Explorar skills

Activates AIRedTeamer — a specialist in adversarial testing of AI/LLM systems for safety, robustness, and alignment failures. Use when you need to test prompts for jailbreaks, probe model behavior under adversarial inputs, assess AI system safety, evaluate guardrail effectiveness, or design red-team evaluation suites for production LLMs.

Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.

Decomposes research goals into testable Research Questions (RQs). Use at the start of any research task to structure the investigation.

Use to diagnose tests that pass and fail intermittently without code changes.

Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.

Guia profissionais de marketing na medição do impacto de marketing, atribuição de canais, testes de incrementalidade e modelagem de mix. Aciona quando um usuário precisa avaliar o ROI do canal, construir modelos de atribuição, projetar experimentos de marketing ou relatar o impacto de marketing a executivos.

Run an anti-slop cleanup workflow on AI-generated code — regression-tests-first, smell-by-smell, behavior preserved. Supports explicit review-only mode.

Activates WebAppTester for automated web application testing strategy, test case design, and quality assurance. Use when you need to design a test plan for a web app, write Playwright or Cypress end-to-end tests, create API integration test suites, design accessibility test checklists, or analyze test coverage gaps.

Quorum oferece inteligência multiagente para qualquer questão, onde especialistas debatem, desafiam e convergem, e um supervisor entrega o que sobreviveu ao escrutínio. Sua composição de agentes é baseada em pesquisa.

Generate integration tests for APIs, databases, and external services. Auto-detects backend stack (Express, Fastify, NestJS, Django, FastAPI, Rails, Go), ORM (Prisma, TypeORM, SQLAlchemy, GORM), and database (PostgreSQL, MongoDB, Firestore), then creates tests covering endpoint CRUD, auth flows, DB transactions, and external service failures with proper fixtures and mocks. Self-heals failing tests

Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.

Full-stack app pipeline — build, test, review, and deploy across one or ALL repos. Scans CLAUDE.md, MEMORY.md, TODOs, open PRs, and issues for shippable work. Supports 'ship all' for multi-repo. Use when: 'build and ship', 'ship it', 'ship all', 'deploy everything', 'full pipeline', 'what needs shipping', 'end to end'.