eval-driven-dev
CommunityAutomate LLM app QA and iteration.
Authoryiouli
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill streamlines the entire quality assurance process for LLM-powered applications, from initial setup to iterative debugging and performance improvement.
Core Features & Use Cases
- Automated Instrumentation: Easily add tracing to your Python LLM applications.
- Dataset Generation: Build golden datasets from real application runs.
- Eval Test Creation: Automatically generate tests using various evaluators.
- Full QA Loop: Instrument, build datasets, write tests, run evals, and investigate failures.
- Use Case: When developing a new AI agent, use this Skill to set up a robust evaluation pipeline that catches regressions and ensures output quality before shipping.
Quick Start
Use the eval-driven-dev skill to set up QA for my Python AI project.
Dependency Matrix
Required Modules
None requiredComponents
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: eval-driven-dev Download link: https://github.com/yiouli/pixie-qa/archive/main.zip#eval-driven-dev 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.