n8n-multi-instance

Use when an n8n-mcp account targets more than one n8n instance — i.e. the `n8n_instances` tool is available, the user mentions multiple n8n instances or environments (prod vs staging, several teams or clients), a workflow / datatable / credential / execution call returns an unexpected NOT_FOUND or reads data you don't recognize, or a credential create/update/delete is refused with an `INSTANCE_AMBIGUOUS` error. Covers choosing and switching which instance this MCP session targets, verifying the target before high-stakes work — credential writes above all — and recovering from misroutes and ambiguous-write fail-closes. Always consult this skill before operating on a specific instance, before any credential create/update/delete on a multi-instance account, or when a call hits the wrong/empty data or an `INSTANCE_AMBIGUOUS` error.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable and workflow-clear, with exact tool calls, return shapes, and explicit validation/feedback loops for high-stakes credential writes. Its main weakness is conciseness: the core credential-safety guidance is repeated across many sections and the monolithic structure leaves no room for progressive disclosure into reference files.

Suggestions

Consolidate the verify-before-credential-write and INSTANCE_AMBIGUOUS→switch→retry guidance into a single authoritative section; have other sections link to it instead of restating it (Golden rules, Credential operations, copy task, and Quick reference currently overlap heavily).

Consider moving the full error-envelope table and the INSTANCE_AMBIGUOUS payload deep-dive into a references/ file, keeping SKILL.md as a lean overview with one-level-deep links.

Tighten the 'How targeting behaves' section — several of its bullets restate rules already covered in Golden rules and Credential operations.

Dimension	Reasoning	Score
Conciseness	No padding with concepts Claude already knows, but the verify-before-credential-write and INSTANCE_AMBIGUOUS→switch→retry guidance is restated across the Golden rules, INSTANCE_AMBIGUOUS section, 'How targeting behaves', Recovery playbook, Credential operations, copy task, and Quick reference — could be tightened by deduplication.	3 / 5
Actionability	Fully executable, copy-paste-ready tool calls (e.g. n8n_instances({mode:"list"}), {mode:"switch", name:"prod"}), exact return shapes, error codes, and numbered procedures cover the common cases.	5 / 5
Workflow Clarity	Clear numbered sequences with an explicit validation checkpoint before credential writes, plus feedback loops (INSTANCE_AMBIGUOUS→switch→retry, NOT_FOUND→re-list→switch→retry) and checklists (Golden rules, Quick reference); validation is present so the destructive-cap does not apply.	5 / 5
Progressive Disclosure	Well-organized single file with clear headers and a Quick reference for navigation, but with no bundle files the ~180-line body is monolithic and the error-envelope / INSTANCE_AMBIGUOUS deep-dive could plausibly live in a one-level-deep reference.	4 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific, trigger-rich, and complete, explicitly stating both what the skill does and when to invoke it with concrete error-code and scenario triggers. It is verbose but every clause carries trigger or capability information rather than fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'choosing and switching which instance this MCP session targets', 'verifying the target before high-stakes work', 'recovering from misroutes and ambiguous-write fail-closes' — covering the skill's full scope with no real gaps.	5 / 5
Completeness	Explicitly answers both what ('Covers choosing and switching… verifying… recovering…') and when ('Use when…' plus 'Always consult this skill before…') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural triggers with synonyms — 'more than one n8n instance', 'prod vs staging', 'several teams or clients', 'unexpected NOT_FOUND', 'reads data you don't recognize', 'INSTANCE_AMBIGUOUS error'.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (n8n multi-instance MCP routing, INSTANCE_AMBIGUOUS, the n8n_instances tool) with highly distinctive triggers and minimal overlap with sibling skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: czlonkowski/n8n-mcp
Path: data/skills/n8n-multi-instance/SKILL.md
Commit: fe3a4cb

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.