By luyzkk
Plugin de desenvolvimento disciplinado com conhecimentos de programador senior. v7.5.0 — System Design Coverage Gaps: fecha os 3 buracos de System Design via sintese de corpus senior (32 fontes, 573 atomos). Onda 1 Filas/Mensageria — 3 references novas em system-design (messaging-models, messaging-reliability, messaging-operations) + secao 9 + cross-link AMQP. Onda 2 SQL-internals + DNS-routing — 3 references SQL (sql-indexing-and-storage, sql-acid-and-durability, sql-query-planning com EXPLAIN/particionamento de doc oficial PostgreSQL) + secao 10 + dns-hosting estendido (7 politicas Route 53, secoes 8-9) + replication-sharding (surge-replacement). Onda 3 Resiliencia (enriquecimento, ZERO reference nova) — defensive-patterns (5 categorias: circuit breaker/timeout/fallback/retry/health check), system-design secao 11 Resiliencia Distribuida + Shuffle Sharding, infrastructure Blue-Green Deploy. 9 conflitos senior (C1-C9) resolvidos via tensao+regra (D4); toda afirmacao citada (fonte); audit global CA-01 zero descarte silencioso (32/32 fontes); advisor do hooks.json passa a listar defensive-patterns + infrastructure (corrige omissao). v7.4.0 — Skill Parity Refresh: novo agente code-reviewer (frota 13→14, correctness+readability a nivel de linha) + ~81 grafts adversarialmente verificados em 19 skills e 3 agents (copy-then-improve, zero regressao de conteudo). v7.3.0 — Next.js Stack Knowledge. PRIMEIRA stack knowledge completa em ingles (D15): 15 atoms em knowledge/nextjs/atoms/ extraidos de 9 fontes declaradas com anti-drift clause + verifier batch (94% rastreabilidade, 0 rework rounds). T1 (7): app-router-and-layouts, react-server-components, server-actions-and-mutations, middleware-and-edge, security-stack-specific, react-hooks-and-state. T2 (6): data-fetching-and-cache, rendering-strategies, performance-and-turbopack, testing-strategy, ui-and-styling, error-handling-observability, react-suspense-patterns. T3 (2): pages-router-migration-tips, supabase-integration. DETECTOR: nextjs e react como StackIds distintos; STACK_ID_TO_MATRIX_FOLDER['nextjs']='nextjs' (era 'nodejs-typescript'); probeReact com vite.config+react guard (G8 false-positive); detectMultiStack inclui next.config.{js,ts} como anchor nextjs-especifico. PARSER: format-knowledge-preview.ts regex (?:Por|By) aceita INDEX em EN alem de PT-BR (RF-11, backward-compat). INFRA: THIRD-PARTY-NOTICES.md (MIT attribution para 6 SKILL.md V2); knowledge/nextjs/INDEX.md (By Cross-Stack Skill / By Tier / By keyword); 2 fixtures (nextjs-app-router-fixture, nextjs-supabase-fixture); 2 E2E (init-v7-nextjs-tracer-bullet 11 testes, init-v7-nextjs-supabase 3 testes). COMPOUND: 2026-05-25-stack-knowledge-extraction-workflow.md — workflow parallel waves + anti-drift + verifier validado em 14 atoms, template reusavel para futuras stacks (Go, Elixir).
Phase Zero consultation for uncertain decisions, trade-off analysis, and irreversible choices. Teaches before coding.
Generate 3+ divergent architectural proposals via parallel subagents to fight premature convergence before deciding.
Integrate Anti-Vibe Coding skills into existing plan/task structure for automated execution by Claude Code.
Execute hierarchical plans phase by phase using isolated subagents. Applies TDD with RED/GREEN context isolation; keeps MEMORY.md and STATE.md current.
Deep pre-implementation interview that resolves all ambiguity before coding. Outputs CONTEXT.md with indexed decisions. Use before planning complex features.
Audite o seguinte snippet:
Schemas canonicos do contrato de subagentes.
Auditor de APIs read-only. Verifica idempotencia, DTOs, REST design, webhooks, rate limiting e seguranca de endpoints. Baseado em conceitos de API Design e boas praticas.
Revisor generalista read-only. Cobre correctness (spec-conformance, null/empty/boundary, error-paths, race/off-by-one/state) e readability (nomes, nesting, organizacao) a nivel de linha. Complementa os auditores estruturais e de dominio.
Detector de code smells read-only. Identifica 9 padroes de codigo ruim com sugestoes de refatoracao. Baseado em conceitos de qualidade de codigo e boas praticas.
<!-- 2026-05-14 (Luiz/dev): Agent e Bash adicionados para permitir delegacao opcional a auditores em v6.2.
This skill should be used when the user asks about 'API design', 'N+1 problem', 'idempotency', 'idempotent APIs', 'DTOs', 'data transfer objects', 'webhooks', 'websockets', 'SSE', 'REST vs GraphQL', 'SQL vs NoSQL', 'race conditions in APIs', 'API concurrency', 'gRPC', 'AMQP', 'RabbitMQ', 'message queue', 'GraphQL schema', 'GraphQL depth', 'DataLoader', 'pagination', 'cursor pagination', 'keyset pagination', 'REST URL design', 'status codes', 'API versioning', 'HATEOAS', 'filtering', 'sorting', 'Protocol Buffers', or needs to analyze and audit API endpoints. Provides expert consultation on API design patterns, protocols, anti-patterns, and best practices.
This skill should be used when the user asks about 'SOLID principles', 'monolith vs microservices', 'CQRS', 'event sourcing', 'REST vs GraphQL', 'tech stack selection', 'architecture decision', 'ADR', 'design patterns', 'Law of Demeter', 'Tell-Don't-Ask', 'composition vs inheritance', 'dependency injection', 'DI', 'IoC container', 'constructor injection', or faces architectural trade-off decisions. Provides senior-level architecture consultation with explicit trade-off analysis.
Detecta configurações espalhadas (strings hardcoded, valores duplicados) e executa migração disciplinada para uma única fonte de verdade. Fluxo: detectar → mapear → centralizar → substituir usos → verificar.
Guia de simplificação de código: identifica over-engineering, duplicação e complexidade desnecessária, aplicando padrões de simplificação por linguagem. Use quando refatorar código para clareza sem mudar comportamento. Use quando o código funciona mas é mais difícil de ler/manter/estender do que deveria. Use quando revisar código que acumulou complexidade desnecessária.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimMatches all tools
Hooks run on every tool call, not just specific ones
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
No model invocation
Executes directly as bash, bypassing the AI model
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub luyzkk/anti-vibe-coding --plugin anti-vibe-codingComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC plugin for engineering teams - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Lazy senior dev mode. Forces the simplest, shortest solution that actually works: YAGNI, stdlib first, no unrequested abstractions.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification