Explorar skills

Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.

Aprendizado profundo com PyTorch para sequências biológicas, abordando quando usar DL versus ML clássico, arquitetura CNN para detecção de motivos, codificação one-hot e o loop de treinamento padrão.

Create, audit, repair, and document cross-platform symlinks that work correctly on both Windows and macOS/Linux. Use this skill whenever the user mentions symlinks, symbolic links, junction points, .gitconfig symlinks, broken links after git pull, cross-platform path issues, or needs help with ln -s equivalents on Windows. Also trigger when the user reports that files are missing or wrong after sw

Scaffold a deterministic GitHub Actions CI/CD workflow

Rastreamento automático de projetos, gerenciamento de progresso e agentes de qualidade em segundo plano para o Claude Code.

Comprehensive UI/UX design review with Playwright. Evaluates responsive design (375-1920px), WCAG AA accessibility, Nielsen's 10 heuristics, component consistency, and visual polish. Trigger keywords: design review, UI review, accessibility audit, responsive check, heuristic evaluation.

A standard Spec-Kitty workflow routine.

Variantes do Problema da Mochila (Knapsack DP): 0/1, ilimitado e soma de subconjuntos, com rastreamento e otimização de espaço.

Montagem metagenômica com MEGAHIT, agrupamento de contigs com MetaBAT2 e avaliação da qualidade de MAGs com CheckM. Inclui sinais de agrupamento, estratégia multi-amostra e níveis de qualidade MIMAG.

Use when the user wants to check usage, view invoices, or manage payment methods on Zilliz Cloud.

Padrões de inferência de modelos de visão-linguagem para documentos científicos.

Dual-layer dependency graph for vibe-* projects. No external packages. DEPENDENCY_GRAPH.json maps file-level relationships with confidence tagging: EXTRACTED (verified from source, confidence 1.0), INFERRED (derived from specs/patterns, 0.6–0.95), AMBIGUOUS (flagged for review). Rationale nodes capture WHY, HACK, DECISION comments from source files — surfaced during bug diagnosis and review to pre