命令列工具

Implementar clientes de infraestrutura em infrastructure/. Use quando criar client externo, configuração, integração LLM, tracing, ou conexão com serviços fora do synth-lab.

Medical PowerPoint presentation generation with clinical data visualization. Creates professional presentations from FHIR resources, lab results, and clinical data. Use when generating patient summaries, care plans, medical reports, or clinical presentations with proper healthcare formatting.

CRITICAL - Guide for using Claudish CLI ONLY through sub-agents to run Claude Code with OpenRouter models (Grok, GPT-5, Gemini, MiniMax). NEVER run Claudish directly in main context unless user explicitly requests it. Use when user mentions external AI models, Claudish, OpenRouter, or alternative models. Includes mandatory sub-agent delegation patterns, agent selection guide, file-based instructions, and strict rules to prevent context window pollution.

Complete WordPress white-labeling using FREE plugins only - ASE, Branda, White Label CMS, Admin Menu Editor. Covers login page branding, admin cleanup, security hardening, and client handoff preparation.

Use when operating Codex CLI itself (config, profiles, sandbox, approvals, and safe usage patterns).

Design CLI tools with consistent UX patterns.

Get real-time weather information using web search. Use when user asks about weather, temperature, forecast, or climate conditions for any location. Supports voice input (microphone) and voice output (TTS). By default outputs BOTH text and voice.

Master programming fundamentals, algorithms, data structures, and multiple languages. Covers Python, Java, Go, Rust, C++, Kotlin, Bash, and computer science essentials for every developer.

Central CLAUDE.md file with project guidelines auto-injected into system prompt, achieving 10% accuracy lift in multi-hop reasoning through consistent context. Use for repo-wide context, coding standards enforcement, project guidelines, or architecture documentation. Auto-loaded by Claude Code CLI. Triggers on "project context", "coding standards", "CLAUDE.md", "project guidelines", "repo documentation".

Review security risks and mitigations for remote WebF content (untrusted bundles, URL allowlists, HTTPS, trust boundaries, clickjacking). Use when the user mentions untrusted remote bundles, bundle URL validation/allowlists, or remote updates risk.

Atlassian Rovo Dev CLI 어댑터 (ACLI 서브커맨드). Jira/Confluence 통합 AI 개발 도구.

Use when creating REST API clients, SDK wrappers, or HTTP service integrations. Generates type-safe client code with retry logic, error handling, rate limiting, and comprehensive tests. Triggered by requests to integrate external APIs, build SDK clients, or create service wrappers.

Expert UX evaluator for command-line interfaces, CLIs, terminal tools, shell scripts, and developer APIs. Use proactively when reviewing CLIs, testing command usability, evaluating error messages, assessing developer experience, checking API ergonomics, or analyzing terminal-based tools. Tests for discoverability, consistency, error handling, help systems, and accessibility.

Execute AI-powered command-line tasks with memory, replay, and resume capabilities using memex-cli. Use when (1) Running AI backend tasks (codex, claude, gemini), (2) Replaying recorded events from JSONL files, (3) Resuming interrupted runs by run_id, (4) Executing prompts with streaming output in jsonl or text format.

Run a batch of visual comparisons defined in a uiMatch suite JSON file using @uimatch/cli, then read each report to summarize which components passed or failed their quality gates. Use this skill when the user wants to run many Figma-vs-implementation checks at once, such as CI-style validation for a component library or flow.

Create apps following contract-port architecture with composition roots. Use when creating new apps in apps/, scaffolding CLI tools, setting up dependency injection, or when the user asks about app structure, entrypoints, or platform-agnostic design.

Create debug test plan from user input. Use when planning browser debug sessions with Chrome DevTools. Parses prompt for URL/target, identifies interactions to test (clicks, inputs, flows), confirms plan with user via HITL, creates specific test steps (navigate, click, fill, verify). Outputs URL and test plan for debug execution.

Asks Gemini CLI for coding assistance. Use for getting a second opinion, code generation, debugging, or delegating coding tasks.

This skill should be used when configuring or using the OpenCode CLI for headless LLM automation. Use when the user asks to "configure opencode", "use opencode cli", "set up opencode", "opencode run command", "opencode model selection", "opencode providers", "opencode vertex ai", "opencode mcp servers", "opencode ollama", "opencode local models", "opencode deepseek", "opencode kimi", "opencode mistral", "fallback cli tool", or "headless llm cli". Covers command syntax, provider configuration, Vertex AI setup, MCP servers, local models, cloud providers, and subprocess integration patterns.

Enhance and refine prompts for AI coding agents using Chain-of-Thought reasoning. Use when user asks to improve, optimize, rewrite, or enhance a prompt. Transforms vague requests into structured, high-context instructions for Claude Code, Codex, or Gemini CLI.