Explorar skills

Formas da hélice do DNA (A/B/Z), geometria do sulco, termodinâmica de vizinhos mais próximos, elementos de estrutura secundária do RNA e notação de ponto-parêntese.

Use the lens library, generating accessors with makeFieldsId for NoFieldSelectors records, export accessors together with their type classes, and prefer lens or OverloadedRecordDot over pattern matching. Use when writing or reviewing Haskell code that uses lens, records, or field access.

Iterative code review and planning discussion between the local agent and Codex CLI. Orchestrates an automatic back-and-forth debate where both agents discuss findings, architecture decisions, or implementation plans until reaching consensus. Codex CLI runs READ-ONLY and never modifies files; model and reasoning effort come from the user's local Codex config. Supports plan mode: when the local age

技术文档编写技能，涵盖 API 文档、架构文档、部署指南和各种技术写作最佳实践。使用此技能创建技术文档、编写 API 文档、创建架构设计文档，或需要部署和运维手册模板时使用。

Explicitly enumerate Haskell module exports instead of exporting everything implicitly, and use re-export sparingly. Use when writing or reviewing Haskell module export lists.

Use when setting latency budgets per request type, when tracking LLM cost per call type, when designing a caching strategy, when reviewing bundle size, when profiling a slow path, or when a service is approaching its latency or cost SLO.

Instruções para descobrir e usar servidores através do registro oficial do MCP, especialmente ao encontrar novas integrações. Para construir servidores personalizados, consulte mcp-reference-servers.

Algoritmos MSA progressivos, seleção de ferramentas por tamanho do conjunto de dados, construção de árvores-guia e alinhamento de perfis.

Algoritmos fundamentais — MDC Euclidiano, método de Newton para raiz cúbica — com análise de complexidade e implementações limpas.

Use when user mentions "security review", "compliance", "SOC 2", "GDPR", "PII", "threat model", when the system handles sensitive data, when preparing for an audit or certification, when assessing risk before launch, or when a STRIDE threat model is needed for a new component.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Incrementally update an existing code-to-docs vault after coding changes. Diffs against the last documented commit, re-analyzes only affected modules, merges with existing docs, and tracks issue resolution. Use when someone says update docs, sync docs, refresh documentation, or after making code changes.