Explorar skills

Debug ML training issues and optimize performance including loss divergence, overfitting, and slow convergence

Modal is a serverless cloud platform for running Python on demand, including on-demand GPUs. Use when deploying or serving AI/ML models, running GPU-accelerated workloads (training, fine-tuning, inference), serving web endpoints, scheduling batch jobs, or scaling Python code to cloud containers with the Modal SDK.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, a

Crie interfaces frontend distintas e de nível de produção com alta qualidade de design. Esta skill gera código criativo e polido para componentes web, páginas ou aplicações, evitando a estética genérica de IA.

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.

AI-guided CAR-T cell design for solid tumors using antigen prioritization, safety-by-design architectures, and exhaustion-resistant engineering.

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.

OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstac

Master prompt engineering for AI models: LLMs, image generators, video models. Techniques: chain-of-thought, few-shot, system prompts, negative prompts. Models: Claude, GPT-4, Gemini, FLUX, Veo, Stable Diffusion prompting. Use for: better AI outputs, consistent results, complex tasks, optimization. Triggers: prompt engineering, how to prompt, better prompts, prompt tips, prompting guide, llm promp

Esta skill auxilia no design de testes A/B e no planejamento de experimentos para publicidade paga, oferecendo ferramentas para hipóteses estruturadas, significância estatística, duração do teste, tamanho da amostra e guias de configuração específicos da plataforma.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Um tutor de IA baseado em ciência cognitiva que garante a compreensão genuína através de um ciclo de ensino completo, repetição espaçada e questionários sem dicas. Ele pode ensinar a partir de materiais de origem específicos ou do seu próprio conhecimento de IA.