Explorar skills

Progressively migrates legacy prototype routes and features to a clean architecture layer slice-by-slice, verifying them against characterization tests, running purity/drift checks, and executing completion certifications.

Esta skill oferece um conselho de revisão de código multiperspectiva, onde consultores analisam, revisores questionam e um presidente sintetiza o veredito. É ideal para decisões de arquitetura, auditorias de segurança e revisões profundas, não para geração de código simples ou correções de sintaxe.

Especializado em regressão, correlação e diagnósticos em R, cobrindo intervalos de confiança, testes t, testes de normalidade, correlação de Pearson/Spearman/Kendall e IC da transformação z de Fisher.

First-time Qualflare setup for this project. Detects languages and test frameworks, writes .qualflare/test-state.md, and configures the optional Stop hook. Use when the user runs /qf-init or asks to "set up Qualflare" or "initialize Qualflare".

Initialize HuggingFace integration - validates .env variables, tests API connectivity, and ensures the dataset repository structure exists. Use when onboarding a new project to HuggingFace or when credentials change.

Use this skill whenever a task requires integrating with an external or internal API — HTTP clients, SDK calls, gRPC stubs, webhooks, or any network boundary. Verifies that an API spec (OpenAPI/Swagger, GraphQL schema, Protobuf, AsyncAPI, or equivalent) is configured and referenced in the plan or design artifact, then probes the endpoint to confirm reachability in the current environment. If the s

[INTERNAL TEMPLATE] Visual evidence capture and regression testing protocol. Called by agent-browser orchestrator.

MAGI System - 三機平行共識決策系統，參考新世紀福音戰士的 MAGI 超級電腦。三機（Claude Opus、Codex-CLI、Gemini）同時平行分析同一任務，各自提出觀點後進行投票共識。支援 brainstorming、架構審查、plan、review、security、test 等任務類型。

Esta skill oferece revisão automatizada de PR e análise de qualidade de código. Ela é ativada para revisar pull requests, auditar código ou buscar problemas, utilizando sub-agentes paralelos para diversas lentes de revisão e sintetizando um relatório estruturado.

Use this skill after Phase 2 Analyze to produce the design artifacts a build depends on — application architecture, data/platform/infrastructure/security architecture, test architecture, test cases, technical specifications, and DevOps pipeline design. Validates existing architecture artifacts against current requirements before writing new ones. Trigger after requirements have been approved, or w

Use this skill during Phase 6 to deploy code that has passed Phase 5 Test. Updates tickets with deployment details when a ticketing system is configured; otherwise generates deployment artifacts as markdown or JSON under .claude/sdlc/deployments/. Never auto-executes a deployment — always proposes and waits for explicit human confirmation. Trigger after test is signed off, or when the user says "d

Armadilhas e padrões de uso de operadores em bioinformática, como divisão inteira para códons, módulo para quadros de leitura, precedência de conteúdo GC e testes de associação.