agentic-plugins

Interactive skill creation and import with automated validation and marketplace compliance. Use when: - "Create a new skill" - "Import an existing skill" - "Create a new agentic pack" - "Add skill to <pack>" - "Build skill for <rh-product>" - User mentions "skill builder", "contribute", "new skill", "import skill", or "new pack" Two modes: create from scratch or import existing SKILL.md. Guides through discovery, definition, generation, and validation. Enforces SKILL_DESIGN_PRINCIPLES.md and agentskills.io spec.

Analyze AI model performance, GPU utilization, and cluster health on OpenShift AI. Use when: - "How is my model performing?" - "What GPUs are available in the cluster?" - "Show me inference latency for Llama" - "Check OpenShift cluster health metrics" - "Trace a slow inference request" - "Correlate errors across my inference stack" Query-driven, read-only analysis. Routes to the appropriate observability domain based on user intent. NOT for deploying models (use /model-deploy). NOT for debugging failed deployments (use /debug-inference).

End-to-end OpenShift cluster creation using Red Hat Assisted Installer. Handles Single-Node OpenShift (SNO) and HA multi-node clusters on baremetal, vsphere, oci, nutanix. Use when: - "Create a new OpenShift cluster" - "Install OpenShift on my servers" - "Set up a single-node cluster for edge deployment" - "Deploy a production HA cluster" Complete workflow: cluster definition, ISO generation, host discovery/validation, role assignment, network configuration (VIPs, static networking), installation monitoring, credential retrieval. NOT for: - Listing existing clusters → Use `/cluster-inventory` skill - Modifying running clusters → Out of scope (Day-2 operations require direct cluster access) - Cluster upgrades (not yet supported)

List and inspect OpenShift clusters across self-managed (OCP, SNO) and managed service (ROSA, ARO, OSD) deployments. Returns cluster name, ID, version, status, platform, and creation date. Use when: - "List all clusters" - "Show cluster status" - "What clusters are available?" - "Get details of cluster [name]" - "Show cluster events for diagnostics" Read-only operations. Does NOT modify clusters.

Generate a consolidated health report across multiple OpenShift clusters. Verifies each kubeconfig context is a genuine OpenShift cluster before reporting. Non-OpenShift contexts are skipped by default. Collects node resources (CPU, memory, GPUs), namespace counts, and pod status into a single comparison view. Use when: - "Show me a report across all clusters" - "Compare cluster health" - "Multi-cluster status overview" - "How are my clusters doing?" - "Include all clusters including non-OpenShift" (override default filter) NOT for single-cluster deep-dives or troubleshooting specific pods.

Diagnose and fix `.catalog/` validation failures (schema, roster, banners, sample workflows, JSON mirror). Use when: - `make validate` or CI reports collection compliance errors - A PR adds skills but catalog was not updated - `collection.json` is out of sync with `collection.yaml` - Catalog metadata/fragments might have drifted from README/CLAUDE/SKILL golden sources Remediation is via the create-collection workflow and `catalog_yaml_to_json.py`—not by weakening checks.

Author and maintain Compass catalog-info.yaml manifests for agentic packs (skills, plugins, Locations, MCP inverse relations). Use when: - Adding or updating a skill and its Compass manifest - Registering an existing pack in Compass (manifests only; not creating a new agentic pack) - MCP usage or orchestration changed in SKILL.md - Auditing bidirectional dependsOn/dependencyOf drift against repo Compass conventions File-based only: Read/Glob/Grep/Bash. For `.catalog/` marketplace metadata use create-collection. NOT for: `.catalog/` metadata (use create-collection) or automated Compass registration.

Run skill design compliance validation for agentic collections. Use when the user asks to: - "Check skill compliance" / "Validate skill design" / "Run compliance check" - "Verify my skills follow design principles" - Before committing skill changes Runs the validate_skills_tier2.py script against SKILL_DESIGN_PRINCIPLES.md.

Validate a CVE against a Red Hat container image using official SBOM attestations, Red Hat VEX data, and CVE metadata from MITRE/OSV.dev.

Validate a CVE against Red Hat Enterprise Linux CoreOS (RHCOS) in a specific OCP release by extracting RPM packages and checking Red Hat VEX data.

Author or refresh `<pack>/.catalog/collection.yaml` and related `.catalog/` artifacts from golden sources (SKILL.md, README, AGENTS.md, Lola marketplace). Use when: - Adding a new pack or refreshing the collection catalog for GitHub Pages / tooling - Aligning catalog narrative, sample workflows, and decision guide with skills on disk - Preparing a PR after changing skills or marketplace metadata Outputs only under `<pack>/.catalog/` (never overwrite README, SKILL, CLAUDE, or marketplace YAML).

**CRITICAL**: Use for ALL CVE discovery and listing. DO NOT call get_cves directly. Use when: "show critical CVEs", "CVEs on hostname X", "remediatable vulnerabilities", "impact of CVE-X", risk assessment. NOT for remediation (use `/remediation`). System-level: FIRST reply = pagination prompt (Step -1). Parsing: scripts/01-cve-response-parser.py.

Query MITRE, OSV.dev, and Go vulnerability database to produce a structured report of affected packages, ecosystems, and vulnerable version ranges for a CVE.

Troubleshoot failed or slow InferenceService deployments on OpenShift AI. Use when: - "My InferenceService won't start" - "Model deployment is stuck" - "Inference endpoint returns errors" - "Model is slow / high latency" - "GPU scheduling failed for my model" Progressive diagnosis: status conditions, events, pod logs, GPU health, and observability analysis. NOT for deploying models (use /model-deploy). NOT for creating runtimes (use /serving-runtime-config).

Create and configure Data Science Projects on OpenShift AI with namespace setup, S3 data connections, pipeline server, and model serving enablement. Use when: - "Create a data science project" - "Set up a new namespace for ML work" - "Add an S3 data connection to my project" - "Configure the pipeline server" - "Enable model serving on my project" Bootstraps an RHOAI Data Science Project with proper labels, data connections, pipeline infrastructure, and model serving configuration. NOT for deploying models (use /model-deploy). NOT for creating workbenches (use /workbench-manage). NOT for managing pipelines after setup (use /pipeline-manage).

Configure TrustyAI Guardrails Orchestrator for LLM input/output content safety on OpenShift AI. Use when: - "Add guardrails to my LLM endpoint" - "Set up content safety for my model" - "Configure PII detection on my inference endpoint" - "Block prompt injection attacks" - "I need a guarded endpoint for my deployed model" Handles GuardrailsOrchestrator CR deployment, detector configuration (content safety, PII, prompt injection, toxicity), orchestration policies, and guarded endpoint validation. NOT for deploying models (use /model-deploy first). NOT for bias/drift monitoring (use /model-monitor). NOT for infrastructure observability (use /ai-observability).

Fetch container image labels, validate registry ownership, resolve tag/digest via SBOM, and report the SBOM artifact reference for a Red Hat container image.

Deploy AI/ML models on OpenShift AI using KServe with vLLM, NVIDIA NIM, or Caikit+TGIS runtimes. Use when: - "Deploy Llama 3 on my cluster" - "Set up a vLLM inference endpoint" - "Deploy a model with NIM" - "Create an InferenceService for Granite" - "I need to serve a model on OpenShift AI" Handles runtime selection, GPU validation, InferenceService CR creation, and rollout monitoring. NOT for NIM platform setup (use /nim-setup first). NOT for custom runtime creation (use /serving-runtime-config).

Configure TrustyAI model monitoring for bias detection and data drift on deployed InferenceServices. Use when: - "Monitor my model for bias" - "Set up drift detection on my inference endpoint" - "Configure TrustyAI for my deployed model" - "Check if my model has fairness issues" - "I need SPD / DIR metrics for my model" Handles TrustyAIService deployment, bias metric configuration (SPD, DIR), drift metric configuration (MeanShift, FourierMMD, KS-Test, Jensen-Shannon), threshold tuning, and monitoring validation. NOT for deploying models (use /model-deploy first). NOT for input/output content safety guardrails (use /guardrails-config). NOT for infrastructure-level observability (use /ai-observability).

Register, version, and manage ML models in the OpenShift AI Model Registry. Browse the Model Catalog, track model metadata, and promote models across environments. Use when: - "Register a new model in the registry" - "List registered models" - "What versions exist for my model?" - "Promote a model from dev to production" - "Show model artifacts and storage URIs" Handles model registration, versioning, metadata management, artifact tracking, and cross-environment promotion. NOT for deploying models (use /model-deploy). NOT for model performance monitoring (use /ai-observability).