Design e Frontend

Target unit handling for MMM: monetary vs acquisition vs volume targets, CPA vs ROAS framing, and value-per-unit conversions. Use when the target variable is not a currency amount (e.g., policies sold, signups, app installs), when designing the spec.yaml target_unit field, or when a CFO report needs to show both CPA and revenue-equivalent ROAS.

This skill should be used when the user asks to conduct a UX review, UX audit, usability review, heuristic evaluation, or design critique of any digital product. Trigger phrases include: 'review this app', 'UX audit', 'UX review', 'critique this design', 'what's wrong with this UI', 'analyze this screen', 'teardown this app', 'heuristic evaluation', 'usability review', 'evaluate the UX', 'design f

Redução de dimensionalidade e agrupamento de scRNA-seq, utilizando PCA, grafo k-NN, UMAP e Leiden. Inclui um guia para seleção de parâmetros, padrões de implementação e armadilhas comuns.

Tiered memory system for cognitive continuity across agent sessions. Manages hot cache (session context loaded at boot) and deep storage (loaded on demand). Use when: (1) starting a session and loading context, (2) deciding what to remember vs forget, (3) promoting/demoting knowledge between tiers, (4) user says 'remember this' or asks about project history.

Model construction and prior specification for Marketing Mix Models with pymc-marketing. Use when building a new MMM, choosing adstock/saturation transformations, specifying priors with moment matching, configuring the likelihood, setting up the model constructor, or designing the fitting strategy. Also activate when discussing prior calibration, spend-share sigma, channel prior tables, or model_c

A genética populacional abrange o equilíbrio de Hardy-Weinberg, simulação de deriva de Wright-Fisher, modelos de seleção, relógio molecular, dN/dS, D de Tajima, Fst e desequilíbrio de ligação.

Run the planning phase only: drive a work item from raw description to a reviewer-approved plan in `.review-loop/sessions/{uuid}.md`, then exit with a hint to resume via `review-loop:execute --session <uuid>`. Use when you want plan-only iteration without immediately entering execution.

Avalie um executivo ou contratação sênior usando a estrutura 'culpado até prova em contrário' de Brian Chesky. Gera um roteiro de verificação de referências, identifica sinais de alerta e avalia o ajuste entre construtor e gerente para candidatos a funções sêniores.

Build and maintain a unique, consistent LinkedIn voice for one or more users. Runs a framework-driven persona interview (brand archetypes + tone spectrum + hot-take exercises), then generates ready-to-publish LinkedIn posts across a 30/25/20/15/10 content mix (Personal / Work / Thought-leadership / Educational / Promotional). Handles multi-user installs — teams, agencies, or families can share one

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.

Set up Claude Code for this project — interviews you, builds CLAUDE.md and settings, then has the curator subagent review everything before handing off

Rules for useEffect usage in React including when to avoid it and when to extract it into custom hooks. Use when writing or reviewing React components that contain or might need useEffect.