发现 Skills

Autonomous GenPark Corporate Training Designer agent for the GenPark Nexus ecosystem.

Build custom UIs on top of Claude Code's headless mode. Covers spawning, NDJSON protocol, permission hooks, and session management. Use when building a desktop app, TUI, web UI, or any custom interface that wraps Claude Code as a subprocess.

Use when making design decisions in Python code - specifically when choosing between patterns, deciding on abstraction levels, or evaluating code complexity

Navigue vers YouTube (youtube.com) dans Safari. Utilisé après open_safari pour accéder à YouTube.

Ouvre Gmail dans le navigateur, compose et envoie un email. Fonctionne via Playwright.

Deploy containerized frontend + backend applications to Azure Container Apps with remote builds, managed identity, and idempotent infrastructure.

Use when a user asks for a plan for a coding task, to generate a clear, actionable, and atomic checklist.

Identify and exploit file path traversal (directory traversal) vulnerabilities that allow attackers to read arbitrary files on the server, potentially including sensitive configuration files, credentials, and source code.

Expert firmware analyst specializing in embedded systems, IoT security, and hardware reverse engineering.

Use when working with full-stack orchestration features

Forensic appraisal of properties in auction. Market value, forced liquidation value, ABNT NBR 14653, direct comparison/income/cost methods, CUB and safety margin.

You are an SLO (Service Level Objective) expert specializing in implementing reliability standards and error budget–based engineering practices. Design comprehensive SLO frameworks, establish meaningful SLIs, and create monitoring systems that balance reliability with feature velocity.

MQTT (Message Queuing Telemetry Transport) is a lightweight publish/subscribe messaging protocol designed for IoT and low-bandwidth, high-latency networks. It provides a simple and efficient way to connect devices and applications.

Investigate, diagnose, and explain why a SailPoint access request is blocked, stuck, failing, pending, or not completing. Use this skill whenever the user asks about an access request that isn't going through, wants to know why a request is stuck, asks about approval status, provisioning failures, access request errors, pending requests, blocked requests, denied requests, or anything related to the lifecycle of an access request in SailPoint Identity Security Cloud. Also trigger when the user says things like "why is my access request stuck", "where is my request blocked", "request won't complete", "who needs to approve", "provisioning failed", "access request error", "show me pending requests", "what happened to my request", "request is taking forever", "can't get access", or "request status".

QA automatizado com Playwright. Simula usuario real navegando na aplicacao - clica, preenche, navega, e captura tudo que quebra (erros de console, falhas de rede, UI inacessivel, fluxos interrompidos). Gera report visual com screenshots e logs. Use apos /construir e /validar para verificar que a aplicacao funciona de ponta a ponta.

Teste exploratorio via Playwright CLI. Navega na aplicacao como usuario real usando browser controlado por IA. Captura screenshots, erros de console, problemas de acessibilidade. Gera relatorio estruturado. Use para QA exploratoria antes de merge ou apos deploy.

UX-QAT PDCA Orchestrator — executa Visual Quality Acceptance Testing com ciclo Plan-Do-Check-Act. Captura screenshots por breakpoint/tema, avalia com AI Judge multimodal, classifica falhas visuais, atualiza KB automaticamente.

Hot-reloadable Flecs modules as Rust dylibs. Covers module architecture, component vs system modules, and inter-module dependencies.

Purpose: Generate stable and maintainable locators for UI automation.

Manage Codex runtime setup and job lifecycle using setup, status, result, and cancel commands.

Drive Antigravity's Open Agent Manager UI to perform file-editing tasks with the built-in LLM when the user explicitly asks for "Antigravity LLM 模式" or wants Antigravity itself—not direct file edits—to handle development. Use for UI-driven agent execution in Antigravity, especially when tasks must be sent through Open Agent Manager with a focused input box, English half-width input mode, explicit workspace/file paths, and post-edit verification.

AFL++ is a fork of AFL with better fuzzing performance and advanced features. Use for multi-core fuzzing of C/C++ projects.

Use when developing firmware for microcontrollers, implementing RTOS applications, or optimizing power consumption. Invoke for STM32, ESP32, FreeRTOS, bare-metal, power optimization, real-time systems, configure peripherals, write interrupt handlers, implement DMA transfers, debug timing issues.

Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug directly) when the user reports errors, 500 errors, stack traces, unexpected behavior, "it was working yesterday", or is troubleshooting why something stopped working. (gstack)