Learning paths

Learn the stack by category.

The learning area now mirrors the marketplace: workflows, skills, MCPs, agents, and operations each get their own path before individual tutorials branch underneath.

Workflows

Learn when to import n8n templates, when to run dynamic agent workflows, and how to review automation graphs before activation.

Skills, MCPs, and agents

Understand reusable skills, connector boundaries, runtime compatibility, install trust, and agent pack evaluation.

Marketplace operations

Prepare for paid artifacts, source verification, creator attribution, hosted installs, and lifecycle signals.

Workflow guides

From first import to production judgment

Start with dynamic workflow fundamentals, then apply the same review discipline to n8n imports and other workflow runtimes.

Start from a scoped task

A good workflow has a clear boundary, a result shape, and a verification bar before agents fan out.

Split independent work

Parallelism helps when branches can investigate separate files, sources, roles, or hypotheses.

Respect cost and approval

Workflow templates and agent runs need source review, credential checks, and clear activation decisions.

Start01

Current Claude Code usage model

Use workflows inside an interactive Claude Code session. Run bundled workflows such as `/deep-research`, inspect runs with `/workflows`, and save successful scripts as slash commands.

Start Claude Code in the project where the work should happen.
Ask Claude to run a workflow for a scoped task, or run `/deep-research <question>` for the bundled research workflow.
Open `/workflows` to inspect phases, agent counts, token totals, and completed results.
Save a useful run from `/workflows`; later invoke the saved workflow as `/<name>`.

Build02

How the orchestration model works

A workflow is not just a longer prompt. The important shift is that branching, loops, intermediate results, and verification policy move into a JavaScript orchestration script.

Use the script to hold state that would otherwise flood the main conversation.
Use subagents for isolated perspectives, file groups, source groups, or reviewer roles.
Use parallel phases only where tasks are independent.
End with a convergence phase that filters findings and explains confidence.

Operate03

Cost and scope checklist

Dynamic workflows are expensive enough that the site should teach restraint: small edits, single-file changes, and unclear success criteria are usually poor fits.

Prefer workflows for migrations, audits, research, and review tasks with many independent branches.
Start with a narrow folder, package, or file sample before scaling up.
Check the raw script or planned phases before approving a large run.
Give agents a test, lint, benchmark, or source-validation bar whenever possible.

Skills, MCPs, agents

Evaluate reusable capabilities

Future tutorials will separate install commands, runtime compatibility, credential boundaries, connector permissions, and agent pack trust signals.

Marketplace operating notes

Source material, creator policy, paid distribution, and translated notes should stay close to the artifacts they explain, while articles remain the deeper reference shelf.