Full 3-phase pipeline (Research → Write+Validate → Deploy+Test) for shipping an n8n workflow end-to-end. Wraps Etienne's `n8n-as-code:n8n-architect` skill for schema research + authoring, adds repo-scoped orchestration — community-template lookup, validate-push-test loop, mcpTrigger publish gate, execution inspection, Completion Report.

Fan-out / fan-in, parallel sub-workflow execution, and batch-orchestrator patterns in n8n. Use when a workflow processes a LIST in parallel, calls sub-workflows, needs faster wall-clock on many items, has a webhook that would otherwise block for minutes, or asks "how do I run sub-workflows in parallel / fan out / fan in".

Extract or classify structured data from text/documents with an LLM in n8n using a real JSON schema. Use when a workflow needs structured fields out of unstructured input (invoice/contract/email extraction, classification), when deciding between an AI Agent and a dedicated extractor node, or when LLM JSON output is unreliable / fails schema validation.

The full `n8nac --help` tree is captured in [`reference.md`](reference.md) (auto-generated, 61 command/subcommand blocks across 24 top-level groups). Read it whenever you need to:

Curated "user intent → exact command" mapping for the n8nac CLI. Use this BEFORE reading `n8nac-reference` or running `--help`. Covers the 60+ common workflows — lookup, deploy, test, debug, migrate, credentials, projects, environments. If your task matches a row here, run the linked command verbatim — no flag fishing.

Pull/update n8n node schemas for offline validation. Discovers node types from local workflows, fetches each via `npx n8nac skills node-info`, falls back to direct npm-package extraction for nodes n8nac does not index, then rebuilds `schemas/_index.json`. Run when schemas are stale, when validation reports "unknown node type", or when SessionStart hooks signal coverage gaps.

Explain and verify how a Claude session pins itself (and all its n8nac workflow/instance commands) to exactly ONE n8n environment without clobbering other sessions' global active env. Use when the user asks "which env am I on", "how does session env pinning work", "pin this session to env X", "why was my env command blocked", or wants to verify env isolation. Reports the session-resolved env vs the shared global active, and can run the empirical isolation test.