Skills
.Work. You
Rest

quality-eval

Community

Durable qualitative evaluation for slow results.

Data & Analytics#evaluation#quality#ux#experimentation#model-comparison#eval#qualitative
AuthorHonigbart
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Qualitative validation can be slow to organize and reproduce across fresh sessions. This skill provides a durable workflow for creating and running eval briefs, and scaffolds the artifacts under .ai/evals/<slug>/ to preserve context, runs, and conclusions.

Core Features & Use Cases

  • Durable eval briefs with a structured brief.md
  • Two modes: Prepare to configure and Run/Resume to execute validations
  • Separate run logs and results under .ai/evals/<slug>/runs/ and .ai/evals/<slug>/results.md
  • Easy slug resolution from the feature or prompt being evaluated
  • Flexible to compare multiple variants, prompts, or UX flows

Quick Start

Create an eval slug and run Prepare mode to set up a durable eval brief in a fresh session.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: quality-eval
Download link: https://github.com/Honigbart/honeyflow/archive/main.zip#quality-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 471,000+ vetted skills library on demand.