Select and apply the right agentic design pattern when building an AI agent, workflow, or multi-step LLM system. Use this skill whenever the user is designing, architecting, debugging, or reviewing an agent/LLM pipeline and needs to decide HOW to structure it -- e.g. they mention agents, orchestration, multi-step workflows, RAG, routing, tool use, retries, evaluation, guardrails, memory, planning, or ask "how should I build/structure this agent?" or "which pattern fits this problem?". Maps problem symptoms to one of 20 patterns and specifies, for each, which steps are LLM calls vs deterministic code and what context each call carries. Use it even when the user does not say the word "pattern".
Build MCP servers, author routes/pipelines/functions, and manage all Cribl Stream artifacts (Stream, Edge, Search, Lake) via REST API and YAML configs. Use when user mentions Cribl, Cribl Stream/Edge/Search/Lake, routes, pipelines, sources, destinations, packs, or observability pipeline management.
Spec-driven development loop (plan → go → review → project) with lifecycle states, YAML frontmatter, a code-grounded feature projection (FEATURES.md), and docs refresh. ALWAYS LOAD THIS SKILL when working on any project that has a `.kiro/specs/` or `specs/` directory, or any CLAUDE.md/AGENTS.md that mentions specs. Use for planning, implementing, refining, or auditing specs, regenerating the feature ledger, or syncing README/docs/CHANGELOG with specs and code. Trigger on: any implementation work in a spec-managed project, specs, requirements/design/tasks, spec-plan, spec-go, spec-project, spec-docs, spec-audit, feature ledger, `.kiro`, `specs/`, 'keep working', 'continue', or resuming prior work. Never hand-edit FEATURES.md — it is derived.
Umbrella skill for agent work discipline across development, analysis, and documentation: inspect the repo before restructuring, keep durable truth in repo artifacts instead of chat memory, co-evolve specs/design/steering/user docs with code, apply sound coding patterns, verify work honestly, avoid shortcuts, work efficiently with subagents without hallucinating, and keep moving through the next concrete work item when the human is away. References cover coding patterns, AI-authored code review, and artifact co-evolution. Trigger when the user asks for workflow discipline, coding patterns, doc/artifact maintenance, code review of AI-authored code, project hygiene, execution guardrails, repo normalization, or when a task risks drifting across architecture, storage, specs, continuity, or tooling boundaries.
Plan and configure ralph-orchestrator deployments for projects at any stage — from a vague phase plan to a mature codebase. Use this skill whenever the user wants to set up ralph for a new project, choose between deployment topologies (direct, Claude+MCP, multi-project supervisor), pick the right config for their project's maturity, run oneshot autonomous builds, or manage multiple concurrent ralph loops across tmux sessions. Also use when the user asks "how should I run ralph on this?", mentions phase plans, or wants to configure cost budgets, hat workflows, or guardrails for a specific project type.
Deep skill for Splunk development, administration, SDK/REST integrations, dashboards, UCC add-ons, ITSI automation, SPL2 authoring, and AI-facing tooling. Use for Splunk SDK, REST, jobs/export, SPL, dashboards, packaging, and MCP-backed analysis workflows.
Instrument agentic LLM apps built on the Claude Agent SDK (claude-agent-sdk) and/or LangGraph with Arize Phoenix and OpenInference — tracing, evaluation, annotations, experiments, cost tracking, and self-hosting. Use when the user mentions Phoenix, arize-phoenix, openinference, LLM observability, LLM-as-judge evals, tracing Claude Agent SDK `query()` / `ClaudeSDKClient` calls, tool-use observability, tracing LangGraph nodes/edges, or debugging latency/cost/quality of an agent.
Structured browser extraction for AI coders — explore first, then draft repeatable Robot Framework BDD suites with shipped generic keywords, templates, and validation harness.