agentleFS
ForgeyClapForgeyClap/claude-forge/.claude/skills/forge-n8n/SKILL.md

forge-n8n

Skill2 starsChanged 36 days agoMITView on GitHub

Forge: building and validating n8n automation workflows: n8n, workflow, webhook, trigger, cron, retry, error branch, credentials, validate_workflow.

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    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. Very specific:

    Gate: run validate_node / validate_workflow via n8n-validation-expert.

    line 21

≈ “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

Forge playbook — n8n / automation

This domain is skill + MCP driven, not agent-heavy. Do not spawn a crowd of agents. Do not duplicate ECC n8n skills — defer to them.

Hard rules

  • Validate before claiming production-ready: webhook method, input schema, credentials, auth/security, error branch present, retry behavior, test/prod separation.
  • Credentials live in n8n credential store / env — never hardcoded in nodes.
  • Imported/new workflows stay inactive until the owner approves activation.
  • Expressions are null-safe: use optional chaining, ?? for defaults (not ||, which also replaces 0 and empty text), and Array.isArray() before looping.
  • Webhook-triggered workflows answer early with a Respond to Webhook node and do slow work afterwards, so the caller never times out.

Workflow

  1. Consult n8n-mcp-tools-expert first (correct nodeType formats + tool selection).
  2. Architecture from n8n-workflow-patterns; node setup from n8n-node-configuration; expressions from n8n-expression-syntax.
  3. Code nodes → n8n-code-javascript (default) or n8n-code-python.
  4. Gate: run validate_node / validate_workflow via n8n-validation-expert; resolve real errors (it knows the false positives).
  5. For custom code/scripts you may run codex-reviewer (Codex, optional) — advisory, not a blocker.

Fan-out & flow

L2 fix/extend; L3 new multi-branch workflow. Mostly serial (a workflow is one artifact); parallelize only independent sub-workflows.

Ship-readiness (unique)

validate_workflow clean; webhook auth enabled; secrets in credentials (not hardcoded); error + retry paths exist; test vs prod URLs separated; a manual test execution shown. Then run the ship-readiness n8n checklist. Never claim production-ready without passing validation; no live activation without owner approval.

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.