Claude Skills by majinmagros

Use when postgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices. Triggers on \"postgres-patterns\", \"postgres patterns\", \"patterns\".

Use when research prediction markets as data sources or oracle signals for products, agents, dashboards, and corporate decision intelligence. Use for source-grounded analysis of market-implied probabilities, caveats, and integration... Triggers on \"prediction-market-oracle-research\", \"prediction market oracle research\", \"research\".

Use when review prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk. Use before any workflow handles venue auth, user portfolio data, API keys, or trade planning. Triggers on \"prediction-market-risk-review\", \"prediction market risk review\", \"review\".

Use when prisma ORM patterns for TypeScript backends — schema design, query optimization, transactions, pagination, and critical traps like updateMany returning count not records, $transaction timeouts, migrate dev resetting the DB, @updatedAt skipped on bulk writes,... Triggers on \"prisma-patterns\", \"prisma patterns\", \"patterns\".

Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ECC-native PRD-to-SRS lane instead of vague planning prose.

Use when use this skill to validate the \"why\" before building, run product diagnostics, and pressure-test product direction before the request becomes an implementation contract. Triggers on \"product-lens\", \"product lens\", \"lens\".

Use when judging production readiness from local evidence: ship/block call with scored risks. Triggers on \"production-audit\", \"production audit\", \"audit\".

Use when scheduling production, resolving bottlenecks, optimizing changeovers, responding to disruptions, or balancing manufacturing lines. Triggers on "production scheduling", "bottleneck resolution", "changeover optimization", "drum-buffer-rope", "SMED", "OEE analysis", "disruption re-sequencing".

Operate execution flow across GitHub and Linear by triaging issues and pull requests, linking active work, and keeping GitHub public-facing while Linear remains the internal execution layer. Use when the user wants backlog control, PR triage, or GitHub-to-Linear coordination.

Use when the user wants a lazy/vague prompt improved or adapted — generate from scratch, fix, or port to another model/tool. Triggers on "melhora esse prompt", "estrutura o prompt", "prompt melhor", "conserta meu prompt", "garbage in garbage out", "prompt para imagem/vídeo/código". Applies the 4 pillars of good prompting.

Use when the user wants a prompt optimized or rewritten — analyze intent and gaps, match ECC components, output a ready-to-paste prompt. Triggers on "optimize prompt", "improve my prompt", "rewrite this prompt", "help me prompt", "优化prompt", "帮我优化这个指令".

Gera proposta comercial a partir de transcricao de reuniao + tabela de precos, com gate humano e follow-up. Use para transformar reuniao em proposta, montar orcamento, fazer follow-up de proposta sem resposta. Triggers PT: gerar proposta, proposta comercial, follow-up proposta, orcamento cliente. Triggers EN: draft proposal, follow up proposal, meeting to proposal, quote follow-up.

Use when prospecting local businesses for freelance web work via Maps search: find listings with no site or weak mobile presence, run automated audits, and send proposals. Triggers on \"maps prospecting\", \"freelance clients\", \"local business audit\", \"sell websites\". Non-triggers: outbound via social or email lists only (use lead-intelligence). Outcome: a ranked prospect list with audit evidence plus proposal and deploy plan.

Use when pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications. Only for Python — not for other languages. Triggers on \"python-patterns\", \"python patterns\", \"patterns\".

Use when python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements. Only for Python — not for other languages. Triggers on \"python-testing\", \"python testing\", \"testing\".

Use when pyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading. Triggers on \"pytorch-patterns\", \"pytorch patterns\", \"patterns\".

Use when investigating non-conformances, performing root cause analysis, managing CAPAs, interpreting SPC data, or handling supplier quality issues. Triggers on "NCR investigation", "root cause analysis", "CAPA management", "SPC interpretation", "supplier quality", "8D report", "non-conformance disposition".

Use when quarkus 3.x LTS architecture patterns with Camel for messaging, RESTful API design, CDI services, data access with Panache, and async processing. Use for Java Quarkus backend work with event-driven architectures. Only for Quarkus — not for other stacks. Triggers on \"quarkus-patterns\", \"quarkus patterns\", \"patterns\".

Use when quarkus Security best practices for authentication, authorization, JWT/OIDC, RBAC, input validation, CSRF, secrets management, and dependency security. Only for Quarkus — not for other stacks. Triggers on \"quarkus-security\", \"quarkus security\", \"security\".

Test-driven development for Quarkus 3.x LTS using JUnit 5, Mockito, REST Assured, Camel testing, and JaCoCo. Use when adding features, fixing bugs, or refactoring event-driven services. Only for Quarkus — not for other stacks. Triggers on \"quarkus-tdd\", \"quarkus tdd\", \"tdd\".

Use when verification loop for Quarkus projects: build, static analysis, tests with coverage, security scans, native compilation, and diff review before release or PR. Only for Quarkus — not for other stacks. Triggers on \"quarkus-verification\", \"quarkus verification\", \"verification\".

Use when building secure corporate RAG: chunking with overlap, hybrid literal-vs-semantic search, ACL filtering before the model, Spring AI or LangChain stacks. Triggers on \"corporate RAG\", \"hybrid search\", \"RAG ACL\", \"secure retrieval\". Non-triggers: plain code search with no access control (use graphify). Outcome: a RAG pipeline that cites sources, filters by profile, and states that RAG does not remove hallucination.

Use when rFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration. Triggers on \"ralphinho-rfc-pipeline\", \"ralphinho rfc pipeline\", \"pipeline\".

Use when running ops agents in the Ramp pattern: repetitive loops vs exploratory dynamic workflows, declarative correct-trace, trace-debug over benchmarks, least-privilege, and cost culture. Triggers on \"Ramp ops\", \"loops vs workflows\", \"correct-trace\", \"trace-debug\". Non-triggers: generic workflow orchestration with no ops surface (use workflows). Outcome: an ops loop system with least-privilege, cost control, and on-call-ready inspection.

React Native and Expo app patterns — Expo Router navigation, state separation (server/client/route/form), TanStack Query data fetching with Zod, performant lists, NativeWind/StyleSheet styling, native APIs, and secure storage. Use when building or editing React Native / Expo screens, components, navigation, or data layers.

React 18/19 patterns including hooks discipline, server/client component boundaries, Suspense + error boundaries, form actions, data fetching, state management decision trees, and accessibility-first composition. Use when writing or reviewing React components.

React and Next.js performance optimization patterns adapted from Vercel Engineering's React Best Practices (https://github.com/vercel-labs/agent-skills). Organizes 70+ rules across 8 priority categories — waterfalls, bundle size, server-side, client fetching, re-render, rendering, JS micro-perf, advanced. Use when writing, reviewing, or refactoring React/Next.js code for performance.

Use when writing or fixing tests for React components, hooks, or pages with Testing Library, Vitest/Jest, MSW, and axe. Triggers on \"react-testing\", \"react testing\", \"testing\".

Use when design composable recommendation, ranking, and feed pipelines using the six-stage Source→Hydrator→Filter→Scorer→Selector→SideEffect framework popularized by xAI's open-sourced For You algorithm. Use this skill whenever the user is buildin... Triggers on \"recsys-pipeline-architect\", \"recsys pipeline architect\", \"architect\".

Use when the user asks for repeated rollouts, marked decision processes, high-dimensional search, stochastic optimization, local-optima exploration, ensemble comparison, or recursive reasoning with a visible evidence trail.

Use when redis data structure patterns, caching strategies, distributed locks, rate limiting, pub/sub, and connection management for production applications. Triggers on \"redis-patterns\", \"redis patterns\", \"patterns\".

Use when choosing between regex and LLM for parsing structured text with repeating patterns. Triggers on \"regex-vs-llm-structured-text\", \"regex vs llm structured text\", \"text\".

Use when best practices for Remotion - Video creation in React. 29 domain-specific rules covering 3D, animations, audio, captions, charts, transitions, and more. Triggers on \"remotion-video-creation\", \"remotion video creation\", \"creation\".

Use when cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports. Triggers on \"repo-scan\", \"repo scan\", \"scan\".

Transforma video longo em shorts com funil de DM por palavra-chave, CTA em voz e publicacao multi-conta. Use para reaproveitar live/curso, gerar leads por comentario, escalar o mesmo corte em varias contas. Triggers PT: transformar live em shorts, funil comentario DM, palavra-chave DM, reaproveitar conteudo. Triggers EN: long to shorts funnel, keyword DM funnel, repurpose long-form, shorts lead funnel.

Evidence-first current-state research workflow for ECC. Use when the user wants fresh facts, comparisons, enrichment, or a recommendation built from current public evidence and any supplied local context.

Use when recupera o historico de uma sessao do opencode travada/perdida e exporta para um arquivo markdown de retomada. Triggers em \"perdi a sessao\", \"janela travou\", \"recupera historico\", \"retoma a tarefa\", \"meu contexto sumiu\", \"opencode.db\". Lê o SQLite de sessoes, lis... Triggers on \"retomar-sessao\", \"retomar sessao\", \"sessao\".

Use when handling product returns, reverse logistics, refund decisions, return fraud detection, or warranty claims. Triggers on "RMA eligibility", "condition grading", "disposition routing", "return fraud", "wardrobing", "swap fraud", "vendor RTV", "warranty claim".

Use when implementing Prime Agent / Recursive Language Model (RLM) patterns — self-improving coding agent that beats human baseline on ARC-AGI3 (95.5% MIT), runs in terminal like Claude Code/Codex but with recursive sub-agents and Pluggable LLM backends (Claude, Codex, GLM). Triggers on "RLM", "Prime Agent", "recursive language model", "ARC-AGI", "self-improving agent", "agente recursivo".

Use when choosing cheap models and routing them in agent loops — OpenRouter as provider in Claude Code, cost-per-task budgeting, using a low-cost model as executor while a strong model verifies, and when cheap+verifier loops become viable. Triggers on "rotear modelo barato", "OpenRouter no Claude Code", "custo por tarefa", "modelo barato pra loop", "DeepSeek", "huggingface barato".

Use when configuring or troubleshooting zero-cost AI model routing via 9router — aggregating free tiers (OpenCode free, Nvidia API, Gemini free, rotating free accounts), building combos with automatic failover on quota errors, and running agents 24/7 on a VPS without paying Anthropic/OpenAI. Triggers on "9router", "rotear modelos grátis", "usar IA de graça", "zero token", "failover de conta", "rotacionar conta gratuita", "API gratuita", "rodar agente 24/7 de graça", "CLAUDE CODE hack", "$0 in...

Use when building a structured learning or execution roadmap for becoming an AI Engineer in 2026. Triggers on "engenheiro de ia", "roadmap de ia 2026", "como virar engenheiro de ia", "fases para aprender ia", "vagas de engenheiro de ia", "estudar ia em 2026".

Use when scheduling autonomous Claude Code sessions in the cloud — recurring tasks that run without the machine being on. Triggers on "routines", "agendar", "tarefa recorrente", "funcionário 24/7", "roda todo dia", "webhook", "gatilho", "cloud code na nuvem". Covers schedule/webhook/GitHub triggers, vs VPS/n8n/Mac mini.

Use when rules in CLAUDE.md or AGENTS.md may no longer match what the code does, after refactors, failed compacts, or coordinator-heavy runs. Triggers on \"rule drift\", \"rules vs code\", \"stale rules\", \"handoff doc\", \"fresh restart\", \"delegator vs coordinator\". Non-triggers: size-only audit (use claude-md-auditor), rules to hooks migration (use rules-to-hooks-auditor). Outcome: a drift report with stale rules, handoff doc, and a delegator fix plan.

Use when scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files. Triggers on \"rules-distill\", \"rules distill\", \"distill\".

Use when auditing CLAUDE.md / AGENTS.md / rules and migrating probabilistic processes to deterministic hooks — stop, pre-tool-use, post-tool-use, start-session, sub-agent-stop. Triggers on "auditoria rules hooks", "converter rules em hooks", "hooks create skill", "garantias determinísticas", "test enforcement", ".env block", "security hooks", "stop hook tests".

Use when idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications. Only for Rust — not for other languages. Triggers on \"rust-patterns\", \"rust patterns\", \"patterns\".

Use when rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology. Only for Rust — not for other languages. Triggers on \"rust-testing\", \"rust testing\", \"testing\".

Migrate SaaS spend to self-hosted VPS with Coolify: cost matrix, app+Postgres+Redis+RabbitMQ catalog, KVM sizing with CPU validation, backup, WhatsApp proxy. Use quando a conta SaaS aperta, para sair de Neon/Vercel/Redis/N8N cloud, montar stack em Coolify, dimensionar VPS. Triggers PT: sair do SaaS, migrar para VPS, stack Coolify, baratear infra, KVM2 KVM4. Triggers EN: saas to vps, self-host stack, coolify deploy, cut saas cost, vps sizing.

Use when use this skill to prevent destructive operations when working on production systems or running agents autonomously. Triggers on \"safety-guard\", \"safety guard\", \"guard\".