Explorar skills

Opcional — necessário apenas para uso direto da API. CLI e MCP utilizam OAuth via `auto login`.

Optimize CLAUDE.md and docs/ ecosystem following Boris Cherny and Thariq Shihipar's best practices

Query NHGRI-EBI GWAS Catalog for SNP-trait associations. Search variants by rs ID, disease/trait, gene, retrieve p-values and summary statistics, for genetic epidemiology and polygenic risk scores.

Impeça que agentes de IA contornem secretamente suas regras através de uma aplicação mecânica com git hooks, detecção de segredos, verificação de implantação e registros de importação. Nascida de incidentes reais de produção, esta solução funciona com Claude Code, Clawdbot e Cursor para uma aplicação contínua.

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Comprehensive security assessment and remediation. Use for security reviews, compliance checks, vulnerability assessments.

Esta skill oferece um fluxo de trabalho de desenvolvimento sistemático (Analisar → Planejar → Executar → eLicit → eXaminar) para qualquer tarefa, incluindo novas funcionalidades, correção de bugs e refatoração. Ela detecta automaticamente o tipo de projeto e impõe boas práticas como arquivos pequenos e princípios SOLID.

Autonomous Dependabot — auto-discover outdated packages, audit overrides, apply migrations for major bumps, resolve conflicts, run quality gate. Trigger when the user clicks the statusline `Run /update-deps` indicator or asks "update dependencies", "bump deps", "run dependabot".

Use this skill for Next.js App Router patterns, Server Components, Server Actions, Cache Components, and framework-level optimizations. Covers Next.js 16 breaking changes including async params, proxy.ts migration, Cache Components with "use cache", and React 19.2 integration. For deploying to Cloudflare Workers, use the cloudflare-nextjs skill instead. This skill is deployment-agnostic and works

Restores full context when user says "hi-ai" or starts a new conversation. Searches project files, loads memory indexes, reads session state, and creates visual dashboard showing current project, recent decisions, active blockers, and quick actions. Use when user says "hi-ai", "continue", "restore context", or starts a fresh conversation.

Use ONE Bash script instead of N sequential Read calls when analyzing multiple files, auditing codebase, finding all matches, scanning dependencies, counting lines, or listing files matching a pattern. Replaces wasteful multi-Read loops with compact shell pipelines.

Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first