Claude Skills by majinmagros

Use when buttons do nothing or UI state contradicts labels after shared-state refactors. Triggers on \"click-path-audit\", \"click path audit\", \"button does nothing\".

Use when clickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads. Triggers on \"clickhouse-io\", \"clickhouse io\".

Use when implementing closed-loop agent verification — deployed app behaving is the ONLY signal that closes the loop; runtime verifiers drive live app; mocks prove nothing. Triggers on "closed loop verifier", "deployed app verification", "runtime verification", "not mocks", "screenshot driven testing".

Use when building internal tools from spreadsheets — sheet to app, automated reports, dashboards, internal APIs. Triggers on "internal tools", "planilha para app", "ferramenta interna", "dashboard interno", "relatorio automatizado".

Use when deploying Claude Code to a VPS (Hostinger KVM1, DigitalOcean, AWS) for 24/7 agents. Triggers on "Cloud Code VPS", "deploy Claude Code", "Hostinger VPS", "KVM1", "code-cloud app".

Use when prototyping UIs with AI — Cloud Design (/design command) or Open Design local-first alternative. Covers canvas workflow, DESIGN.md tokens, and export to HTML/CSS, PPTX, PDF, MP4. Triggers on \"cloud design\", \"protótipo ia\", \"design com ia\", \"/design command\".

Use quando precisar de prototipagem UI alta-fidelidade no Claude (Cloud Design) — design system versionado, referências visuais (screenshots/URLs), iteração em linguagem natural, export standalone HTML/PDF para handoff ao Cursor/Cloud Code. Limites de uso SEPARADOS do Cloud Code. Triggers: "cloud design", "protótipo alta fidelidade", "design system versionado", "export html pdf handoff", "claude design". Não use para direção criativa genérica (`frontend-design-direction`, `make-interfaces-fee...

Use when create CodeTour `.tour` files — persona-targeted, step-by-step walkthroughs with real file and line anchors. Use for onboarding tours, architecture walkthroughs, PR tours, RCA tours, and structured \"explain how this works\" requests. Triggers on \"code-tour\", \"code tour\", \"tour\".

Use when auditing a codebase for architectural improvements, identifying shallow modules that should be combined or deepened into clean, simple interfaces. Triggers on "improve codebase architecture", "deepening modules", "auditoria de arquitetura", "módulos profundos", "arquitetura limpa".

Index the repo ONCE and query the code map instead of re-reading files. Use when working in large codebases to save tokens and find blast-radius. Use quando indexar repo uma vez, consultar mapa do código, achar GPS e blast-radius sem reler tudo.

Use when joining a new repo, understanding an unfamiliar codebase, or generating CLAUDE.md. Triggers on \"codebase-onboarding\", \"onboard me\", \"understand this codebase\".

Real-time structural Code Health via CodeScene MCP — review before edits, verify score deltas after changes, gate commits and PRs. Use when reviewing code quality, refactoring, checking if AI changes degraded a file, or before commit/PR.

Export a deterministic automation built inside an AI subscription (Astra/Codex) to external code + scheduler without eating usage limits. Use quando a automação canibaliza a subscription, para exportar para trigger.dev/scheduler externo, migrar .env, hosted proof test. Triggers PT: tirar automação da subscription, exportar para trigger, offload subscription, usage limit estourado. Triggers EN: subscription offload, export automation to scheduler, trigger.dev export, usage limit automation.

Use when baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use detailed frontend or backend skills for framework-specific patterns. Triggers on \"coding-standards\", \"coding standards\", \"standards\".

Use when the user wants to check a YouTube channel against local transcripts, collect skill/automation opportunities from videos, download missing transcripts, analyze videos for new skill ideas, or keep a catalog up to date. Triggers on "defasagem do canal", "oportunidades de skill", "analisa os vídeos", "transcrições faltando", "baixar transcrição", "vídeos novos", "coletar oportunidades", "yt-oportunidades". Uses scripts/yt-oportunidades.mjs (sync-check/catalog/diff/download/dedup/mark/ana...

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before benchmarking. First step before benchmark-methodology. Triggers on "competitor set scoping", "direct adjacent aspirational tiers", "landscape report scope", "who counts as competitor", "competitive tiers".

Use when use after benchmark-methodology has produced scored competitor profile cards. Assembles findings into a decision-grade report: landscape map, competitor profiles, benchmarking matrix, white-space analysis, strategic recommendations,... Triggers on \"competitive-report-structure\", \"competitive report structure\", \"structure\".

Use when compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI. Triggers on \"compose-multiplatform-patterns\", \"compose multiplatform patterns\", \"patterns\".

Use when implementing Computer Use API patterns — OS World 72.6%, screen reading, mouse/keyboard/slide/drag-drop, self-correction, 150k context, 40min memory. Triggers on "computer use api", "os world benchmark", "screen reading agent", "slide controls", "self correcting agent", "40min memory agent".

Garbage collection for your Claude Code configuration. Periodically scans ~/.claude (skills, memory, hooks, permissions, MCP servers, caches) for redundant, stale, orphaned, or low-value items, then walks the user through a confirm-each-deletion cleanup. Use when the user says "clean up my config", "config GC", "too many skills", "audit my setup", "my .claude is bloated", or asks for a periodic config review.

Use when installing, updating, or reconfiguring ECC from inside Claude Code, Codex, or Kimi. Triggers on \"configure-ecc\", \"configure ecc\".

Reorganize the user's X and LinkedIn network with review-first pruning, add/follow recommendations, and channel-specific warm outreach drafted in the user's real voice. Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph around higher-signal relationships.

Use to create or amend a project constitution — the non-negotiable principles that govern all future work. Triggers on "/constituicao-projeto", "constituição do projeto", "princípios inegociáveis do projeto", "regras de governança", "atualizar a constituição". Cria/atualiza o documento de princípios com versionamento semântico, Scope Guard e Sync Impact Report. Só escreve o arquivo da constituição — nada mais.

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

Use when cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation. Triggers on \"content-hash-cache-pattern\", \"content hash cache pattern\", \"pattern\".

Use when audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations. Triggers on \"context-budget\", \"context budget\", \"budget\".

Use quando precisar transformar arquivos brutos dispersos (e-mail, WhatsApp, Drive, calendário, transcrição de call, repositório) em um índice cronológico pesquisável com fonte e data — o Ledger que alimenta o segundo cérebro. Cria vault privado SQLite+FTS5, inbox, 3 tools MCP read-only e cofre 1Password. Triggers em "ledger", "context ledger", "segundo cérebro", "captura de contexto", "empresa agêntica", "agent-context-kit", "context kit", "vault privado".

Use when patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. Triggers on \"continuous-agent-loop\", \"continuous agent loop\", \"loop\".

Use when instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination. Triggers on \"continuous-learning-v2\", \"continuous learning v2\".

Use when [DEPRECATED - use continuous-learning-v2] Legacy v1 stop-hook skill extractor. v2 is a strict superset with instinct-based, project-scoped, hook-reliable learning. Do not invoke v1; route continuous learning, session learning, and pattern extraction r... Triggers on \"continuous-learning\", \"continuous learning\", \"learning\".

Use when frontend/backend or service-to-service teams must evolve a shared API or event schema without field drift or integration surprises. Triggers on \"contract-first\", \"contract first\", \"boundary contract\".

Use after implementation to compare code against spec/plan/tasks and surface remaining work. Triggers on "/convergencia", "converge a implementação", "código bate com o spec?", "o que falta implementar?", "gap entre código e requisitos". Avalia o estado ATUAL do código contra spec/plano/tarefas, classifica gaps (missing/partial/contradicts/unrequested) e ANEXA tarefas restantes à lista — append-only, nunca reescreve.

Agente Conversa. Use quando o usuário quiser ensaiar reuniões, entrevistas, vendas ou negociações antes da conversa real. Triggers em "ensaio", "simular reunião", "entrevista", "negociação", "objeção de preço", "role-play", "feedback de performance".

Agente Coordenação. Use quando o usuário pedir para organizar a rotina, proteger o dia de interrupções, cruzar e-mails/agenda, categorizar mensagens ou rascunhar respostas. Triggers em "agenda", "e-mail", "planejar dia", "rotina", "organizar", "mensagens", "compromissos", "refocar".

Rastreia conformidade de direitos autorais e licenças de ativos de IA (datasets de treino, pesos de modelo, mídia gerada, código de terceiros) para evitar uso não licenciado. Gatilho: usuário vai usar dados/ modelo/ mídia gerada em produção ou comercialmente, pergunta "posso usar X comercialmente", ou precisa auditar licenças de um projeto de IA. Não-gatilho: não é registro de propriedade intelectual (use advogado); não é para licenciar sua própria obra (use copyright oficial). Outcome: inven...

Use when cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching. Triggers on \"cost-aware-llm-pipeline\", \"cost aware llm pipeline\", \"pipeline\".

Track and report Claude Code token usage, spending, and budgets from the local ECC cost-tracker metrics log. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by model, session, or date.

Use when deciding under ambiguity with a four-voice council for tradeoffs and go/no-go calls. Triggers on \"council\", \"second opinions\", \"go no-go\".

C++ coding standards based on the C++ Core Guidelines (isocpp.github.io). Use when writing, reviewing, or refactoring C++ code to enforce modern, safe, and idiomatic practices. Only for C++ — not for C or other languages. Triggers on "cpp-coding-standards", "cpp coding standards", "c++ standards".

Use when use only when writing/updating/fixing C++ tests, configuring GoogleTest/CTest, diagnosing failing or flaky tests, or adding coverage/sanitizers. Triggers on \"cpp-testing\", \"cpp testing\", \"testing\".

Use when creating visual ad campaigns (images/video) with budget control and brand references. Triggers on "gera campanha", "anúncios para a marca", "campanha visual", "imagens da marca", "orçamento de geração", "modelo mais barato". Routes to the cheapest available model, uses brand reference images, logs every generation.

Use when creating, authoring, or refining Claude Code skills. Triggers on "cria uma skill", "skill nova", "gravar skill", "record a skill", "como criar skill", "melhora a skill", "4 regras de skill". Encodes the 4-step authoring process, Skill Creator / Record a Skill, the 3-layer structure, the DBS framework, the EADA filter, skill systems, and the Anthropic engineers' 4 rules.

Agente Criatividade. Use quando o usuário quiser transformar anotações/materiais brutos em entregáveis formatados (slides PowerPoint, documentos Word/PDF). Triggers em "slides", "apresentação", "powerpoint", "documento", "relatório", "rascunho", "entregável", "design".

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

Use when c# and .NET testing patterns with xUnit, FluentAssertions, mocking, integration tests, and test organization best practices. Only for C#/.NET — not for other languages. Triggers on \"csharp-testing\", \"csharp testing\", \"testing\".

Use quando precisar criar ou otimizar currículo para passar no filtro ATS brasileiro — formatação parser-safe, extração de 70–80% keywords da vaga, Verbo+Ação+Resultado com métricas, Gupy/Kenoby/Lever/Greenhouse/LinkedIn. Triggers em "currículo ats", "currículo gupy", "currículo sem experiência", "otimizar currículo", "palavras-chave vaga", "stack vagas", "scanner ats", "currículo júnior".

Operate customer billing workflows such as subscriptions, refunds, churn triage, billing-portal recovery, and plan analysis using connected billing tools like Stripe. Use when the user needs to help a customer, inspect subscription state, or manage revenue-impacting billing operations.

Use when handling customs clearance, tariff classification, trade compliance, import/export documentation, or duty optimization across jurisdictions. Triggers on "customs clearance", "tariff classification", "HS code classification", "duty optimization", "restricted party screening", "FTA qualification", "customs audit".

Use when production-ready Dart and Flutter patterns covering null safety, immutable state, async composition, widget architecture, popular state management frameworks (BLoC, Riverpod, Provider), GoRouter navigation, Dio networking, Freezed code generation,... Triggers on \"dart-flutter-patterns\", \"dart flutter patterns\", \"patterns\".

Build monitoring dashboards that answer real operator questions for Grafana, SigNoz, and similar platforms. Use when turning metrics into a working dashboard instead of a vanity board.