (sequences of courses), data modeling, UI/UX patterns, and implementation guidelines.Learn how to structure Learning Paths correctly: a Proposed Path is NOT a container of loose flashcards, but a curated sequence of Study Areas (courses). Each path references existing courses with metadata like order, availability status, and estimated hours.Real-world examples are taken from the Hub MVP implementation (US-044), including caminhoExemploData.js, HubView.jsx, and LearningPathView.jsx. The skill demonstrates the reference pattern used for "Desenvolvedor Backend" path that sequences Bash, Linux, Docker, and DevOps courses.Key topics include data schema design (cursos array with ordem, areaId, disponivel flags), computed properties (getters for statistics), navigation patterns (path -> course
localstorage-patterns
Comprehensive guide to localStorage patterns for the Plataforma B2B de treinamento técnico corporativo educational platform. This skill covers schema design, error handling strategies, quota management, and synchronization patterns essential for building resilient web applications with client-side persistence.Learn how to handle common localStorage errors (QuotaExceededError, SecurityError, DOMException), implement graceful degradation, manage storage quotas (5-10MB browser limits, 50KB per note), and sync localStorage with React state. The skill emphasizes defensive programming, user-friendly error messages, and fallback strategies.Real-world examples are taken directly from the project codebase, including CNotesView, BashNotesView, and auto-save patterns used across 5 learning systems. Each pattern is demonstrated with production code showing how localStorage is used to persist 227 educational modules' progress and user notes.Key topics include try/catch patterns for all localStorage operations, Quota
meta-configuracao-evolucao
Automatiza processo de pesquisa de documentação oficial, extração de melhores práticas e aplicação no projeto Plataforma B2B de treinamento técnico corporativo através de skills/agents/hooks
platform-architecture
Conhecimento completo da arquitetura, padrões de código, estrutura de dados e convenções do sistema educacional Plataforma B2B de treinamento técnico corporativo
react-components-patterns
Comprehensive guide to React component patterns used in the Plataforma B2B de treinamento técnico corporativo educational platform. This skill covers functional components with hooks, composition patterns, state management, props flow, and error handling strategies essential for building maintainable React applications.Learn how to create reusable, testable components following React best practices while avoiding common antipatterns like prop drilling, unnecessary class components, and improper state management. The skill emphasizes composition over inheritance, unidirectional data flow, and separation of concerns.Real-world examples are taken directly from the project codebase, including CLearningSystem, BashLearningSystem, Breadcrumb, AreaCard, and FlashcardModal components. Each pattern is demonstrated with production code showing how architectural decisions were implemented in a 5,500+ line React application with 17 components.Key topics include functional components (vs class components), React Hoo
ux-nomenclature
Garante nomenclatura consistente seguindo o glossário do ÉPICO 12 (Arquitetura de Informação do Plataforma B2B de treinamento técnico corporativo)
cva-case-study-roi
Real-world ROI case study for healthcare content automation pipeline. Clínica Mente Saudável case with validated metrics - 99.4% time reduction (4h15m to 1.5min), 92.4% cost reduction (R$192.50 to R$14.70), +180% monthly ROI turnaround. Includes detailed cost breakdown, optimization strategies, and business impact analysis. Use when evaluating ROI, presenting business case, or validating automation benefits.
cva-concepts-adk
Google ADK (Agent Development Kit) architecture and core concepts. Covers agent types (LLM, Sequential, Parallel, Loop, Multi-agent), tool ecosystem, execution flows, deployment options, and observability. Model-agnostic framework for production AI agents. Use when understanding ADK architecture, selecting agent patterns, designing agent systems, or deploying to Vertex AI.
cva-concepts-agent-types
Agent system taxonomy (A/B/C/D) based on capabilities - Type A (pure AI), Type B (AI+database context), Type C (AI+web grounding), Type D (AI+database+web). Includes latency/cost analysis, decision tree, healthcare pipeline mapping, and ROI optimization. Use when designing agent architecture, selecting agent type, optimizing costs, or implementing multi-agent workflows.
cva-healthcare-compliance
Brazilian healthcare compliance for regulated medical and psychological content. Includes LGPD data protection, CFM/CRP/ANVISA regulatory requirements, scientific research validation, and data sanitization. Use when developing healthcare applications, ensuring LGPD compliance, validating medical content, implementing data protection, or creating regulated healthcare systems in Brazil.
cva-healthcare-pipeline
Complete 5-system healthcare content pipeline for regulated medical content generation. Includes LGPD data extraction (Type B), claims identification (Type A), scientific reference search (Type C), SEO optimization (Type B), and final consolidation (Type D). Validated ROI - 99.4% time reduction, 92.4% cost reduction. Use when implementing healthcare content automation, building regulated medical systems, or optimizing production pipelines.
cva-healthcare-seo
Healthcare SEO strategy for Brazilian medical and wellness professionals. Includes specialized keyword research (dermatology, psychology, nutrition), professional content templates, local SEO optimization, and regulatory-compliant content structures. Use when optimizing healthcare websites, creating medical practice content, implementing local SEO for health professionals, or building patient acquisition funnels.
cva-overview
Overview of Clojure + Google ADK + Vertex AI development environment. Comprehensive lab for building production AI agents using Clojure as primary language, integrating Google ADK via Java SDK and Python libraries via libpython-clj. Includes healthcare pipeline with validated ROI (-99.4% time, -92.4% cost). Use when starting new projects, understanding architecture, or needing general context about the stack.
cva-patterns-context
Context management patterns for multi-source AI agents in Clojure+Vertex AI. Covers 4 context types (static/query/API/previous-result), lifecycle management (load/cache/invalidate), TTL strategies, and LGPD-compliant sensitive data handling. Includes production metrics (58% cost reduction via caching). Use when designing agent contexts, implementing multi-source data integration, optimizing cache strategies, or building LGPD-compliant systems.
cva-patterns-cost
Cost optimization strategies for production AI pipelines in Clojure+Vertex AI. Covers multi-model routing (70% Gemini/20% Haiku/10% Sonnet), token optimization (prompt engineering, output constraints), aggressive caching (58% cost reduction), batch processing, and real-time monitoring. Includes production metrics showing $0.391 to $0.162 per pipeline (-58%). Use when optimizing production costs, implementing multi-model strategies, designing budget controls, or scaling to high volume.
cva-patterns-workflows
Multi-agent workflow orchestration patterns for Clojure+Vertex AI. Covers sequential/parallel/DAG topologies, state management (stateless/stateful/hybrid), error handling (retry/circuit breaker), and monitoring. Includes production metrics from healthcare pipeline (99.4% latency reduction, 92.4% cost reduction). Use when designing multi-agent systems, implementing complex pipelines, optimizing workflow performance, or building production orchestration.
cva-quickref-adk
Quick reference cheatsheet for Google ADK in Clojure. Includes agent creation patterns, model configuration, tool building, execution patterns, and common workflows. Use when writing ADK code, looking up API syntax, building agents, or troubleshooting implementations.
cva-quickref-libpython
Quick reference cheatsheet for libpython-clj Python interop. Includes initialization, module imports, function calls, data conversions, NumPy/Pandas/Transformers patterns, and troubleshooting. Use when calling Python from Clojure, using Python libraries, or debugging interop issues.
cva-setup-clojure
Clojure project setup and configuration for agent development with Google ADK. Includes deps.edn configuration, directory structure, namespace organization, REPL-driven development workflow, and build system integration. Use when starting new agent projects, configuring Clojure dependencies, troubleshooting project setup issues, organizing namespaces and code structure, or need guidance on Clojure best practices for agent development.
cva-setup-interop
Python interoperability setup using libpython-clj for Clojure agent development. Includes Python environment configuration, module importing strategies, data type conversion between Python and Clojure, NumPy/Pandas/HuggingFace integration, virtual environment setup, and performance optimization. Use when integrating Python ML libraries, setting up data science workflows, troubleshooting Python interop issues, working with NumPy arrays or Pandas DataFrames, or calling HuggingFace transformers from Clojure.
cva-setup-vertex
Complete Vertex AI and Google Cloud Platform setup for Clojure agent development. Includes GCP project saas3-476116 credentials, security best practices (IAM, key rotation, LGPD), cost analysis, API enablement, and environment configuration. Use when starting new Clojure+Vertex project, configuring GCP credentials, implementing security compliance, or troubleshooting authentication.