skills.rest
codewizwit
codewizwitCOMMUNITY
Explore all skills by this author →
GitHub

prompt-optimization

Analyzes prompts for clarity and structure issues and produces optimized rewrites with improvement metrics.

1|Updated Oct 11, 2025
Search Tags:#prompt engineering#prompt optimization#llm#claude#ai quality#prompt analysis#prompt rewrite
One-click install
npx skills add https://github.com/codewizwit/human-in-the-loop --skill prompt-optimization-codewizwit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prompt-optimization
Source: https://github.com/codewizwit/human-in-the-loop/tree/main/lib/skills/prompt-optimization
Command: npx skills add https://github.com/codewizwit/human-in-the-loop --skill prompt-optimization-codewizwit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Existing prompts often suffer from vagueness, missing context, poor structure, and scope creep, which degrade LLM output quality. This Skill diagnoses those issues and delivers a rewritten, higher-quality prompt. ## Core Features & Use Cases - Severity-Rated Analysis: Scans prompts across five categories (clarity, context, structure, scope, efficiency) and rates each issue as High, Medium, or Low severity. - Optimized Rewrites: Applies prompt engineering principles like specificity, explicit output formats, and prompt splitting to produce an improved version. - Before/After Metrics: Quantifies improvement with specificity, actionability, completeness, and structure scores. - Use Case: You have a vague code review prompt like "review this code and tell me if it's good." The Skill identifies missing criteria and output format, then rewrites it with specific review categories and a severity-rated output table. ## Quick Start Ask the assistant to analyze and optimize your existing prompt, specifying the target model such as Claude, GPT-4, or Gemini.

Frequently Asked Questions about prompt-optimization

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

FAQPage Schema
How do I optimize a prompt for Claude or GPT-4?▼

Provide the existing prompt and specify the target model such as Claude, GPT-4, or Gemini. The Skill analyzes issues across clarity, context, structure, scope, and efficiency, then delivers an optimized rewrite tailored to that model's strengths.

What makes a prompt vague or low quality?▼

Common problems include subjective terms without criteria, missing context the model needs, no defined output format, conflicting requirements, and unnecessary padding like fictional credentials. Each issue is rated High, Medium, or Low severity based on its impact on output quality.

When should I split a prompt into multiple prompts?▼

Split when a prompt serves multiple purposes, contains conflicting requirements, or shows scope creep, such as asking for system design plus cost estimates across three cloud providers. Simple single-purpose prompts should not be split into chains.

Can prompt optimization reduce token usage?▼

Yes, the efficiency analysis identifies wasted tokens, redundant content, and unnecessary persona details. Selecting conciseness as the optimization focus prioritizes reducing token count while preserving the prompt's intent.

What are the limitations of automated prompt optimization?▼

The Skill preserves the original prompt's intent and does not add requirements the user did not request. It avoids over-engineering simple prompts that only need minor tweaks and focuses on practical improvement over theoretical perfection.

Related Skills

Explore More Software Engineering Skills→
tronghieutronghieu
36

system-prompt-creator

Create structured system prompts for LLMs using layered drafting and review.

Community
Advanced
QuestNova502QuestNova502
4

senior-prompt-engineer

Design and optimize prompts for Claude and GPT-4 AI systems.

Community
Advanced
tanveerriaztanveerriaz
1

llm-eval-golden-set

Builds a golden set of test cases and an eval runner to detect LLM output regressions.

Community
Intermediate
wasintohwasintoh
90

prompt-optimizer

Optimizes text and image prompts for enhanced LLM and AI performance.

Community
Basic