n8n:create-instance-ai-eval

Automate AI workflow eval case creation with JSON files and LangTracer integration.

Updated Jul 3, 2026
One-click install
npx skills add https://github.com/Rub-git/n8n-auto --skill n8n-create-instance-ai-eval
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: n8n:create-instance-ai-eval
Source: https://github.com/Rub-git/n8n-auto/tree/main/.agents/skills/create-instance-ai-eval
Command: npx skills add https://github.com/Rub-git/n8n-auto --skill n8n-create-instance-ai-eval

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires n8n, langtracer, langsmith, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the creation and evaluation of AI workflow eval cases, ensuring that AI workflows are robust and perform as expected.

Core Features & Use Cases

  • Automated Case Creation: Generates JSON files for AI workflow eval cases, including build, behavior/process, credential, and seeded cases.
  • Real Build Calibration: Calibrates expectations against real builds to ensure accuracy.
  • Multi-Turn Director Scripting: Supports multi-turn director scripts for complex conversation scenarios.
  • Integration with LangTracer and LangSmith: Utilizes LangTracer for discovery and LangSmith for verification of AI failures.
  • Use Case: When you need to add a new AI workflow eval or debug why an existing one is flaky, this Skill can automate the process and provide detailed insights.

Quick Start

Run the 'n8n:create-instance-ai-eval' skill to create a new AI workflow eval case for the 'packages/@n8n/instance-ai/evaluations/data/workflows/' directory.

Frequently Asked Questions about n8n:create-instance-ai-eval

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate AI workflow evaluation case creation in n8n?

To automate AI workflow evaluation, use this Skill to generate JSON eval files for n8n workflows, calibrating expectations against real builds to ensure robustness.

Why does my n8n AI workflow fail during debugging and how can I trace it?

To debug flaky AI workflows, this Skill utilizes LangTracer for discovery and LangSmith for verification, providing detailed insights into why an existing evaluation fails.

Do I need LangSmith and LangTracer to evaluate n8n AI workflows?

Yes, you need LangSmith and LangTracer dependencies to evaluate n8n AI workflows, as the Skill utilizes LangTracer for discovery and LangSmith for verifying AI failures.

Can I test complex multi-turn conversation scenarios in n8n AI workflows?

Yes, you can test complex multi-turn conversation scenarios in n8n AI workflows using this Skill's multi-turn director scripting feature to automate comprehensive evaluation cases.

What types of evaluation cases are generated for n8n AI workflows?

Evaluation cases generated for n8n AI workflows include build, behavior/process, credential, and seeded cases, outputting JSON files to the specific evaluations data directory.

What's the best way to add a new evaluation case for a flaky n8n AI workflow?

The best way to add an evaluation case for a flaky n8n AI workflow is running this Skill to automate case creation, calibrating against real builds to debug performance issues.