Run any Skill in Manus with one click

n8n-workflow-operator

Stars10

Forks1

UpdatedJune 21, 2026 at 16:58

Create, update, validate, test, and debug n8n workflows through ThinkWork's managed n8n MCP tools. Use when a request names n8n, workflows, executions, Code node packages, workflow migration, automation drafts, or asks to create an automation from a thread.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

thinkwork-ai

thinkwork-ai/thinkwork

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

File Explorer

4 files

SKILL.md

readonly

name	n8n-workflow-operator
description	Create, update, validate, test, and debug n8n workflows through ThinkWork's managed n8n MCP tools. Use when a request names n8n, workflows, executions, Code node packages, workflow migration, automation drafts, or asks to create an automation from a thread.
license	Apache-2.0
compatibility	ThinkWork n8n plugin with managed n8n MCP tools and a tenant n8n instance.
metadata	{"thinkwork-plugin":"n8n","skill-format":"agentskills"}

n8n Workflow Operator

Use n8n as a shared tenant automation runtime. Read live workflow and node state, make draft-safe changes, validate the result, and leave production activation to the shared native n8n operator unless the human explicitly says otherwise.

First Move

Use this skill before any n8n workflow create, update, validation, test, or debug action.
Use the n8n MCP tools provided by the installed ThinkWork n8n plugin. The plugin uses a tenant service credential, not per-user n8n activation.
If n8n tools are missing, report that the operator must install the n8n plugin, deploy the managed app, enable instance-level MCP in n8n, and enable MCP access on the workflow, project, or folder.
Trust live MCP tool descriptions and node schemas over memory. n8n changes quickly; if a live tool or schema disagrees with this skill, follow the live tool and report the drift in the handoff.

Authoring Loop

For requests such as "create a workflow", "edit this workflow", or "make a smoke test":

Classify the pattern: manual trigger, webhook, schedule, HTTP API integration, database sync, AI agent, or batch processing.
Read MCP tooling, then discover live node schemas before configuring nodes.
Read workflow authoring, then create or update an inactive draft. Use UUID-shaped node ids, current typeVersion values, and no placeholder credentials or secrets.
Validate iteratively. Treat validation errors as normal feedback: fix the specific field, then validate again.
Fetch the workflow after every create or update and inspect connections so silently dropped or wrong wires are caught before handoff.
Test only when safe. n8n test runs execute real HTTP calls, writes, sends, and other side effects.
Finish with validation and handoff.

ThinkWork Agent-Step Bridge

For n8n-to-ThinkWork agent work, use the v1 agent-step bridge with stock HTTP Request and Wait nodes. Do not suggest a custom ThinkWork n8n node in v1.
The HTTP Request node calls ThinkWork's /api/integrations/n8n/agent-steps endpoint with the separate inbound bridge credential. Do not reuse the native n8n MCP service credential.
The workflow must pass target Space, target agent, instructions, structured input, workflow id/name, execution id, step id, correlation id, optional request id, optional timeout, and the current Wait-node resume URL from $execution.resumeUrl.
The Wait node should use On webhook call. Downstream nodes should branch on the resumed payload's status and read output, error, summary, and links; they should not scrape ThinkWork thread pages.
Explain idempotency as workflow id + execution id + correlation id + step id. Retrying the same bridge step should recover or replay the existing ThinkWork thread rather than creating a duplicate.

Stop Conditions

Stop before writing when multiple workflows match, the workflow/project/folder does not have MCP access enabled, credentials are unknown, a test would touch production side effects, the user asks for production activation without using the native n8n operator account, or the live MCP tool surface conflicts with the requested action.

More from this repository

same repository

document-composer

thinkwork-ai/thinkwork

Compose beautiful, self-contained HTML document deliverables — ideation docs, plans, reports, and briefs — saved as durable artifacts via emit_document. Use whenever the deliverable is document-shaped: the user asks for a plan, report, brief, write-up, analysis, proposal, or ideation summary, or asks to "write this up", "make a document", "put together a report", or when a substantial multi-section answer deserves a durable, shareable form instead of chat text.

2026-07-0410

thinkwork-plugin-builder

thinkwork-ai/thinkwork

Package existing Terraform projects as reviewable ThinkWork Application Plugin catalog contributions. Use when a user asks to convert Terraform, AWS infrastructure, customer POCs, managed applications, or integration repos into ThinkWork plugins, especially premium/key-gated plugins such as McPherson Lakehouse.

2026-07-0410

thinkwork-linear-dispatcher

thinkwork-ai/thinkwork

Route ThinkWork Linear issues through Codex automation. Use when acting as the ThinkWork `linear-agent-dispatcher` heartbeat, when asked to inspect ThinkWork Linear automation state, or when deciding whether to launch/continue Codex workers for ThinkWork issues labeled Codex/LFG.

2026-06-2410

automation-loop-designer

thinkwork-ai/thinkwork

Design a ThinkWork Automation from a prompt by interviewing for goal, Space, trigger, verification, judge settings, stop guards, and privacy boundaries, then emit a reviewable AutomationDraft.

2026-06-2310

skill-creator

thinkwork-ai/thinkwork

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

2026-06-2210

artifact-builder

thinkwork-ai/thinkwork

Builds reusable ThinkWork Computer apps and interactive artifacts from research prompts. Use when the user asks to build, create, generate, or make a dashboard, app, report, briefing, workspace, or other interactive surface.

2026-05-2210

name	n8n-workflow-operator
description	Create, update, validate, test, and debug n8n workflows through ThinkWork's managed n8n MCP tools. Use when a request names n8n, workflows, executions, Code node packages, workflow migration, automation drafts, or asks to create an automation from a thread.
license	Apache-2.0
compatibility	ThinkWork n8n plugin with managed n8n MCP tools and a tenant n8n instance.
metadata	{"thinkwork-plugin":"n8n","skill-format":"agentskills"}

n8n Workflow Operator

First Move

Use this skill before any n8n workflow create, update, validation, test, or debug action.
Use the n8n MCP tools provided by the installed ThinkWork n8n plugin. The plugin uses a tenant service credential, not per-user n8n activation.
If n8n tools are missing, report that the operator must install the n8n plugin, deploy the managed app, enable instance-level MCP in n8n, and enable MCP access on the workflow, project, or folder.
Trust live MCP tool descriptions and node schemas over memory. n8n changes quickly; if a live tool or schema disagrees with this skill, follow the live tool and report the drift in the handoff.

Authoring Loop

For requests such as "create a workflow", "edit this workflow", or "make a smoke test":

Classify the pattern: manual trigger, webhook, schedule, HTTP API integration, database sync, AI agent, or batch processing.
Read MCP tooling, then discover live node schemas before configuring nodes.
Read workflow authoring, then create or update an inactive draft. Use UUID-shaped node ids, current typeVersion values, and no placeholder credentials or secrets.
Validate iteratively. Treat validation errors as normal feedback: fix the specific field, then validate again.
Fetch the workflow after every create or update and inspect connections so silently dropped or wrong wires are caught before handoff.
Test only when safe. n8n test runs execute real HTTP calls, writes, sends, and other side effects.
Finish with validation and handoff.

ThinkWork Agent-Step Bridge

For n8n-to-ThinkWork agent work, use the v1 agent-step bridge with stock HTTP Request and Wait nodes. Do not suggest a custom ThinkWork n8n node in v1.
The HTTP Request node calls ThinkWork's /api/integrations/n8n/agent-steps endpoint with the separate inbound bridge credential. Do not reuse the native n8n MCP service credential.
The workflow must pass target Space, target agent, instructions, structured input, workflow id/name, execution id, step id, correlation id, optional request id, optional timeout, and the current Wait-node resume URL from $execution.resumeUrl.
The Wait node should use On webhook call. Downstream nodes should branch on the resumed payload's status and read output, error, summary, and links; they should not scrape ThinkWork thread pages.
Explain idempotency as workflow id + execution id + correlation id + step id. Retrying the same bridge step should recover or replay the existing ThinkWork thread rather than creating a duplicate.