File contents KServe — Skill Router
Pick the right sub-skill.
Which Sub-Skill?
User wants to...
Load skill
Manage CRDs (InferenceService, ServingRuntime, InferenceGraph, LLMInferenceService, LocalModelNode), configure predictors, storage, transformers, explainers
kserve-operator
Deploy, configure, upgrade KServe via Helm (10 charts, deployment modes)
kserve-helm
Quick Map
Task
Skill
"Deploy a sklearn InferenceService with S3 model"
kserve-operator
"Configure a multi-node LLM serving with vLLM"
kserve-operator
"Create a ServingRuntime for custom Triton setup"
kserve-operator
"Set up an InferenceGraph ensemble pipeline"
kserve-operator
"Configure S3/GCS/HF storage credentials"
kserve-operator
"Enable LocalModelCache for NVMe model caching"
kserve-operator
"Deploy KServe on Kubernetes with Helm"
kserve-helm
"Configure Standard vs Knative deployment mode"
kserve-helm
"Install KServe CRDs only"
kserve-helm
"Set up LLMInferenceService with disaggregated prefill/decode"
kserve-operator
"Add a transformer for pre/post-processing"
kserve-operator
"Create a canary rollout for model update"
kserve-operator
"Configure Gateway API ingress"
kserve-helm
1 --- 2 name: kserve 3 description: KServe — Skill Router 4 --- 5 6 # KServe — Skill Router 7 8 Pick the right sub-skill. 9 10 ## Which Sub-Skill? 11 12 | User wants to... | Load skill | 13 |---|---| 14 | Manage CRDs (InferenceService, ServingRuntime, InferenceGraph, LLMInferenceService, LocalModelNode), configure predictors, storage, transformers, explainers | `kserve-operator` | 15 | Deploy, configure, upgrade KServe via Helm (10 charts, deployment modes) | `kserve-helm` | 16 17 ## Quick Map 18 19 | Task | Skill | 20 |---|---| 21 | "Deploy a sklearn InferenceService with S3 model" | `kserve-operator` | 22 | "Configure a multi-node LLM serving with vLLM" | `kserve-operator` | 23 | "Create a ServingRuntime for custom Triton setup" | `kserve-operator` | 24 | "Set up an InferenceGraph ensemble pipeline" | `kserve-operator` | 25 | "Configure S3/GCS/HF storage credentials" | `kserve-operator` | 26 | "Enable LocalModelCache for NVMe model caching" | `kserve-operator` | 27 | "Deploy KServe on Kubernetes with Helm" | `kserve-helm` | 28 | "Configure Standard vs Knative deployment mode" | `kserve-helm` | 29 | "Install KServe CRDs only" | `kserve-helm` | 30 | "Set up LLMInferenceService with disaggregated prefill/decode" | `kserve-operator` | 31 | "Add a transformer for pre/post-processing" | `kserve-operator` | 32 | "Create a canary rollout for model update" | `kserve-operator` | 33 | "Configure Gateway API ingress" | `kserve-helm` |
Aidas-dev/k8s-agent-skills/tree/main/skills/kserve commit 80ee41e57d
Frequently asked questions How do I install the Kserve skill? Run npx skillmds@latest add aidas-dev/kserve in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
What does the Kserve skill do? KServe — Skill Router It is listed under Coding & Dev Tools on SkillMD.
Is Kserve safe to use? This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
Which AI agents work with Kserve? This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Is Kserve free to use? Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Who published Kserve? Aidas-dev (@aidas-dev) published this skill. Their other Agent Skills are listed on their SkillMD profile.