Prompt Optimizer

This turns fuzzy requirements into testable specs using EARS syntax, a Rolls-Royce methodology that structures natural language into precise patterns like "When user creates task, system shall guide decomposition into sub-tasks." It layers on domain theory grounding (GTD for productivity, BJ Fogg for behavior change), extracts concrete examples with real data, then outputs a complete Role/Skills/Workflows/Examples/Formats prompt. Most useful when someone gives you "build a dashboard" or "make it user-friendly" and you need measurable criteria and explicit triggers. The four reference files cover EARS patterns, 40+ theories across 10 domains, complete transformations, and advanced techniques for multi-stakeholder requirements. Honest take: this is overkill for simple features but genuinely helpful when requirements ambiguity would otherwise cost you three revision rounds.

skills.sh installs: 2.1K
GitHub stars: 1.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add daymade/claude-code-skills --skill prompt-optimizer --agent claude-code

Installs into .claude/skills of the current project.

Files

Prompt Optimizer

Overview

Optimize vague prompts into precise, actionable specifications using EARS (Easy Approach to Requirements Syntax) - a Rolls-Royce methodology for transforming natural language into structured, testable requirements.

Methodology inspired by: This skill's approach to combining EARS with domain theory grounding was inspired by 阿星AI工作室 (A-Xing AI Studio), which demonstrated practical EARS application for prompt enhancement.

Four-layer enhancement process:

EARS syntax transformation - Convert descriptive language to normative specifications
Domain theory grounding - Apply relevant industry frameworks (GTD, BJ Fogg, Gestalt, etc.)
Example extraction - Surface concrete use cases with real data
Structured prompt generation - Format using Role/Skills/Workflows/Examples/Formats framework