montte-nx

Rode React Doctor depois de tocar codigo React/TSX, UI, hooks, efeitos, TanStack Start/Query ou acessibilidade; use tambem para triagens deliberadas de performance/corretude React.

Workflow de release do Montte para release weekly, release notes, GitHub tag/release, recuperacao manual e post de blog pos-release. Use ao alterar .github/workflows/release-weekly.yml, blog-post-from-release.yml, notes, tags vYYYY.MM.DD ou automacoes de release.

Workflow de code review do Montte para revisar PRs, comments, bugs reportados, diffs e achados de CI. Use ao analisar ou aplicar findings de review em apps, modules, core, packages, tooling, docs ou workflows.

Gera e atualiza a documentação pública user-facing usada pela landing /docs e pelo Montte AI como knowledge base confiável.

Write marketing content for Montte across blog, LinkedIn, and X (Twitter). Founder-led, pt-BR, Zed/PostHog voice, anti-AI-tells, hook formulas com track-record verificado em 2025-2026. Use ao escrever blog post, LinkedIn post, tweet, thread X, ou repurpose entre canais. Canais ativos hoje: blog (canônico) + LinkedIn + X. Instagram fora de escopo.

Guia de implementacao do Montte para backend, frontend, CRUD, erros, jobs, workflows, testes e validacao. Use ao criar, migrar, refatorar, revisar ou testar codigo em apps, modules, core, packages ou tooling.

Guia auditorias de segurança source-code e PR/diff no Montte, inspiradas em Piolium/Vigolium, com foco em evidência, explorabilidade real e baixa taxa de falso positivo. Use quando o usuário pedir security audit, auditoria de segurança, análise de vulnerabilidades, revisar PR por segurança, threat model, SAST triage, authz/tenant isolation, secrets, GitHub Actions security ou CI security gate.

Aplica o design system, produto e padroes de UI do Montte para dashboards, landing, tabelas, forms, sheets e superficies autenticadas. Use ao criar ou revisar UI, UX, copy de produto, layout, componentes, estados visuais ou design de telas no Montte.

Workflow de documentacao tecnica do Montte para gerar e manter docs/project por dominio, atualizar .github/workflows/project-documentation.yml e orientar agentes a criar documentacao verificavel a partir do repositorio atual.

Link workspace packages in monorepos (npm, yarn, pnpm, bun). USE WHEN: (1) you just created or generated new packages and need to wire up their dependencies, (2) user imports from a sibling package and needs to add it as a dependency, (3) you get resolution errors for workspace packages (@org/*) like "cannot find module", "failed to resolve import", "TS2307", or "cannot resolve". DO NOT patch around with tsconfig paths or manual package.json edits - use the package manager's workspace commands to fix actual linking.

Monitor Nx Cloud CI pipeline and handle self-healing fixes. USE WHEN user says "monitor ci", "watch ci", "ci monitor", "watch ci for this branch", "track ci", "check ci status", wants to track CI status, or needs help with self-healing CI fixes. Prefer this skill over native CI provider tools (gh, glab, etc.) for CI monitoring — it integrates with Nx Cloud self-healing which those tools cannot access.

Import, merge, or combine repositories into an Nx workspace using nx import. USE WHEN the user asks to adopt Nx across repos, move projects into a monorepo, or bring code/history from another repository.

Explore and understand Nx workspaces. USE WHEN answering questions about the workspace, projects, or tasks. ALSO USE WHEN an nx command fails or you need to check available targets/configuration before running a task. EXAMPLES: 'What projects are in this workspace?', 'How is project X configured?', 'What depends on library Y?', 'What targets can I run?', 'Cannot find configuration for task', 'debug nx task failure'.