Desenvolvimento

When the user wants to optimize for AI search visibility (ChatGPT, Claude, Perplexity, AI Overviews). Also use when the user mentions "GEO," "AEO," "generative engine optimization," "AI search visibility," "LLM optimization," "GitHub GEO," "Grokipedia," "optimize for ChatGPT," "AI Overviews," "Bing Copilot," "Yandex AI," "Perplexity optimization," "GEO strategy," or "AI search optimization." For t

Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.

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'.

Implement comprehensive observability for service meshes including distributed tracing, metrics, and visualization. Use when setting up mesh monitoring, debugging latency issues, or implementing SLOs for service communication.

Profile and optimize Python code using cProfile, memory profilers, and performance best practices. Use when debugging slow Python code, optimizing bottlenecks, or improving application performance.

Pro mode — engineering standard enforcement. Forces senior-engineer behavior: root-cause discipline, layer awareness, current-gen API verification, blast-radius thinking, caller-first API design, no stubs, no sycophantic agreement, no unverified assumptions. Invoke via /prodev or 'prodev' — always run via Skill tool, never skip or summarize.

Generates complete Solana blockchain projects with Anchor framework (v0.32.1) and Next.js frontend including Rust smart contracts, tests, and wallet integration. Use when creating Solana dApps, NFT marketplaces, token programs, DAOs, DeFi protocols, or when user mentions Solana, Anchor, or blockchain projects.

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.

Claude Code 스킬, 훅, 에이전트, 명령어를 생성하고 관리하기 위한 메타 스킬. 새 스킬 생성, 스킬 트리거 설정, 훅 설정, Claude Code 인프라 관리 시 사용.

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

Test LogiDocs Certify features from customer persona perspectives. Use when the user wants to test features as a customer, get simulated feedback, review UI from user perspective, or mentions "test as Aftrac", "test as Sirius", "customer feedback", "user testing", or "persona review".

Create Mermaid software diagrams: flowcharts, sequence, class, ERD, C4, state, git, pie, and gantt; use for diagram, visualize, model, map out, show the flow, architecture, database, code, or user-flow docs.