Browse Skills

This skill simplifies running and managing LLMs like VLLM, enabling efficient experimentation and deployment for developers and researchers.

This skill assesses LLM performance within a harness, providing insights into accuracy and efficiency for optimized deployments.

Langsmith Observability monitors your LLM deployments, surfacing insights into performance and errors to improve reliability & troubleshoot issues quickly.

This skill streamlines LLM integration by automatically deploying and configuring GPT models for your projects, boosting AI capabilities quickly.

Continuously monitors open-source LLM deployments for prompt injection vulnerabilities and security risks using automated analysis.

Official elastic skill for LLMs — helps with software development workflows.

Serves LLMs like VLLM efficiently for experimentation and deployment, streamlining development workflows and scaling AI applications.

Provides deployment guidance and assistance for software development workflows.

This skill streamlines LLM integration by automatically deploying and configuring GPT models for your projects, boosting AI capabilities quickly.

This skill deploys and integrates LLMs like ChatGPT for enhanced conversational AI applications and content generation.

This skill assesses LLM performance within a harness environment, providing insights for optimization and ensuring consistent results across deployments.

This skill provides a concise guide to using the Llmlb CLI for managing your LLM deployments and configurations effectively.

Automate LangSmith deployment and configuration for seamless LLM observability and debugging workflows.

Quickly deploy vLLM inference endpoints with a single command, simplifying large language model serving.

Automates vLLM model deployment and scaling across infrastructure for optimized performance and resource utilization.

Reduces LLM file sizes & speeds up inference by quantizing GGuf models – making them more efficient to run and deploy.

Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) for secrets, PII, prompt injection, and dangerous patterns. Runs 4 model behavior probes (persuasion, sandbagging, deception, hallucination). Supports LLM-enhanced semantic analysis. Works with OpenClaw, Claude Code, Cursor, and Codex. Use when a user asks for a security audit, health check, or wants to scan their AI agent setup for vulnerabilities.