Explorar skills

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Single-entry slash command for the Peec AI growth loop. Detects whether the current working directory has a setup_state.json, what state it's in (missing / fresh / stale / very stale / brownfield-importable), and hands off to the right skill — /peec-setup (full or import or audit) or /peec-agent. Use when the user says "/peec-start", "what should I do for Peec", "is my setup done", or any opening

Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback. No API keys required.

Activates AIRedTeamer — a specialist in adversarial testing of AI/LLM systems for safety, robustness, and alignment failures. Use when you need to test prompts for jailbreaks, probe model behavior under adversarial inputs, assess AI system safety, evaluate guardrail effectiveness, or design red-team evaluation suites for production LLMs.

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

Guarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize inference speed with Outlines - dottxt.ai's structured generation library

Activates PromptEngineer for system prompt design, prompt optimization, and LLM evaluation. Use when you need to design a system prompt for a Claude-based application, optimize prompts for accuracy and consistency, implement chain-of-thought reasoning, build evaluation frameworks (evals) to measure prompt quality, or prevent prompt injection and jailbreaks.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.

Esta skill realiza auditorias de SEO, GEO e AEO para qualquer site, mapeando cada verificação às melhores práticas do Google para Busca, Visões Gerais de IA, Core Web Vitals, dados estruturados e camadas de recuperação cross-LLM. Cada achado cita sua documentação do Google ou do provedor.

Run 150+ AI apps via inference.sh CLI (infsh) — image generation, video creation, LLMs, search, 3D, social automation. Uses the terminal tool. Triggers: inference.sh, infsh, ai apps, flux, veo, image generation, video generation, seedream, seedance, tavily

Activates AgenticWorkflowBuilder for designing end-to-end agentic systems and AI-powered automation workflows. Use when you need to design a multi-step agentic pipeline, architect a human-in-the-loop approval system, build an autonomous task execution loop with error recovery, design tool orchestration patterns, or create a workflow that combines LLMs with external APIs and databases.

Turns a Peec AI prompt set into strategic content zones — not keyword groups. Groups prompts by buyer intent + funnel stage + visibility gap + shared demand signals, producing 4–8 "content zones" with the competitive weakness to attack, supporting evidence (forum quotes, SERP patterns), and a rank-ordered next-move per zone. Use when a Peec project has 20+ prompts and needs a topic architecture —