production-evals-framework
CommunityBuild robust LLM evaluation systems.
Authornathankoerschner
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill provides a comprehensive framework for building, implementing, and operating production-grade evaluation systems for LLM applications, ensuring quality, reliability, and cost-effectiveness.
Core Features & Use Cases
- End-to-End Evals Stack: Covers everything from defining systems under test to running experiments and establishing operating cadences.
- Multi-Stage Evaluation: Implements golden sets, labeled scenarios, replay harnesses, rubric scoring, and experiment comparisons.
- Use Case: You've deployed a new AI chatbot for customer support. Use this Skill to set up automated tests that continuously check its accuracy, relevance, and tone against predefined benchmarks and user feedback, ensuring it meets quality standards before and after updates.
Quick Start
Use the production-evals-framework skill to define a system under test for your RAG application.
Dependency Matrix
Required Modules
None requiredComponents
references
💻 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: production-evals-framework Download link: https://github.com/nathankoerschner/dotfiles/archive/main.zip#production-evals-framework 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 471,000+ vetted skills library on demand.