Explorar skills

Forbid unsafe Haskell functions such as unsafePerformIO, unsafeCoerce, and other unsafe-prefixed functions. Use when writing or reviewing Haskell code that uses any unsafe-prefixed function.

Use when a task is complete and ready for review, when reviewing a PR, when validating an implementation against its contract, when checking quality before merging, or when a five-axis quality gate is needed before approving code.

Complete pymc-marketing API reference for writing and reviewing MMM code. Use when you need exact constructor signatures, method names, parameter lists, or code patterns for pymc-marketing v0.19.1+. Load this skill when writing new model code, debugging import errors, checking method signatures, or reviewing code that uses pymc-marketing. Also activate when you need to look up plotting methods, ev

Fluxos de trabalho de geração de imagens e restauração de problemas inversos.

Investigate any topic by querying multiple external sources (web, official docs, GitHub, MCP servers). Use whenever a question requires information not already in the working context, including library behavior, API specifications, error diagnostics, version comparisons, or general factual lookup.

Triggers the L5 Red Team Sub-Agent to rigorously audit a plugin against the 39-point L4 pattern matrix.

This skill should be used when the user asks about 'knowledge gaps', 'package coverage', 'which packages need notes', 'undocumented dependencies', 'dependency audit', 'missing documentation', 'tool coverage', 'undocumented tools', 'brew/action/docker/vscode coverage', 'standard coverage', 'protocol coverage', 'domain standards', 'concept gaps', 'missing hub notes', 'undocumented concepts', 'topics

Conjuntos e Contador para bioinformática: operações com listas de genes (interseção/união/diferença), deduplicação de k-mers e rastreamento de elementos únicos. Apenas padrões bio-específicos.

Utilize ao criar equipes de agentes que precisam de visibilidade de discussão compartilhada, indo além das mensagens diretas (DMs) em formato hub-and-spoke.

Testes Cypress E2E e de componentes de nível de produção, cobrindo seletores, stubbing de rede, autenticação, paralelização CI, eliminação de falhas intermitentes, Page Object Model e suporte a TypeScript. Esta é a skill Cypress completa para agentes de IA.

Use when establishing visual foundations for a new product, when defining design tokens, when building or auditing a component library, before any UI work begins on a fresh codebase, or when the existing UI has drifted into hex codes and magic numbers.

Análise do número de cópias de DNA — normalização da profundidade de leitura, segmentação CBS, chamada de estado de CN e visualização em todo o genoma.