prompt-elo

Analyze prompts to generate Elo-based quality scores and HTML reports.

1|Updated Feb 3, 2026
One-click install
npx skills add https://github.com/bicro/PromptElo --skill prompt-elo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-elo
Source: https://github.com/bicro/PromptElo/tree/main/skills/prompt-elo
Command: npx skills add https://github.com/bicro/PromptElo --skill prompt-elo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Prompt prompts want objective quality assessment; Provide Elo-based scoring to standardize evaluation of prompts and guide improvements.

Core Features & Use Cases

  • Elo-style scoring across 5 criteria (Clarity, Specificity, Context, Creativity, Novelty) for consistent prompt quality measurement.
  • Detailed visual reports including radar charts and score breakdowns for quick insights.
  • Global ranking and privacy-preserving comparisons to benchmark prompts without exposing raw prompts.
  • HTML report export for sharing results with teams or clients.

Quick Start

Provide the prompt you want evaluated to generate a detailed Elo report.

Frequently Asked Questions about prompt-elo

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

FAQPage Schema
How do I evaluate prompt quality using Elo scoring?

To evaluate prompt quality using Elo scoring, provide your prompt to the analyzer. It applies an Elo-based system across five criteria—Clarity, Specificity, Context, Creativity, and Novelty—to generate a standardized quality score.

Can I generate a radar chart for prompt analysis?

Yes, you can generate a radar chart for prompt analysis. The scorer processes your prompt and outputs a detailed visual report that includes a radar chart, a score breakdown, and targeted improvement suggestions.

How does Elo-based prompt scoring work?

Elo-based prompt scoring works by evaluating individual prompts against five specific criteria: Clarity, Specificity, Context, Creativity, and Novelty. This mechanism produces an objective quality score to standardize evaluation and guide improvements.

What is the best way to share prompt evaluation reports with a team?

The best way to share prompt evaluation reports is by exporting the generated HTML report. This allows you to distribute the detailed radar charts and score breakdowns directly with teams or clients.

Does the prompt scorer support privacy-preserving comparisons?

Yes, the prompt scorer supports privacy-preserving comparisons. It includes a global ranking feature that allows you to benchmark your prompts against others without exposing your raw prompt text.

Are there limitations to evaluating prompts with Elo scoring?

A limitation of evaluating prompts with Elo scoring is that it assesses quality based strictly on five criteria: Clarity, Specificity, Context, Creativity, and Novelty. It generates scores and suggestions but does not execute the prompts to measure runtime outputs.