create-eval

Official

Test skill triggers and accuracy.

Authordlt-hub
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps ensure that your AI assistant correctly understands when to use a specific tool (skill) by setting up automated tests for its trigger conditions.

Core Features & Use Cases

  • Trigger Testing: Create a dedicated environment to test if a skill's description accurately matches user requests.
  • Accuracy Measurement: Generate realistic "should-trigger" and "should-not-trigger" queries to measure and improve skill recall and precision.
  • Use Case: Before deploying a new skill for generating Python code, use this to create a suite of tests that verify it only activates for code-related requests and not for general conversation.

Quick Start

Create an evaluation for the 'rest-api-pipeline' toolkit's 'create-pipeline' skill.

Dependency Matrix

Required Modules

uvlist_skill_descriptions.pycreate_eval_workspace.py

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: create-eval
Download link: https://github.com/dlt-hub/dlthub-ai-workbench/archive/main.zip#create-eval

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.