raphaelfh

prumo's visual language — the *what it should look like* layer (Plane/Linear/WorkOS aesthetic). Use when deciding layout structure, density, header height, sidebar behaviour, hover affordances, empty states, loading patterns, or any "how should this screen feel" question for frontend/ pages and components. The sibling ui-styling skill is the *how* layer underneath (Tailwind/shadcn/Radix mechanics) — read this one first when designing, that one when implementing classes.

Use this when writing or modifying anything under `backend/app/` — FastAPI endpoints, SQLAlchemy 2.0 async models or queries, Alembic migrations, Celery tasks in `backend/app/worker/`, Pydantic v2 schemas, Supabase RLS policies in `supabase/migrations/`, or `pytest` tests. Covers prumo's HITL stack (extraction + quality assessment), project-membership auth, structlog observability, and the migration split between Alembic (app schema) and Supabase CLI (auth/storage). Trigger on requests like "add endpoint", "create migration", "write a Celery task", "fix RLS", "new SQLAlchemy model", or anything touching `extraction_*` tables or `/api/v1/runs/...` / `/api/v1/hitl/sessions`.

Runbook for shipping prumo to production — promoting dev to main, Railway deploy mechanics (Wait-for-CI, SKIPPED-SHA recovery), Supabase auth/storage migration deploys, env-var rotation, and rollback. Invoke manually with /deploy-release when deploying, promoting, or recovering a stuck deploy.

Use whenever writing, debugging, or designing tests for prumo — Playwright E2E (with a11y + visual), Vitest unit/component, pytest backend integration, MSW v2 network mocks, or whenever a test is flaky. Pulls in the right tool, the right fixture pattern, and the project rule that integration beats heavy mocking. Trigger on "test", "spec", "flaky", "Playwright", "Vitest", "pytest", "MSW", "axe", "snapshot", "visual regression", "test strategy", "mock the database", "test fixture", "CI test".

Use when writing or modifying the STRUCTURE of anything under `frontend/` — where code lives, data flow, and state. Covers components/{domain} organization, TanStack Query hooks + key factories, `services/*Service.ts` via the typed apiClient, Zustand stores vs React Context, react-hook-form + Zod forms, generated `types/api/schema.d.ts`, ErrorResult boundaries, and the React Compiler constraints. Trigger on "add a page", "add a data hook", "add a mutation", "wire a form", "new store", "fetch data", or anything about how the frontend is organized. NOT for visual language (use `frontend-ux`) or Tailwind/shadcn class mechanics (use `ui-styling`).

Use BEFORE claiming done, before writing a PR body, when receiving review feedback (especially unclear or technically questionable), when requesting review, or after completing a feature/bugfix. Enforces technical rigor over performative agreement, evidence-based completion claims, and a prumo-specific review checklist tuned to recurring incident classes (BOLA, run-state TOCTOU, error swallowing, schema drift, ApiResponse envelope drift, stale TanStack cache). Triggers on phrases "looks good", "should be fine", "I'll fix it", "ready to merge", "tests pass", "done", "complete", "fixed", "ready for review", "let me draft the PR". Be pushy about running it.

prumo's visual feedback loop — render the screen, screenshot it, compare to the Plane/Linear target, list the diffs, fix, re-screenshot, confirm. Use BEFORE claiming any frontend screen or component "done", and whenever the ask is "does this look right", "match Linear/Plane", "tighten this screen", "iterate on the UI", "why does this look off / generic / AI-made", or after any non-trivial layout, density, spacing, or theme change. The `/design-review` command runs this loop on a route. Siblings: `frontend-ux` sets the visual language (what it should look like), `ui-styling` is the Tailwind/shadcn mechanics (how to wire the classes); this skill is the *did it actually end up that way* layer that closes the loop with your eyes, not the diff.

Tailwind + shadcn/ui + Radix mechanics for the prumo frontend (Vite + React 19 + TS strict). Use whenever you are adding or editing a `frontend/components/**/*.tsx` file, installing a new shadcn primitive, writing className strings, building a cva variant, touching `frontend/index.css` / `tailwind.config.ts` / `components.json`, wiring dark mode, fixing a contrast/focus/keyboard a11y bug, or hand-rolling a Radix primitive. Be a little pushy: if you are about to write JSX with classes, read this first — it will stop you from inventing colors, breaking the cn() merge order, or shipping focus-less buttons. For the project's *visual language* (Plane/Linear aesthetic, header height, density, hover affordances) see the sibling `frontend-ux` skill; this skill is the *how* layer underneath.

Simula revisão crítica de draft acadêmico (paper, capítulo, grant, proposta) produzindo feedback estruturado por seção com forças, fraquezas, claims sem evidência e sugestões acionáveis. Aplica mental model adequado (TRIPOD+AI / TRIPOD-LLM / DECIDE-AI / CLAIM / CONSORT 2025 / PRISMA / STROBE).

Aplica convenções editoriais de escrita científica em drafts Markdown/Quarto/Pandoc, em pt-BR ou inglês americano (idioma resolvido por cascata, default en-US) — citação sempre imediatamente antes do ponto final, múltiplas citações num único colchete ([@a; @b]), pontuação sem travessão/dois-pontos/ponto-e-vírgula em texto corrido, remoção de superlativo, economia lexical, coesão entre períodos. Preserva conteúdo (forma, não substância).

Gera draft de paper IMRaD venue-aware a partir do PICOT, callouts _extract.md, protocol.md e project_guide.md, com citação strict do acervo ([REF FALTANTE] quando ausente).

Gera projeto pra CEP/CONEP via Plataforma Brasil a partir do PICOT, protocol.md e acervo — estrutura formal (Resumo, Pergunta, Justificativa, Hipótese, Coorte, Métodos, Riscos, TCLE, Cronograma, Orçamento, Conformidade). Citação strict. Linguagem acessível pra revisor não-técnico no Resumo.

Gera prose acadêmica genérica quando o usuário tem texto-base ou só uma seção isolada e não cabe em paper/CEP/statistics. Aceita --seed, --section, --template. Citação strict do acervo.

Gera Plano de Análise Estatística (PAE) — outcome operacional, sample size justification, métricas primárias/secundárias, sensitivity analyses, splits + anti-leakage. Usa PicotSpec.outcome+metrics e protocol.md § Splits. TRIPOD+AI/SPIRIT-AI compatível; TRIPOD-LLM quando o pipeline usa LLM; reporting CONSORT 2025/DECIDE-AI conforme o desenho.

Porta de entrada do prumo-assist. Use quando o pesquisador não sabe por onde começar; lista as capacidades e roteia para a skill certa (paper-manager, paper-extract, wiki-ingest, wiki-query, write-*).

Classifica se cada citação de uma página sustenta a frase que a cita (Fully/Partially/Unsubstantiated) usando os extracts do acervo — SINALIZA apenas, nunca edita nem bloqueia. Roda `prumo paper verify-refs` antes (base determinística: existência/retração/título).

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

Generate a custom checklist for the current feature based on user requirements.

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.

Execute the implementation plan by processing and executing all tasks defined in tasks.md

Execute the implementation planning workflow using the plan template to generate design artifacts.

Create or update the feature specification from a natural language feature description.

Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.