n8n-agent-skills
AGENTS.md1 starsChanged 3 months agoMITView on GitHub
This repository teaches AI coding agents how to build production-grade n8n workflows. Author: Taghi Molavi · Repo: https://github.com/tmolavi/n8n-agent-skills All skills: ./skills/*/SKILL.md Example configs: ./configs/ Tool routing: ./skills/n8n-mcp-tooling/SKILL.md
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository17 other files it gives its agents.
- llms.txtllms.txt
- n8n-agentsSkill
- n8n-ai-seo-geo-automationSkill
- n8n-binary-dataSkill
- n8n-code-nodesSkill
- n8n-credentials-securitySkill
- n8n-data-tablesSkill
- n8n-debuggingSkill
- n8n-error-handlingSkill
- n8n-expressionsSkill
- n8n-loopsSkill
- n8n-mcp-toolingSkill
- n8n-node-configurationSkill
- n8n-production-opsSkill
- n8n-subworkflowsSkill
- n8n-workflow-lifecycleSkill
- using-n8n-skillsSkill
The file
We split this AGENTS.md into the rules it gives an agent
5 rules. About 1 is common, 4 are distinctive, and 0 are very specific to this project.
≈1
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Prefer live node schema over training memory.
- Common: line 13
Never place secrets in text fields.
- Distinctive: line 14
Ask before tests with real side effects.
- Distinctive: line 28
Prefer targeted file reads.
- Distinctive: line 29
Do not dump entire workflow JSON into chat when a lint summary suffices.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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.
Files
AGENTS.md — n8n Agent Skills (Molavi)
This repository teaches AI coding agents how to build production-grade n8n workflows.
Author: Taghi Molavi · Repo: https://github.com/tmolavi/n8n-agent-skills
Required protocol
- For any n8n task, load skill
using-n8n-skillsfirst. - Route to the matching capability skill before MCP calls or JSON/SDK edits.
- Prefer live node schema over training memory.
- Validate/lint and re-check
connectionsbefore activate/publish. - Never place secrets in text fields; use n8n credentials.
- Ask before tests with real side effects.
Skill root
All skills: ./skills/*/SKILL.md
MCP
Example configs: ./configs/
Tool routing: ./skills/n8n-mcp-tooling/SKILL.md
Token hygiene
- Load references/ only when needed.
- Prefer targeted file reads.
- Do not dump entire workflow JSON into chat when a lint summary suffices.
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
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.