run-eval
OfficialTest and refine skill triggers.
Software Engineering#prompt engineering#skill refinement#skill evaluation#trigger testing#workbench#AI accuracy
Authordlt-hub
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill helps improve AI assistant accuracy by evaluating how well a skill's description triggers for various user requests, identifying and fixing issues like missed triggers or incorrect activations.
Core Features & Use Cases
- Trigger Evaluation: Runs predefined test queries against a skill's description to measure precision and recall.
- Clash Analysis: Identifies when multiple skills might incorrectly trigger for the same query.
- Description Refinement: Provides actionable insights and proposed changes to improve skill descriptions for better AI understanding.
- Use Case: After updating a skill's description, use this to ensure it now correctly captures new user intents without negatively impacting existing ones.
Quick Start
Use the run-eval skill to test the 'run-eval' skill in the 'workbench' toolkit.
Dependency Matrix
Required Modules
None requiredComponents
scripts
💻 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: run-eval Download link: https://github.com/dlt-hub/dlthub-ai-workbench/archive/main.zip#run-eval Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.