Desenvolvimento

Analyze application logs to identify errors, performance issues, and security anomalies. Use when debugging issues, monitoring system health, or investigating incidents. Handles various log formats including Apache, Nginx, application logs, and JSON logs.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Safety guardrails - warns before destructive commands (rm -rf, DROP TABLE, force-push). CARL TRIGGERS: be careful, careful mode, destructive command warning, safety warning. SOURCE: garrytan/gstack/careful, integrated as gs-careful on 2026-05-29.

Padrões de arquitetura amigáveis à IA para projetos TypeScript, incluindo Domain-Driven Design, Clean Architecture, Hexagonal Architecture e padrões de teste Page Object Model.

When the user wants to validate product-market fit, measure PMF, or plan before scaling. Also use when the user mentions "PMF," "product-market fit," "product market fit," "Sean Ellis test," "very disappointed," "vitamin vs painkiller," "PMF validation," "premature scaling," or "validate before scale." For GTM after validation, use gtm-strategy.

Design judgment via design-director taste — reads design intent, assesses whether execution serves it, returns opinionated verdict with clear direction. Scales from one element to a whole app. Always judgment, never fixing. Invoke ONLY via /eye — do NOT trigger on 'review the design' or 'how does it look'.

Master Rust async programming with Tokio, async traits, error handling, and concurrent patterns. Use when building async Rust applications, implementing concurrent systems, or debugging async code.

Build financial models, backtest trading strategies, and analyze

Per-call and aggregated latency tracking for MEV infrastructure. Use when implementing performance monitoring or debugging slow operations. Triggers on: latency, timing, performance, slow, speed, instrumentation.

Patiently AI simplifies medical documents for patients. Takes doctor's letters, test results, prescriptions, discharge summaries, and clinical notes and explains them in clear, personalised language. Built by PharmaTools.AI.

Use when implementing any feature or bugfix, before writing implementation code

Use when setting up LibreChat logging, configuring metrics collection, integrating Langfuse for LLM observability, tracking token usage and costs, or analyzing LibreChat server logs. Also use when asked about monitoring LibreChat in production or debugging performance from logs.