Explorar skills

Use when something is broken, a test is failing, behavior is wrong, when investigating a production incident, when a user reports a bug, when a feature works locally but not in another environment, or when the system behaves differently than the contract specifies.

Batch translate JSON locale files to 39+ languages using LM Studio (local LLM). Structure-preserving translation with validation. Requires i18n-translator extension. Triggers on: /creo i18n, translate, localize, i18n, internationalization.

Audit and fix mobile app UI/UX — enumerates every element on a named screen, questions existence and appearance, then fixes violations. Supports Flutter, Jetpack Compose, SwiftUI, and React Native.

Use when the user asks to fine-tune, train, evaluate, audit, or ship a machine-learning model on the Hugging Face ecosystem — SFT, DPO, GRPO, RLHF, LoRA/QLoRA, post-training, dataset auditing, paper-driven research, hf jobs submission, Trackio monitoring, push-to-Hub. Triggers include "fine-tune", "train a model", "SFT", "DPO", "GRPO", "RLHF", "post-training", "audit this dataset", "literature rev

Um framework de escalonamento de 5 estágios para titulares de contas legítimas cuja recuperação falhou através do suporte padrão da plataforma. Abrange canais legais da plataforma, Procuradores-Gerais estaduais, FTC, escritórios congressionais e engajamento de advogados, para ser usado quando um usuário perde acesso a uma conta de mídia social ou plataforma devido a sequestro, banimento, bloqueio, disputa de faturamento ou personificação.

Diariamente, sugere aos pais uma atividade familiar específica de 3 minutos, focando em interações físicas e emocionais que a IA não pode fazer, estendendo o aprendizado para o tempo em família. Às sextas-feiras, gera atividades de fim de semana. Aciona-se ao final do relatório diário ou quando os pais perguntam sobre o que podem fazer à noite.

Introdução ao Python para Bioinformática.

Use OpenAI Codex CLI (GPT-5.5 + gpt-image-2) programmatically: second-opinion code review, GitHub PR audit, plan/spec auditing, edge-case discovery, style/persona prompting, and subscription-billed image generation for visual assets, decorations, infographics, banners. Activate whenever the user says 'codex', 'second opinion', 'audit plan', 'review PR with codex', 'generate image', 'create banner/

Structured development workflow that sequences planning, building, testing, and shipping. Use when the user says: 'feature flow', 'build this feature', 'implement this', 'dev workflow', 'eagle flow', 'start feature', 'build and ship', 'full dev cycle', 'plan and build', 'implement and review'. Also trigger when the user describes a feature to build and expects the full cycle: planning, implementat

Codex Stage 1 guide for review-loop and the shared Claude/Codex state model.

Fast codebase scouting using parallel agents. Use for file discovery, task context gathering, quick searches across directories. Supports internal (Explore) and external (Gemini/OpenCode) agents.

WAI-ARIA usage guidelines. Avoid redundant ARIA attributes. No ARIA is better than Bad ARIA. Use when writing or reviewing HTML/JSX with accessibility attributes.