skills-claude-code

Persistent knowledge base for Claude Code projects using the LLM Wiki methodology by Andrej Karpathy. Bootstraps a structured wiki (markdown files with cross-references) and configures Claude Code to maintain it automatically across sessions. Integrates with Obsidian via MCP for graph view and visual navigation. Use this skill whenever the user wants to: set up a project wiki, create persistent memory for a project, use the Karpathy wiki method, organize knowledge with Obsidian integration, bootstrap a knowledge base, or mentions "wiki", "knowledge base", "persistent memory", "LLM wiki", or "Karpathy wiki". Also trigger when the user says "wiki ingest", "wiki query", "wiki lint", "wiki status", "wiki decision", "wiki learning", "wiki search", or "wiki sync".

Anti-Vibe Coding methodology for building software projects with AI in a disciplined, spec-driven way. Use this skill ALWAYS when the user wants to create a new project, start a SaaS, MVP, system, web application, API, or any software from scratch. Also use for adding major features to existing projects (brownfield). Trigger when the user mentions: 'new project', 'create system', 'start project', 'build application', 'build SaaS', 'make MVP', 'start development', 'plan project', 'architect system', 'project foundation', 'anti-vibe', 'disciplined coding', 'spec-driven', 'project from zero', 'scaffold project', 'bootstrap project', 'plan before coding', 'structured development', 'TDD project', 'build from scratch', 'add feature properly', 'plan this feature'. This skill enforces 7 sequential phases (onboarding, isolation, foundation with SDD artifacts, specs with Given/When/Then, TDD, implementation, optimization, deploy) — supports both greenfield and brownfield projects. Discipline over Intuition.

Elite Application Security Auditor — realiza auditoria ofensiva completa de aplicações web antes de qualquer deploy. Cobre reconhecimento, mapeamento de superfície de ataque, autenticação, autorização, lógica de negócio, pagamentos, APIs, injeções, headers de segurança, supply chain, race conditions avançadas e vulnerabilidades específicas de código gerado por IA. Age como um hacker ético sênior com mentalidade ofensiva real — simula ataques, testa race conditions com requisições simultâneas, explora fluxos de negócio para fraudes, verifica secrets vazados no git history, e valida se a IA não introduziu padrões inseguros. Use quando: revisar código (especialmente vibe-coded/AI-generated), preparar deploy, criar features de autenticação/pagamento/admin/afiliados, auditar segurança, analisar vulnerabilidades, testar race conditions, ou quando o desenvolvedor pedir "review de segurança".

Second Brain for Claude Code - maintains complete project context, documentation, architecture mapping, progress tracking, and knowledge persistence using Obsidian as the knowledge vault. Automatically syncs documentation after every task. Supports BMAD, OpenSpec, GSD, and SpecKit methodologies. Uses Obsidian Canvas for architecture visualization. Invoke this skill to CREATE or UPDATE project documentation, map the codebase, track progress, or sync knowledge.

Senior Software Architect with absolute mastery in fundamentals, design principles, architectural patterns, DDD, system design, cloud computing, DevOps, security, testing, modularization and technical communication. This skill should be used for any task related to software development, architecture design, code analysis and strategic technical decisions.

Ultra Senior Software Engineer (15+ years experience) with absolute mastery across 8 levels - from CS fundamentals and algorithms through clean code, design patterns, system design, DevOps, security, AI-assisted development, and technical leadership. Use this skill for any software development task including implementing features, writing production-grade code, debugging, testing, code reviews, refactoring, performance optimization, and strategic technical decisions. Designed for building MVPs, Micro-SaaS and SaaS with engineering excellence from day one.

Especialista em analise visual e extracao de design de paginas web. Transforma qualquer URL em documentacao tecnica completa de design (cores, tipografia, espacamento, componentes, wireframe) pronta para implementacao. Usar quando o usuario pedir para "analisar design", "extrair design", "copiar estilo", "inspiracao de design", "analisar layout", "extrair paleta de cores", "analisar pagina", ou fornecer uma URL pedindo analise visual. Tambem usar quando precisar replicar o visual de um site existente, fazer engenharia reversa de UI, ou documentar o design system de uma pagina.

Maintain a per-repo napkin as a continuously curated runbook (not a session log). Activates EVERY session. Read and curate it before work, keep only recurring high-value guidance, organize by priority-sorted categories, and cap each category at top 10 items. The napkin lives at `.claude/napkin.md`.

Create comprehensive course materials including detailed schedules, technology summaries, lesson ideas, and educational infographics. Use when the user requests: (1) Creating course schedules/cronogramas with modules and lessons, (2) Technology summaries for Claude Code, Vibe coding, n8n, programming, or other tech topics, (3) Lesson themes and ideas, (4) Educational infographics about technical concepts, (5) Extracting and processing content from URLs (documentation, articles, videos) to create course materials. Outputs are delivered in markdown format with rich detail including objectives, topics, code examples, and practical activities.

This skill should be used when creating marketing campaigns, copywriting content, sales emails, landing pages, or any persuasive communication for selling products/services, especially programming courses and digital products. Use when the user needs help with marketing strategies, mental triggers application, headline creation, sales funnel optimization, or when they need to validate marketing approaches through research. This skill specializes in Gustavo Ferreira's copywriting and mental triggers methodology applied to technology and programming courses.

Build responsive, mobile-first web applications with modern CSS and Tailwind CSS (2025/2026). Use this skill when implementing responsive layouts, touch interactions, mobile navigation, optimizing for various screen sizes, working with breakpoints, container queries, fluid typography, safe areas, or any mobile-first design work. Triggers on: responsive design, mobile-first, breakpoints, touch events, viewport, media queries, container queries, fluid spacing, mobile navigation, hamburger menu, bottom nav, safe area, notch handling.

Comprehensive SEO optimization guidance for websites and web applications. Use this skill when optimizing content for search engines, conducting keyword research, implementing technical SEO (schema markup, sitemaps, robots.txt, canonical tags), improving Core Web Vitals, creating SEO-friendly meta tags, auditing websites for SEO issues, planning content strategy for organic traffic, implementing structured data, or improving page speed. Also use when the user mentions SEO, search rankings, organic traffic, meta descriptions, title tags, keyword optimization, or anything related to search visibility.

Comprehensive code quality verification for Node.js/TypeScript projects before production deployment. Executes Prettier (formatting), ESLint (linting), TypeScript (type checking), and test runners. Use this skill when: - User asks to "verify code quality" or "check code quality" - User wants to "run linter", "run prettier", "run type check", or "check types" - User needs to "prepare code for production" or "pre-deploy check" - User requests "code review" or "automated code review" - User asks to "verify project standards" or "check coding standards" - User mentions "format code", "lint code", or "fix formatting" - Before deploying, merging, or releasing code

Generate premium AI image and video prompts for landing page hero sections. Creates cinematic, commercial-quality visual prompts optimized for tools like Nano Banana, FreePik AI, Google Veo Flow, Runway ML, and Pika Labs. Use when user mentions: - "Criar prompt para hero" / "Hero image prompt" / "Hero video prompt" - "Prompt para landing page" / "Imagem para hero section" - "Video para landing page" / "Visual premium para LP" - "Prompt Nano Banana" / "Prompt para FreePik AI" / "Prompt para Veo Flow" - "Animar imagem de produto" - Any request for premium product visuals for websites Supports: Beverages, Food, Technology, Cosmetics, Fashion, Lifestyle products. Outputs: Structured prompts in English with desktop (16:9) and mobile (9:16) versions.

Especialista em criar PRDs (Product Requirements Documents) técnicos ultra detalhados para geração de landing pages e sites premium usando Gemini CLI como ferramenta de desenvolvimento. Triggers - Usar quando o usuário mencionar: - "Criar PRD para landing page" / "Planejar landing page" - "Documentar site para Gemini" / "Criar especificação de LP" - "PRD para site" / "Arquitetar landing page" - "Briefing de landing page" / "Especificação técnica de site" - "Planejar página web" / "Criar documentação para Gemini CLI" - Qualquer pedido para criar documentação completa de landing page Capacidades: - Extrair contexto profundo através de discovery interativo - Pesquisar inspirações visuais (Dribbble, Awwwards, Behance) - Definir identidade visual completa (cores, tipografia, ícones) - Criar wireframes detalhados (desktop e mobile) - Gerar prompts de imagem para Nano Banana/IA - Entregar documentação completa pronta para Gemini CLI executar

Brainstorming interativo e geração de PRD estruturado para novos projetos

Enforce a precise, minimal design system inspired by Linear, Notion, and Stripe. Use this skill when building dashboards, admin interfaces, or any UI that needs Jony Ive-level precision - clean, modern, minimalist with taste. Every pixel matters.

Assists in creating optimized, well-structured prompts for the ralph-loop plugin. Use this skill when (1) about to use /ralph-loop and need to craft an effective prompt, (2) need to validate a prompt for ralph-loop compatibility, (3) want templates for common ralph-loop use cases (TDD, feature dev, bug fixing, greenfield projects), or (4) need to ensure prompts have clear completion criteria and proper <promise> tags. Ensures prompts follow ralph-loop best practices with measurable success criteria and prevents errors that could compromise project execution.

Generates comprehensive sprint documentation (spec.md, plan.md, tasks.md, research.md, features.xml) following Spec-Driven Development methodology with multi-persona analysis (Architect, Dev, QA, Designer, PM, BA). Use when planning new features or refactoring existing ones. Compatible with long-running-agent. Automatically researches documentation (WebSearch/WebFetch), creates 50-100 granular tasks with E2E (Playwright) and TDD coverage, generates sequential feature IDs (FEAT-XXX), and creates git branch/commit. Always asks interactive questions to gather requirements before generating complete, production-ready context.

Expert guidance for ffuf web fuzzing during penetration testing, including authenticated fuzzing with raw requests, auto-calibration, and result analysis

Comprehensive fullstack development skill combining architecture, testing, security, DevOps, and code quality best practices for building modern web applications from frontend to backend.

This skill should be used when the user asks to "create a prompt for Lisa", "generate PROMPT.md", "write specs for Lisa loop", "prepare Lisa execution", mentions "Lisa plugin", "iterative loops", "spec-based verification", or discusses creating high-quality prompts with completion promises and verification steps for the Lisa Claude Code plugin.

This skill should be used when developing complex projects that span multiple sessions or context windows. It implements the Long-Running Agent Protocol based on Anthropic's recommended practices for maintaining progress across sessions using SubAgents with isolated context windows, progress tracking files, and incremental feature development.