agentleFS
neurawork-gitneurawork-git/n8n-autopilot/skills/n8nac-reference/SKILL.md

n8nac-reference

Skill18 starsChanged 43 days agoMITView on GitHub

Authoritative reference for every `n8nac` CLI command, subcommand, and flag (n8nac 2.7.0). Use this BEFORE running `--help` interactively, BEFORE guessing flags, and BEFORE inventing a subcommand. If a command does not appear in this file, it does not exist — research stops, do not invent CLI surface. Covers workspace, env, setup, credentials, credential, workflow, execution, skills, list/find/pull/push/promote/verify/test/test-plan/fetch/resolve/convert/native-mcp, plus subcommand-level help.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Look up exact flag names and short/long forms.

    line 12
  2. Very specific:

    Search the reference file with grep:

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

n8nac CLI — Authoritative Reference

The full n8nac --help tree is captured in reference.md (auto-generated, 68 command/subcommand blocks across 24 top-level groups). Read it whenever you need to:

  • Know if a command exists (rule: not in the file → does not exist, do not invent it).
  • Look up exact flag names and short/long forms.
  • Understand the argument order for a subcommand.

Quick navigation

Search the reference file with grep:

# Find a parent command
grep "^## \`n8nac credential" "$CLAUDE_PLUGIN_ROOT/skills/n8nac-reference/reference.md"

# Find a specific subcommand
grep -n "^### \`n8nac credential list\`" "$CLAUDE_PLUGIN_ROOT/skills/n8nac-reference/reference.md"

# Pull the full help block for one subcommand (next 30 lines after the header)
awk '/^### `n8nac workflow credential-required`/{flag=1;n=0} flag{print;n++; if(n>30)exit}' \
  "$CLAUDE_PLUGIN_ROOT/skills/n8nac-reference/reference.md"

Subcommand index (alphabetical by parent)

ParentSubcommands
(root)find, pull, push, promote, verify, test, test-plan, fetch, resolve, convert, convert-batch, list, mcp, setup, setup-modes, update-ai
credentialcreate, delete, get, list, schema
credentials (readiness/recipes)delete, ensure, inventory, recipes, starter-kit, starter-kits, test
envadd, auth, list, pin, remove, status, update
executionget, list
skillsdocs, examples, guides, list, mcp, node-info, node-schema, related, search, update-ai, validate
workflowactivate, credential-required, deactivate, present
workspacestatus (alias get) — read-only since 2.3; all mutation moved to env
telemetry(no subcommands — flags only)

credentials (plural) and credential (singular) are different parent groups. Plural is for recipe / readiness / inventory management; singular is for direct create/list/get/delete/schema operations on the active instance. Mixing them is a common source of "command not found" errors.

When to read the full file vs. a single block

  • Single subcommand lookup (90% of cases): use grep / awk snippet above to pull just the block you need. ~30 lines.
  • Full file read (rare): only when you need an overview of a parent group's surface (e.g. "what does the env group do as a whole?").

How to regenerate

bash "$CLAUDE_PLUGIN_ROOT/scripts/dump-n8nac-help.sh" > "$CLAUDE_PLUGIN_ROOT/skills/n8nac-reference/reference.md"

Re-run whenever the setup-check.sh REFERENCE_N8NAC_VERSION constant is bumped. The script captures the version from npx n8nac --version and stamps it at the top + bottom of the file.

Companion: high-level patterns

For the curated "which command for which user intent" mapping (cheat-sheet form), see n8nac-cheatsheet and the Cheat-Sheet section in CLAUDE.md. This skill is the raw-help fallback when the cheatsheet does not have a row for the user's request.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.