Install
$ agentstack add skill-cuopipyyy-skills-for-agent-n8n-api-v1 ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
n8n API v1
Use this skill when working with n8n over REST API v1. Start from the smallest endpoint set needed for the task, prefer read-only verification before mutation, and keep authentication and destructive operations explicit.
Quick Start
- Confirm the base URL and API key before making requests.
- Prefer these environment variables:
N8N_BASE_URL, defaulthttp://localhost:5678/api/v1N8N_API_KEY
- Send the API key in header
X-N8N-API-KEY. - For list endpoints, handle cursor pagination with
limitandcursor. - For destructive operations, identify the exact resource ID first, then perform the write.
Safety Rules
- Prefer
GETrequests beforePOST,PUT,PATCH, orDELETE. - Do not delete, transfer, deactivate, or bulk-update resources unless the user asked for it.
- When mutating resources, restate the target endpoint, target ID, and key payload fields.
- Avoid exposing credential secrets or tokens in responses.
- If the base URL, workspace, or auth context is unclear, surface the assumption.
Workflow
Establish request context
- Read
references/endpoint-map.mdfirst for the endpoint family. - Read
references/api-guide.mdonly for the sections needed for the current task. - Default to the local instance unless the user provides another URL.
Choose the endpoint family
- Workflows: create, update, activate, deactivate, transfer, tag.
- Executions: list, inspect, retry, delete, tag.
- Credentials: list, create, update, transfer, delete, inspect schema.
- Tags, users, variables, data tables, projects, audit, source control: use the matching section in the references.
Build requests carefully
- Use the auth header and explicit
Content-Type: application/jsonfor JSON bodies. - Preserve IDs exactly as returned by n8n.
- For paginated listings, loop on
nextCursoruntil empty. - For bulk or scripted operations, validate with one small request first.
Output Expectations
- Provide the exact endpoint path and method.
- Mention required headers, query parameters, and body fields.
- Prefer
curlexamples unless the user asked for another language. - Mention when a response may be paginated or destructive.
Resources
references/endpoint-map.md: compact endpoint map and operating rules.references/api-guide.md: full API v1 guide, examples, and appendix.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Cuopipyyy
- Source: Cuopipyyy/skillsfor_agent
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.