Use this skill to learn hot to use the IBM Cloud CLI (`ibmcloud`) commands, flags, command patterns, or troubleshooting guidance. Covers core CLI workflows: install/verify/update, login with SSO or API keys, select account/region/resource group targets, inspect and configure CLI output, manage plug-ins (e.g. `vpc-infrastructure` / `ibmcloud is ...` for VPC infrastructure.).
Build voice-enabled agents in watsonx Orchestrate using the ADK. This guide covers initial setup, key concepts for building your first voice agent.
Reusable skills for the Turbonomic Resource Dashboard project. Each skill is a specialized workflow that Bob can activate to help with specific development tasks.
Deploy and manage HashiCorp Vault using Ansible automation with proper configuration, permissions, and security setup.
Plan and run evaluations, red-teaming, and runtime observability for watsonx Orchestrate (WXO) agents across Developer Edition and SaaS. Use when validating WXO agents pre-deploy, authoring benchmark JSON DAGs, interpreting Journey Success / Tool Call Recall / Agent Routing F1 / RAG Faithfulness, diagnosing agent failures, running adversarial red-teaming (Instruction Override, Jailbreaking, Crescendo Attack), searching runtime traces, exporting traces via the Python SDK, wiring Langfuse for cost & latency analysis, or registering model pricing in Langfuse. Interview-first; emits bash commands for the user to run in their IDE terminal.
Evaluate GenAI applications — RAG pipelines, LLM/chatbot outputs, and AI agents with tool-calling — before deployment using IBM watsonx.governance metrics. Use when scoring RAG faithfulness / answer relevance / context relevance / retrieval precision, screening LLM outputs for HAP / PII / social bias / jailbreak / prompt safety risk, evaluating agentic tool-call accuracy / parameter accuracy / relevance / syntactic validity, authoring custom LLM-as-judge metrics (criteria_judge or prompt_template styles) for domain-specific concerns, preparing eval datasets in the watsonx-gov SDK format, interpreting results against pass/fail thresholds, or producing prioritized [CRITICAL]/[WARNING]/[INFO] recommendations. Partners install `ibm-watsonx-gov[metrics,agentic,tools,llmaj]` directly and call the SDK in-process; no MCP server, no hosted dependency.
Add IBM watsonx.governance-backed runtime safety and quality guardrails to AI/RAG agents. Use when shipping LLM apps to production, designing 4-choke-point Pass/Flag/Block pipelines (input → retrieval → generation → output), picking metric sets from the 28-metric catalog, wiring guardrails into FastAPI / Flask / LangChain / watsonx Orchestrate, authoring custom LLM-as-judge metrics, building compliance audit logs, integrating chat widgets with backend proxies, or tuning per-tenant threshold policies. Covers Python library, REST sidecar, and MCP tool deployment modes.
Expert skill for fetching, analyzing, optimizing, and securing IBM Maximo automation scripts with comprehensive best practices. Fetches scripts from Maximo environments via REST API and provides detailed optimization reports.