executing-plans
executing-plans
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available
model-kernel-extensionExtend SGLang model support, model configs, custom serving paths, CUDA/JIT kernels, quantization-related kernels, and cookbook model workflows.
Independent GitHub snapshot · Automated classification · Original documentation governs
Use this sub-skill for adding or reviewing model support under python/sglang/srt/configs, serving model executors, kernel changes, JIT kernels, SGL kernels, custom CUDA paths, and repo-local cookbook skills such as add-model/add-kernel guidance. Require targeted tests and benchmark or correctness evidence for kernel changes.
../../SKILL.md../../references/workflow-map.md../../references/troubleshooting.md