agentic-plugins

Design and validate Kubernetes NetworkPolicies following Zero Trust principles (NIST SP 800-207). Two-tier analysis — architecture review then live cluster verification — produces a verified implementation plan with apply-and-verify results. Use when: - "Create NetworkPolicies for my namespace" - "Audit network isolation for this workload" - "Design network segmentation for a new application" - "Verify NetworkPolicies implement Zero Trust" - User mentions "network policy", "microsegmentation", "default-deny" NOT for Admin Network Policy (ANP) cluster-wide rules — those are cluster-admin infrastructure guardrails, not application-level microsegmentation. NOT for CNI plugin configuration or Multus secondary networks.

Configure NVIDIA NIM platform on OpenShift AI for optimized model inference. Use when: - "Set up NIM on my cluster" - "Configure NGC credentials for NIM" - "I want to deploy a NIM model but haven't set up the platform" - "Create the NIM Account CR" One-time prerequisite before deploying models with NVIDIA NIM runtime via /model-deploy. NOT for deploying models (use /model-deploy instead). NOT for vLLM or Caikit deployments (NIM-specific only).

Create, run, schedule, and monitor Data Science Pipelines (Kubeflow Pipelines 2.0) on OpenShift AI. Use when: - "Run a pipeline in my project" - "Schedule a recurring pipeline" - "Check my pipeline run status" - "List pipeline runs and their logs" - "Set up the pipeline server" - "Delete a pipeline or pipeline run" Handles pipeline server setup, pipeline run submission from YAML, scheduling recurring runs, monitoring execution, and viewing step logs. NOT for creating data science projects (use /ds-project-setup). NOT for deploying models (use /model-deploy). NOT for model training jobs (use training skills).

**CRITICAL**: Use this skill for ALL CVE remediation workflows. DO NOT use individual skills piecemeal for end-to-end remediation. Use when users request: - CVE remediation playbooks or security patch deployment - Multi-step remediation (validation → context → playbook → execution) - Batch remediation across multiple systems or CVEs - End-to-end CVE management (analysis + remediation + verification) - Prioritizing and remediating CVEs (not just listing them) - Emergency security response with immediate remediation plans DO NOT use for simple queries: - "List critical CVEs" → Use `/cve-impact` skill - "What's the CVSS score for CVE-X?" → Use `/cve-impact` or `/cve-validation` - Standalone impact analysis without remediation → Use `/cve-impact` This skill orchestrates 6 specialized skills (cve-impact, cve-validation, system-context, playbook-generator, playbook-executor, remediation-verifier) for complete remediation workflows.

Configure custom ServingRuntime CRs on OpenShift AI for model serving frameworks not covered by built-in runtimes. Use when: - "Create a custom serving runtime" - "I need a runtime for ONNX / Triton / custom framework" - "Customize vLLM runtime parameters" - "What serving runtimes are available?" - "Add a custom container image for model serving" Handles listing existing runtimes, creating new ServingRuntime CRs, and validating compatibility with target models. NOT for deploying models (use /model-deploy after runtime is configured). NOT for NIM platform setup (use /nim-setup).

Validate skills against agentskills.io specification. Use when adding new skills to the marketplace, reviewing skill PRs, checking skill compliance, or running quality gates on skills. Validates frontmatter fields (name, description, compatibility, metadata, allowed-tools), directory naming, line limits, and structure.

Create and manage Jupyter notebook workbenches on OpenShift AI with image selection, resource configuration, PVC storage, and lifecycle management. Use when: - "Create a notebook workbench" - "Spin up a Jupyter environment for data science" - "Start / stop my workbench" - "What notebook images are available?" - "Delete a workbench I no longer need" Handles Notebook CR lifecycle: create with configurable images and resources, start/stop, attach storage, and delete with data loss warnings. NOT for deploying models (use /model-deploy). NOT for creating projects (use /ds-project-setup). NOT for managing pipelines (use /pipeline-manage).