Skill UI

Secure LLM-powered applications against prompt injection, data leakage, and abuse using input validation, output controls, and tenant isolation. Implements OWASP LLM Top 10 mitigations with Python and Node.js examples.

Improve LLM prompts using task-specific evaluation, structured instructions, chain-of-thought reasoning, and regression checks for production-ready AI applications.

This skill helps reduce LLM API and infrastructure costs by 50-90% using strategies like model selection, prompt caching, batching, quantization, and self-hosting. It covers cost tracking, right-sizing models for tasks, provider-side caching, and semantic caching to avoid redundant calls. Suitable for developers managing AI spend and optimizing cloud infrastructure.

Run Fireworks-hosted open-weight model councils that compare responses and synthesize a final answer. This skill implements Karpathy's LLM Council concept with parallel model responses, ranking, and chairman synthesis.

This skill covers setting up infrastructure for fine-tuning Large Language Models (LLMs) using techniques like QLoRA, LoRA, and full fine-tuning. It includes configuring distributed training with DeepSpeed or FSDP, utilizing frameworks such as Hugging Face TRL and Axolotl, and implementing alignment methods like RLHF and DPO. Suitable for domain-specific model adaptation and production deployment.

This skill enables horizontal scaling of Large Language Model inference clusters on Kubernetes. It utilizes KEDA for event-driven autoscaling based on custom GPU metrics like request queues and cache usage. The guide covers deploying vLLM on GPU nodes, configuring Prometheus for monitoring, implementing spot instance strategies for cost efficiency, and setting up queue-based scaling for batch jobs. It ensures optimal resource utilization and cost management for high-traffic AI workloads.

Comprehensive guide to LLM Operations (LLMOps). Covers advanced topics like Retrieval-Augmented Generation (RAG), vector database management (Pinecone, Chroma), embeddings, fine-tuning, prompt engineering, and cost optimization. Essential for bridging the gap between AI prototypes and reliable, scalable, production-grade AI systems.

This skill provides comprehensive techniques for optimizing prompts used with any Large Language Model (LLM). It teaches proven methodologies—including Role definition (R), Context setting (S), Constraints (C), Instructions (I), and Templates (T)—to transform vague inputs into precision-engineered instructions. Users can reliably achieve structured JSON output, implement Chain-of-Thought reasoning, reduce hallucinations, and minimize token usage, ensuring consistent and high-quality results across different AI platforms.

Conduct authorized security assessments for LLM applications and AI agents. Covers prompt injection, tool abuse, RAG exposure, memory poisoning, and system prompt extraction following OWASP LLM/ASI Top 10 guidelines. Includes red-teaming, vulnerability mapping, and compliance engineering for AI systems to ensure safety and robustness.

An expert guide for deploying and optimizing Large Language Models (LLMs) entirely on local hardware. Mastering the entire local AI ecosystem, including inference engines like Ollama, vLLM, and llama.cpp. Provides deep knowledge on quantization formats (GGUF, EXL2, AWQ), VRAM calculation, and ensuring privacy-first, offline deployment for state-of-the-art models.

Loki Mode is a multi-agent autonomous startup system designed to execute workflows from PRD to production without human intervention. It integrates research-enhanced AI models including OpenAI SDK, DeepMind, Anthropic, and AWS Bedrock. This skill ensures zero human involvement in the deployment process while maintaining strict constraints on dependencies and response times.

Discover, find, compare, audit, repair, adapt, craft, run, debrief, and prepare repeatable AI-agent loops for publication. A comprehensive tool for managing bounded feedback loops in AI agent workflows.