quality-enriched-prompting

Evaluate and iteratively refine prompts using [0,1]-enriched category quality metrics.

1|Updated Feb 2, 2026

Search Tags:#prompt engineering #AI development #LLM optimization #quality metrics #category theory #prompt quality

Ready to run

npx skills add https://github.com/HermeticOrmus/hermetic-claude --skill quality-enriched-prompting-hermeticormus

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: quality-enriched-prompting
Source: https://github.com/HermeticOrmus/hermetic-claude/tree/main/claude/skills/quality-enriched-prompting
Command: npx skills add https://github.com/HermeticOrmus/hermetic-claude --skill quality-enriched-prompting-hermeticormus

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of systematically improving prompt quality for language models by applying principles from category theory, specifically [0,1]-enriched categories, to create a quantifiable and optimizable framework for prompt engineering.

Core Features & Use Cases

Quality Metrics: Defines multi-dimensional quality vectors (clarity, specificity, completeness, coherence, relevance) for prompts and responses.
Enriched Category Framework: Implements enriched categories where morphisms represent quality scores, enabling composition and analysis of prompt transformation quality.
LLM-Based Evaluation & Improvement: Leverages LLMs to evaluate prompt quality and suggest improvements based on identified weak dimensions.
Use Case: Enhance the quality of prompts used for generating technical documentation by iteratively refining them to maximize clarity, specificity, and relevance, ensuring the output is accurate and useful.

Quick Start

Use the quality-enriched-prompting skill to optimize the prompt 'Write a summary of the document.' for clarity and specificity.

Frequently Asked Questions about quality-enriched-prompting

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

FAQPage Schema

How do I optimize prompt quality for language models systematically?▼

To systematically improve prompt quality, this framework uses LLM-based evaluation to identify weak dimensions in clarity, specificity, completeness, coherence, or relevance, and iteratively refines the prompt to maximize output accuracy.

What are the best metrics for evaluating prompt engineering effectiveness?▼

Effective prompt engineering metrics include clarity, specificity, completeness, coherence, and relevance. These dimensions are structured as enriched categorical morphisms to analyze prompt transformation quality and guarantee Pareto optimality.

Can category theory be used to guarantee prompt optimization?▼

Yes, category theory provides categorical guarantees like transitivity and Pareto optimality for prompt refinement. It uses a [0,1]-enriched category framework where morphisms represent quality scores to systematically enhance prompts.

How do I refine technical documentation prompts for specificity and relevance?▼

You refine technical documentation prompts by iteratively improving them to maximize clarity, specificity, and relevance. This involves using LLM-based evaluation to identify weak dimensions and applying categorical guarantees to ensure output accuracy.

Does LLM optimization require prerequisite frameworks for prompt evaluation?▼

LLM optimization requires an enriched categorical framework to define quality metrics and evaluate prompts. This structure supports LLM-based evaluation and iterative improvement by identifying weak dimensions in the prompt.