n8n-skills
n8n skillset for Claude Code to build flawless n8n workflows
Runs with mockssource: GitHubhomepageShellMITcommit 19cd793f4789
Shell, MIT licensed. The project labels itself: ai agents, n8n and workflow automation.
n8n-skills runs, with stand-ins for the services it depends on. An Argusic agent installed it in 4.5 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
n8n-skills builds 16 valid distribution zips (98 files, 15 skills), n8n-mcp v2.90.0 MCP server responds to all 7 tools correctly via stdio protocol, skills install into ~/.codex/skills/, and all pre/post-tool-use hooks are executable.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 86 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- zip: command not found0.5 minutes
- npm install -g n8n-mcp: EACCES on /usr/local0.5 minutes
- mcp.json points to remote HTTPS endpoint (401 unauthorized)0.5 minutes
- Node v18.19.1 < required >=20.0.0, engine warnings
- Install time
- 5 minutes
- Cold machine to finish
- 8 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- n8n-mcp MCP server stdio protocol: initialize, tools/list (7 tools), tools/call search_nodes/webhook/validate_node/get_node/validate_workflow all returned correct results; build.sh exited 0 producing 16 valid zips
- Model tokens used
- 87,153
- Exact commit tested
- 19cd793f4789
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
87,153 Let me now compile the comprehensive summary. I've done a thorough evaluation. Here's my final report: **What I did and verified:** 1. **Installed n8n-mcp** (prerequisite) via `npm --prefix ~/.local install n8n-mcp` — all 150 packa… 2. **Ran `build.sh`** — failed on `zip: command not found`. Patched the script with a Python `zipfi… 3. **Tested n8n-mcp MCP server end-to-end** via stdio protocol: `initialize` → returned protocol `2… 4. **Fixed mcp.json**: originally pointed at `https://api.n8n-mcp.com/mcp` (returns HTTP 401). Crea… 5. **Verified all 15 skills** have proper SKILL.md frontmatter (name + description). Bundle contain… 6. **Verified 62 evaluations** across 14 skill categories (3–6 per skill). 7. **Installed skills** into `~/.codex/skills/` for Argusic Agent usage. 8. **Hooks** all present and executable (8 pre-tool-use hooks, 1 post-tool-use, session-start.sh).
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 4.5 minutes, faster than the median of the 29 comparable projects Argusic has measured.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
Of the 30 ai-agents projects Argusic has installed and timed, n8n-skills was the 13th fastest to reach a running state, and 20 of 30 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.05 | |
| Argusic Runner | 1/3 | Unverified | 80.00 | 0.05 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/n8n-skills)Questions
- Does n8n-skills run?
- n8n-skills runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 5 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test n8n-skills?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 19cd793f4789. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test n8n-skills?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does n8n-skills take to install?
- 4.5 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does n8n-skills need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing n8n-skills?
- 4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does n8n-skills compare with the alternatives?
- Of the 30 ai-agents projects Argusic has installed and timed, n8n-skills was the 13th fastest to reach a running state, and 20 of 30 reached one at all.
- Where is the evidence for n8n-skills?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.