skills.rest
hjemmesidekongen
hjemmesidekongenCOMMUNITY
Explore all skills by this author →
GitHub

prompt-optimizer

Refine vague prompts into structured instructions using RSCIT, RTF, RISEN, RODES, and CoT frameworks.

1|Updated Mar 1, 2026
Search Tags:#prompt engineering#prompt optimization#ai#llm#instruction tuning#rscit
One-click install
npx skills add https://github.com/hjemmesidekongen/ai --skill prompt-optimizer-hjemmesidekongen
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prompt-optimizer
Source: https://github.com/hjemmesidekongen/ai/tree/main/plugins/kronen/skills/prompt-optimizer
Command: npx skills add https://github.com/hjemmesidekongen/ai --skill prompt-optimizer-hjemmesidekongen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill transforms vague or underspecified prompts into precise, actionable instructions for AI, ensuring better and more predictable results.

Core Features & Use Cases

  • Auto-Sharpening (Mode A): Automatically refines prompts detected as vague by inferring context from the codebase.
  • Prompt Builder (Mode B): Guides users through creating polished prompts using structured frameworks via the /prompt:create command.
  • Use Case: When you give an AI a vague request like "improve this code," the prompt-optimizer will analyze your project, ask clarifying questions if needed, and output a structured prompt like "Refactor this React component to optimize state management, focusing on reducing re-renders, and provide the updated code in a block."

Quick Start

Use the prompt-optimizer skill to build a prompt for generating a marketing email.

Frequently Asked Questions about prompt-optimizer

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

FAQPage Schema
How do I optimize vague AI prompts into structured instructions?▼

To optimize vague AI prompts, this Skill transforms underspecified natural language into precise instructions by inferring codebase context and applying structured frameworks like RSCIT, RTF, and RISEN to ensure predictable AI model outputs.

What is the best way to automatically refine prompts for an LLM?▼

Automatically refine LLM prompts using the Auto-Sharpening mode, which detects vague requests and infers missing context directly from your codebase to generate structured instructions without manual intervention.

How do I build a prompt using the RSCIT framework step by step?▼

Build a prompt using the RSCIT framework through the interactive Prompt Builder mode, which guides you step by step via command-line interface to define clarity, context, and constraints for your AI interactions.

Can I use prompt optimization for instruction tuning on existing code?▼

Yes, you can use prompt optimization for instruction tuning on existing code, as the Skill analyzes your project context to refine requests like code improvement into specific instructions focusing on constraints and output formatting.

Why does my AI model return unpredictable results from underspecified prompts?▼

Underspecified prompts cause unpredictable AI results because they lack sufficient clarity, context, and constraints, a problem solved by transforming vague requests into structured instructions using defined frameworks like RODES and Chain of Thought.

Related Skills

Explore More Software Engineering Skills→
MomoChenisMeMomoChenisMe
1

speclink-onboard

Generate initial canonical specifications from current codebase behavior using Speclink CLI.

Community
Intermediate
LynxLabVNLynxLabVN

outlines

Generate valid JSON, XML, or code outputs using Pydantic models and local model backends.

Official
Advanced
LynxLabVNLynxLabVN

mcporter

Manage MCP servers and tools via command-line interface.

Official
Intermediate
d0whc3rd0whc3r

llm-prompt-optimizer

Diagnose and rewrite LLM prompts using RSCIT, Chain-of-Thought, and Few-Shot patterns.

Community
Advanced