jpeetz/agent-skills

n8n-api-shape

Use this skill when working with the n8n REST API — read, update, or verify workflows on ANY n8n instance.

View source

How to use

  1. Copy the installation command and review the source package before installing it in your own agent environment.
  2. Check the source document for required tools, credentials and supported hosts.
  3. Describe your input and desired deliverable; review the output against the source material.
npx skills add https://github.com/jpeetz/agent-skills --skill n8n-api-shape

Before you start

  • Installation does not include a model subscription, API allowance or permission to access your files.
  • Repository stars and installation counts describe activity, not an independent quality or security test.
Original skill document

Rendered from the source repository. Headings, examples, code, tables, links, and referenced images are preserved.

n8n REST API — Shape Reference (instance-agnostic)

A reusable, instance-agnostic reference for the n8n REST API. Usable on any n8n instance (a client's fresh one, or your own) without hardcoding host, instance, or workflow IDs.

When to Use This Skill

Use this skill when:

  • You need to read, update, or verify an n8n workflow via the REST API.
  • Prior skills point at a SPECIFIC n8n instance (a host/workflow ID) that does

not apply to the instance you're touching now.

  • You hit 400 additional properties on workflow PUT.

Auth

  • Header: X-N8N-API-KEY: <key> (generate at Settings → API; store in the vault by label).
  • Base: https://<n8n-host>/api/v1/.

Read a workflow (GET)

GET /api/v1/workflows/{id} → returns the workflow JSON.

Update a workflow (PUT) — the exact recipe that works

n8n rejects extra fields on PUT with 400 additional properties. Strip to a minimal 4-key payload:

python
import json, requests
wf = requests.get(f"{base}/workflows/{wf_id}",
    headers={"X-N8N-API-KEY": key}, timeout=20).json()
for node in wf["nodes"]:
    for k in ["id", "position", "credentials", "webhookId"]:
        node.pop(k, None)
payload = {
    "name": wf["name"],
    "nodes": wf["nodes"],
    "connections": wf["connections"],
    "settings": {"executionOrder": wf["settings"].get("executionOrder", "v1")},
}
r = requests.put(f"{base}/workflows/{wf_id}",
    headers={"X-N8N-API-KEY": key, "Content-Type": "application/json"},
    json=payload, timeout=20)
assert r.status_code == 200, r.text

Banned top-level fields on PUT: id, active, tags, versionId, pinData, staticData, createdAt, updatedAt, meta, activeVersionId, versionCounter, triggerCount, shared, activeVersion, isArchived, description.

Health

GET /api/v1/health → {"status":"ok",...}. Check this first — an n8n instance whose API key is scoped wrong or host unreachable fails here before any workflow edit.

Guardrails

  • The API key lives by label in the vault; never hardcode, never echo.
  • Save the GET response to disk before editing (enables retry without re-fetch).
  • Verify after every PUT (HTTP 200 + spot-check content).
  • Never copy another instance's host/workflow IDs into a different profile.

PITFALLS

  • 400 additional properties = payload has extra fields → use the strip recipe.
  • Check /health before assuming workflow edits are possible.
  • credentials must be popped from nodes before PUT or n8n rejects the payload.
from this repository

More skills

All skills
jpeetz
Community

accessibility-compliance-audit

Comprehensive web accessibility (a11y) audit and compliance skill. Audits HTML, React, Vue, and Angular codebases against WCAG 2.2 AA standards. Activates when users ask for "accessibility audit", "a11y check", "WCAG compliance", "ADA compliance", "screen reader testing", "keyboard navigation audit", "color contrast check", "accessibility fix", or "make this accessible". Detects violations, explains impact, and generates fix-ready code. Covers semantic HTML, ARIA authoring, focus management, col

installs
1
GitHub stars
14
Updated
Oct 21
jpeetz
Community

agent-n-video-pipeline

Use this skill when producing a fully-local "Agent N presents a message" video on the 16GB Apple-Silicon M5 executor: Kokoro mature TTS → LTX-2.3 MLX A2V talking render with native lip sync → karaoke captions → trim → QA → X caption. Replaces the old cloud Herald pipeline (grok-imagine + volcengine) with zero cloud cost. Activates for Herald release videos, Agent N announcements, and newsletter video messages.

installs
1
GitHub stars
14
Updated
Oct 21
jpeetz
Community

anti-over-engineering

Use when AI agents over-engineer code beyond user requests.

installs
1
GitHub stars
14
Updated
Oct 21
jpeetz
Community

api-and-interface-design

Use this skill when designing APIs, module boundaries, or any public interface. Create stable, well-documented interfaces that are hard to misuse — REST endpoints, GraphQL schemas, module contracts, component props. Covers contract-first design, error semantics, validation boundaries, idempotency, and consistent naming.

installs
1
GitHub stars
14
Updated
Oct 21