Desenvolvimento

Save the current conversation context as a reloadable snapshot. Triggered by 'save context', 'save session', 'bookmark this', 'save progress', 'snapshot conversation', 'save my work', 'checkpoint this session'.

Utilize ao iniciar um trabalho em um repositório com Agent Powerups instalados, caso a tarefa possa corresponder a uma skill local reutilizável, comando, fluxo de trabalho, receita de hook, modelo AGENTS.md ou recurso MCP.

Um loop determinístico de 3 ciclos para coletar o contexto da base de código antes de agir. Ele envolve uma busca ampla, seguida pela fonte exata e testes, e então documentação e configuração específicas do alvo. O processo para quando há contexto suficiente ou relata o que ainda está faltando.

Analyze game code for performance bottlenecks including draw call batching and overdraw, shader complexity and LOD strategy, per-frame GC allocation pressure, object pooling gaps, physics timestep and collision matrix tuning, spatial partitioning for entity queries, async scene loading and asset streaming, mobile thermal throttling, WebGL bundle size, and frame budget compliance for 30/60/90 FPS t

Audit risk simulation and decision support systems for Monte Carlo modeling quality, wargaming analysis, threat assessment, mission planning support, and course-of-action decision analysis. Use when reviewing probabilistic risk models, defense planning tools, cost-schedule risk engines, scenario simulators, or decision matrices built on DoD risk management and operational planning frameworks.

Safely analyze code impact before refactors, behavior changes, API changes, and cross-module edits.

Process follow-up files from autonomous runs (ops:batch-execute, ops:get-to-work). Walks through each item, presents options, takes action, and cleans up.

Automate web browsing tasks — navigate websites, click buttons, fill forms, extract data, handle logins. Use when asked to interact with any website or web application.

Audit litigation analytics and case outcome prediction systems -- ML outcome models (logistic regression, gradient boosting, neural nets with temporal train/test splits), settlement range modeling (Monte Carlo simulation, comparable case matching, BATNA analysis), litigation cost forecasting by phase, judge profiling and venue analysis (win rates, motion grant rates, bias safeguards), precedent ma

Relay questions and tasks to a local Claude CLI using one-shot subprocesses per ask.

Bootstrap a project from zero to working dev environment. Detects runtime versions, installs dependencies, creates .env from templates, starts Docker services, runs database migrations, and verifies build plus tests pass. Use when cloning a new repo, onboarding to a project, setting up local development, or troubleshooting a broken dev environment.

Run a comprehensive mobile app QA audit covering permission flows, deep link verification, push notification delivery, offline mode resilience, background/foreground state preservation, memory leak detection, network condition simulation, accessibility compliance, and iOS/Android platform edge cases. Supports Flutter, React Native, and native iOS/Android. Use when you need to QA test a mobile app,