Explorar skills

Scans the codebase for technical debt indicators, categorizes and prioritizes findings, and maintains a debt register with repayment recommendations. Use when assessing codebase health, planning refactoring, or when the user mentions technical debt or code quality.

Investiga bugs, testes falhando, falhas de build, problemas de desempenho e comportamentos inesperados com disciplina de causa raiz antes que qualquer correção seja proposta ou implementada.

Curated documentation reference for developers building with Pinecone. Contains links to official docs organized by topic and data format references. Use when writing Pinecone code, looking up API parameters, or needing the correct format for vectors or records.

Comprehensive Next.js development patterns for App Router, Server Components, TypeScript, and Tailwind CSS. Covers foundational principles, data fetching, routing, performance, and an 8-phase development workflow. Also includes Server Actions and Metadata patterns.

Architecture and design planning for new Claude Code skills. Guides through use case definition, complexity tier selection, sub-skill decomposition, and file structure planning. Use when user says "plan skill", "design skill", "skill architecture", or "skill planning".

Provides architectural patterns for LLM-powered applications and AI assistants, including prompt engineering, RAG, agent loops, conversation management, and evaluation. Use when building AI-based features, chatbots, or complex AI system architectures.

Package and distribute Claude Code skills for sharing via GitHub, Claude.ai uploads, or team deployment. Creates install scripts, documentation, and .skill packages. Use when user says "publish skill", "share skill", "package skill", "distribute skill", or "release skill".

Forces the strict Red-Green-Refactor development cycle. Requires one failing behavior test through a public interface before each implementation slice.

Process audio and video with clipping, conversion, analysis, captions, thumbnails, GIFs, and batch utilities. Use for practical media manipulation workflows.

Identifies performance bottlenecks, measures against budgets, and generates prioritized optimization recommendations. Use when investigating slow performance or when the user mentions performance profiling, bottleneck, or optimization.

Requires fresh verification evidence before claiming work is complete, fixed, passing, safe, ready, merged, or clean. Use before completion claims, commits, PRs, merge readiness, or moving to the next task.

Revisa textos em Markdown conforme as regras fixadas do estilo de agente v0.3.5 e, opcionalmente, escreve uma cópia aprimorada ao lado da fonte. Use para especificações, ADRs, corpos de PR, notas de lançamento e documentos técnicos quando a qualidade da prosa ou a disciplina de evidências forem importantes.