Claude Skills by majinmagros

Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Runs on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from user feedback. Runs 100% free on GitHub Actions. Use when the user wants to monitor, collect, or track any public data automatically.

Use when large data ingestion, backfill, export, ETL, warehouse loading, manifest catch-up, or table synchronization needs to become much faster while preserving data correctness.

Use when database migration best practices for schema changes, data migrations, rollbacks, and zero-downtime deployments across PostgreSQL, MySQL, and common ORMs (Prisma, Drizzle, Kysely, Django, TypeORM, golang-migrate). Triggers on \"database-migrations\", \"database migrations\", \"migrations\".

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any topic with evidence and citations.

Use when security checklist for Solidity AMM contracts, liquidity pools, and swap flows. Covers reentrancy, CEI ordering, donation or inflation attacks, oracle manipulation, slippage, admin controls, and integer math. Triggers on \"defi-amm-security\", \"defi amm security\", \"security\".

Sanitize a web page to relevant content only before giving it to the agent (remove chrome/navigation/ads/scripts) to save context. Use when the user says "limpar página", "sanitizar HTML", "só o conteúdo", "página muito grande", "estourou contexto com web", or in EN "sanitize page", "clean HTML", "remove boilerplate", "defuddle page", "strip chrome/ads", "reduce page context".

Use when stop hook that blocks Claude from finishing until quality checks pass. Detects rationalization patterns (surface text heuristics), stale learning logs (filesystem mtime), and low disk space. Complements self-audit by mechanically enforcing learning capture habits. Triggers on \"delivery-gate\", \"delivery gate\", \"gate\".

Use when deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Triggers on \"deployment-patterns\", \"deployment patterns\", \"patterns\".

Detect design-to-code drift in CI on every PR with headless engine and drift report. Use when design/ diverges from code, PR changes UI vs prod, need to break build on visual drift. TRIGGER when: design drift, drift report, headless design CI, PR vs main UI diff, AI review visual change. Gatilhos PT: drift design código, CI de drift visual, relatório de drift, quebrar build por divergência visual.

Version design files inside the repo as source of truth. Use when saving .pen JSON to design/, avoiding cloud-only design, binary merge conflicts, splitting tokens lib vs pages. TRIGGER when: design in repo, .pen JSON, gitattributes binary, design tokens lib, design conflict. Gatilhos PT: design versionado no repo, salvar .pen, conflito de design, biblioteca de tokens, nunca editar JSON na mão.

Use when iterating an existing design in place with A/B variants, an editable artboard, and anti-slop moodboards instead of generating from zero. Triggers on \"iterate design\", \"design variants\", \"artboard edit\", \"click to edit\", \"anti-slop\". Non-triggers: blank-page prototype generation (use cloud-design-prototyping), generic UI polish rules (use frontend-design-direction). Outcome: variant set against the existing system plus an edited winner ready to implement.

Use when use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling. Triggers on \"design-system\", \"design system\", \"system\".

Django + Celery async task patterns — configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing. Use when adding background jobs, scheduled tasks, or async processing to a Django app.

Use when django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps. Only for Django — not for other frameworks. Triggers on \"django-patterns\", \"django patterns\", \"patterns\".

Use when django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations. Only for Django — not for other frameworks. Triggers on \"django-security\", \"django security\", \"security\".

Use when django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs. Only for Django — not for other frameworks. Triggers on \"django-tdd\", \"django tdd\".

Use when verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR. Only for Django — not for other stacks. Triggers on \"django-verification\", \"django verification\", \"verification\".

Use when automating comment keyword to DM flows with UTM tracking and qualification scripts as a self-hosted ManyChat replacement. Triggers on \"keyword DM\", \"comment automation\", \"manychat replacement\", \"DM funnel\". Non-triggers: paid ads account operation (use ads-operator). Outcome: keyword map plus DM scripts plus UTM log plus qualification flow.

Use when running multiple agent sessions in parallel with dmux/tmux panes across harnesses. Triggers on \"dmux\", \"multi-agent\", \"parallel agents\", \"tmux panes\".

Use when creating or refining Drum'n Bass tracks in this project. Triggers on "gerar musica", "drum and bass", "dnb", "loop engineering", "graph engineering", "gerar loops", "pipeline", "MusicGen", "orquestrador". Encodes the Harness workflow: Generation, Loop Engineering (iterate until score>=80), Graph Engineering (parallel verification), and Creator/Verifier separation.

Docker and Docker Compose patterns for local development, hardened CLI installer harnesses, container security, networking, volumes, and multi-service orchestration. Use when creating or reviewing Dockerfiles and Compose services, testing installers across Linux distributions, or planning accurate native macOS and Windows validation.

Remove "peso morto" de projetos, agentes e skills — instruções verbosas que modelos modernos não precisam mais, contexto duplicado, skills/plugins não usados e arquivos órfãos que inflam a janela de contexto e o custo por execução. Use quando a sessão engole tokens rápido, o contexto alcança o limite cedo demais, o CLAUDE.md está sobrecarregado, ou você nunca revisou/atualizou suas skills e agentes há meses. Inclui a estratégia radical de revalidação: a cada ~6 meses (ou quando modelos novos ...

Use when use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma). Triggers on \"documentation-lookup\", \"documentation lookup\", \"lookup\".

Use when establishing or maintaining a shared domain vocabulary, glossary, and CONTEXT.md file for a project to align agent and human terminology, prevent verbosity, and reduce token consumption. Triggers on "context.md", "shared language", "domain model", "glossário de domínio", "vocabulário compartilhado".

Use when idiomatic C# and .NET patterns, conventions, dependency injection, async/await, and best practices for building robust, maintainable .NET applications. Only for C#/.NET — not for other languages. Triggers on \"dotnet-patterns\", \"dotnet patterns\", \"patterns\".

Pilot the whole OS with only a coding agent plus native CLI (PowerShell, AppleScript, Linux CLI) — no heavy computer-use harness. Use when asked to drive screen, control desktop apps, morning setup, test a GUI app, watch another agent session, automate clicks/screenshots via terminal. Gatilhos PT: pilotar tela, controlar computador, automação de tela, setup matinal, testar app desktop. Gatilhos EN: drive screen, computer use, desktop automation, control my screen, screenshot loop.

Use when design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses. Triggers on \"dynamic-workflow-mode\", \"dynamic workflow mode\", \"mode\".

Use when playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies. Triggers on \"e2e-testing\", \"e2e testing\", \"testing\".

Use when guide users through ECC's current agents, skills, commands, hooks, rules, install profiles, and project onboarding by reading the live repository surface before answering. Triggers on \"ecc-guide\", \"ecc guide\", \"guide\".

Use when map a described workflow to the right ECC command-GROUP with run-order and stop condition, and browse all command-group recipe families. Adds a family-grouping + run-order + when-to-stop layer on top of the flat command catalog. Advisory only. TRIGGER when the user sa... Triggers on \"ecc-recipes\", \"ecc recipes\", \"recipes\".

Evidence-first ECC Tools burn and billing audit workflow. Use when investigating runaway PR creation, quota bypass, premium-model leakage, duplicate jobs, or GitHub App cost spikes in the ECC Tools repo.

Evidence-first mailbox triage, drafting, send verification, and sent-mail-safe follow-up workflow for ECC. Use when the user wants to organize email, draft or send through the real mail surface, or prove what landed in Sent.

Use when the user needs to find a Claude Code skill for a problem — existing solution, best option among many, or curated lists. Triggers on "encontra uma skill", "procura skill", "qual skill pra", "tem skill pra isso", "melhores skills", "app store de skills". Filters by stars, installs, recency, license; reviews before installing.

Use when procuring energy, optimizing tariffs, managing demand charges, evaluating PPAs, or developing energy strategies. Triggers on "energy RFP", "tariff optimization", "demand charge mitigation", "PPA evaluation", "block-and-index", "capacity tag reduction", "load profiling".

Engenharia de Grafos (Graph Engineering) — decompor um objetivo em tarefas paralelas que executam simultaneamente e convergem para um único resultado, com verificadores independentes por ramo, e iterar até uma nota mínima quando houver candidatos ranqueáveis. Use quando várias sub-tarefas independentes podem rodar ao mesmo tempo (pesquisa de fontes múltiplas, geração em volume, coleta paralela, thumbnails/variantes) e precisam convergir em um único entregável, em vez de uma execução sequencia...

Use when operate long-lived agent workloads with observability, security boundaries, and lifecycle management. Triggers on \"enterprise-agent-ops\", \"enterprise agent ops\".

Use when patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages. Triggers on \"error-handling\", \"error handling\", \"handling\".

Use when formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles. Triggers on \"eval-harness\", \"eval harness\", \"harness\".

Use when prevent silent decimal mismatch bugs across EVM chains. Covers runtime decimal lookup, chain-aware caching, bridged-token precision drift, and safe normalization for bots, dashboards, and DeFi tools. Triggers on \"evm-token-decimals\", \"evm token decimals\", \"decimals\".

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine.

Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.

Use when fastAPI best practices covering project structure, Pydantic v2 schemas, dependency injection, async handlers, authentication, authorization, transactional service layers, and testing with httpx and pytest. Triggers on \"fastapi-patterns\", \"fastapi patterns\", \"patterns\".

Evidence-first revenue, pricing, refunds, team-billing, and billing-model truth workflow for ECC. Use when the user wants a sales snapshot, pricing comparison, duplicate-charge diagnosis, or code-backed billing reality instead of generic payments advice.

Use when analyzing Brazilian real estate financing (CAIXA, FGTS, ITBI, SIOPI, contracts, buyer rights). Triggers on \"financiamento\", \"imobiliário\", \"CAIXA\", \"FGTS\", \"ITBI\", \"SIOPI\".

Create reproducible, cross-platform (macOS/Linux) development environments with Flox, a declarative Nix-based environment manager. Use when setting up project toolchains for any language, installing system-level dependencies (compilers, databases, native libs like openssl/BLAS), pinning exact package versions for a team, running local services (PostgreSQL, Redis, Kafka), onboarding developers with one command, or solving 'works on my machine' problems — including agent/vibe-coding setups that...

Use when library-agnostic Flutter/Dart code review checklist covering widget best practices, state management patterns (BLoC, Riverpod, Provider, GetX, MobX, Signals), Dart idioms, performance, accessibility, security, and clean architecture. Triggers on \"flutter-dart-code-review\", \"flutter dart code review\", \"review\".

Use when building on-device Apple Intelligence features with text generation, structured output, or tool calling. Triggers on \"foundation-models-on-device\", \"foundation models on device\", \"device\".

Use when building accessible React/Next.js UI — semantic HTML, ARIA, form labeling, keyboard navigation, focus management, screen reader support. Triggers on "accessible form", "aria-label", "keyboard navigation", "focus trap modal", "screen reader", "a11y review".

Set an ECC-specific frontend design direction for production UI work. Use when building or improving websites, dashboards, applications, components, landing pages, visual tools, or any web UI that needs stronger product-specific design judgment.

Use when frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices. Only for React/Next.js frontend — not for backend or other frameworks. Triggers on \"frontend-patterns\", \"frontend patterns\", \"patterns\".