Risemi

Best n8n skills and prompts (2026)

Two ways to get an n8n workflow from AI: let a coding agent build it, or have a chat model write it from a short spec.

1 skill · 1 prompt and packs · 1 free · written and tested in-house · Filter in the catalog

n8n workflows are JSON under the hood, which means an AI can write them and also means it can get node settings and expressions subtly wrong. The products here are written to catch those mistakes before you import anything.

n8n Builder Skills for Coding Agents is for Claude Code, Cursor, Codex and similar agents: the agent builds, configures and validates workflows while avoiding the usual expression and node-config errors. The free n8n Workflow From a Plain-English Spec is a prompt for ChatGPT or Claude: five spec lines in, a node list, importable JSON, an error path and a test plan out.

Start with the prompt if you build a workflow now and then. Move to the skills if automation is a regular part of your work or you build for clients. More automation products are on the ops hub.

n8n skills

Assumption: no n8n-MCP server is connected in this session, so I took the skill's fallback path: I wrote the workflow JSON directly from the bundled rules and checked it by review (a rule-check script plus a dry run of every expression). The real validator (`validate_workflow`) was not run, and nothing was deployed.

How the skill routed this

| Step | Sub-skill used | What it decided |
|---|---|---|
| Shape | `n8n-workflow-patterns` | Webhook processing pattern: Webhook, then Validate, then Action, then Respond |
| Node parameters | `n8n-node-configuration` | Slack post needs a channel and text. `responseMode: "responseNode"`. `options.responseCode` set on every Respond node. UUID node ids, no placeholder credentials |
| Expressions | `n8n-expression-syntax` | Webhook data lives under `.body`. Use `$('Webhook').item.json.body.*` once past the IF node. `=` prefix on every expression field |
| Error paths | `n8n-error-handling` | Slack gets `onError: "continueErrorOutput"` and its `main[1]` is wired to the 500 responder. `retryOnFail` is on. Bad input is caught upstream and gets a 400 |
| Validation | `n8n-validation-expert` | Runtime-profile checks done by review. Security warnings get fixed (header auth on the webhook) |

```
Webhook ──> Validate Input ──true──> Post to #signups ──success (main[0])──> Respond 200 OK
                        └──false──> Respond 400 Invalid Input
                                     Post to #signups ──error (main[1])────> Respond 500 Slack Failed
```

Validation result (excerpt)

```
PASS  Webhook responseMode is responseNode (Respond nodes control the reply)
PASS  Every branch (success and each error) ends at a Respond to Webhook node: no hanging branch
PASS  'Post to #signups': onError=continueErrorOutput AND main[1] wired
PASS  'Post to #signups': retryOnFail with maxTries <= 5 and waitBetweenTries <= 5000
PASS  Every {{ }} field starts with = (no 'Expression requires = prefix' error)
PASS  Webhook fields read from .body, never $json.name / $json.email / $json.plan
…
43 passed, 0 failed
```

Expression dry run against sample webhook items:

```
valid           IF -> true  (Slack)  Slack text: New signup: Ana Lima (ana@example.com) on pro
missing_plan    IF -> false (400)
bad_email       IF -> false (400)
no_body         IF -> false (400)
500 body:   {"error":"upstream_error","message":"The signup was received but could not be posted to Slack. Please retry later."}
```

Not verified without the server: the node typeVersions (Webhook 2.2, IF 2.3, Slack 2.3, Respond 1.5) and the Slack v2 parameter names; confirm by opening the nodes after import.

[The full answer also holds the six-node list, the importable workflow JSON and the expressions table with the reason behind each one.]
SkillCodePro
  • Antigravity
  • Claude Code
  • Codex
  • +4
Coding

n8n Builder Skills for Coding Agents

Use it to have your coding agent build, configure and validate n8n workflows without the usual expression and node-config mistakes.

0 installs
$12.99

n8n prompts and packs

n8n: common questions

Can AI build n8n workflows?

Yes. A chat model can write workflow JSON you import into n8n, and a coding agent with the right skill can build and validate it directly. Both work better from a short, specific spec.

Do I need a coding agent for n8n?

No. The n8n Workflow From a Plain-English Spec prompt runs in ChatGPT or Claude and returns JSON you import. The builder skills are for people who already use a coding agent.

Is there a free n8n prompt?

Yes, n8n Workflow From a Plain-English Spec is free with a Risemi account.

Guides

By agent or tool

By task

By role

By output