Analyze and optimize prompts using a six-dimensional quality assessment framework.
npx skills add https://github.com/mbed92/phd --skill clavix-improve-mbed92
Please help me install this Agent Skill. Skill: clavix-improve Source: https://github.com/mbed92/phd/tree/main/.skills/clavix-improve Command: npx skills add https://github.com/mbed92/phd --skill clavix-improve-mbed92
This Skill addresses the challenge of crafting effective prompts for AI models by providing a structured analysis and optimization process, ensuring prompts are clear, complete, and actionable.
Use the clavix-improve skill to analyze and optimize the prompt: "Make me a website."
High-intent search queries and answers about installing and using this skill.
Analyze prompt quality across six dimensions: Clarity, Efficiency, Structure, Completeness, Actionability, and Specificity. This process identifies ambiguities and applies refinement patterns to generate an enhanced, actionable prompt for LLM code generation.
Refine a vague prompt by calculating its quality score to automatically select an analysis depth. The process then applies proven improvement patterns to transform the vague input into a structured, detailed prompt.
You need automated prompt refinement before implementing complex AI-driven features to ensure the AI understands requirements precisely. This prevents misinterpretations, leading to better output and reduced iteration cycles.
No, this prompt optimization process does not generate or execute code directly. It is strictly designed for prompt refinement and quality assessment before implementation, ensuring your instructions are clear and complete.
Automated depth selection works by calculating an initial quality score from your prompt. Based on this score, the system intelligently chooses between standard or comprehensive analysis depth to apply the appropriate level of improvements.
nathankoerschnerEstablish production-grade evaluation frameworks for LLM applications and agents.
heysuhasEvolve prompt templates, regex patterns, and code snippets via LLM-driven search.
0xHoneyJarAnalyze and enhance user prompts using PTCF framework and task classification.
QcasaresDesign and optimize AI prompts using CoT, few-shot, and XML techniques.
