Agent Skills

vLLM-Omni Video Generation

vllm-omni-skills

Generate videos (text→video, image→video, text+image→video) using vLLM-Omni and Wan2.2-style diffusion models, with guidance on parameters and performance trade

Hugging Face Evaluation Manager

skillattack

Extract, import, and add structured model evaluation results to Hugging Face model cards; run or import benchmark evaluations and generate model-index YAML for

vLLM Qwen3 Coder Optimization

ai-infra-auto-driven-skills

Guided, PR-backed manual for auditing, debugging, and extending the Qwen3 Coder tool parser in vLLM—focuses on schema edge cases, tool-parser regressions, and v

vLLM Qwen3.6 Optimization

ai-infra-auto-driven-skills

Guidance and PR-driven validation steps for optimizing and documenting Qwen3.6 support in vLLM; use when auditing or implementing model-specific changes.

Graphsignal GPU Profiler

graphsignal-profiler

Set up and manage GPU profiling, tracing, and monitoring for AI inference workloads using vLLM, SGLang, and PyTorch.

Router Service Platform Change

semantic-router

Modifies router-side API, authz, memory, provider, and storage modules for the Semantic Router platform.

TAO Inference Microservice

tao-skill-bank

Deploy and manage network-specific TAO inference microservices across diverse compute platforms including Docker, Kubernetes, and Slurm.

Inference Runtime Manager

tools

Standardizes the creation, auditing, and promotion of local inference engine runtimes (vLLM, llama.cpp, etc.) to prevent toolchain sprawl.