dw-skill-eval-report

Convert scores.yaml into a cross-model evaluation report with key findings.

1|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/xurik/dataworks-skill-evaluator --skill dw-skill-eval-report
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dw-skill-eval-report
Source: https://github.com/xurik/dataworks-skill-evaluator/tree/main/eval/skills/dw-skill-eval-report
Command: npx skills add https://github.com/xurik/dataworks-skill-evaluator --skill dw-skill-eval-report

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill converts the evaluation results captured in scores.yaml into a human-readable report, including a cross-model comparison matrix, key findings with references to transcripts, and improvement recommendations tied to the SKILL.md location.

Core Features & Use Cases

  • Convert scores.yaml into a formatted, shareable report (report.md)
  • Present cross-model performance with a comparison matrix
  • Reference specific cases and transcripts to support findings
  • Propose improvement recommendations linked to the source SKILL.md

Quick Start

Run the report generator on the existing scores.yaml to produce the human-readable report.

Frequently Asked Questions about dw-skill-eval-report

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate a human-readable report from scores.yaml?

This Skill reads scores.yaml and generates report.md, a human-readable evaluation report that includes a cross-model comparison matrix, key findings with transcript references, and improvement recommendations.

Can I include cross-model comparison results in my evaluation report?

Yes, the generated report.md includes a cross-model comparison matrix derived from scores.yaml, allowing you to compare performance metrics and key findings across different models directly.

How do I reference specific evaluation transcripts in my data analytics report?

The Skill automatically references specific transcripts and evaluation artifacts within report.md, linking key findings to their source cases to ensure traceability and support the analysis.

What is the best way to add improvement recommendations to a model evaluation report?

The best way is to use this Skill, which automatically proposes improvement recommendations in report.md and links them directly to the source SKILL.md location for actionable context.

Does the report generator require skill-analysis.yaml to function?

The report generator requires scores.yaml as the primary input to produce report.md, and it also references skill-analysis.yaml to provide additional context for the evaluation findings.