meta-prompting

Community

Systematically improve LLM outputs

AuthorHermeticOrmus
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill addresses the challenge of generating high-quality, iterative outputs from LLMs by providing a structured framework for prompt improvement and complexity routing.

Core Features & Use Cases

  • Recursive Prompt Improvement: Automatically refines prompts based on previous outputs and quality assessments.
  • Complexity Routing: Adapts strategies based on task complexity (simple, medium, complex).
  • Context Extraction: Learns from each iteration to inform subsequent steps.
  • Quality Assessment: Scores outputs to guide the iteration process.
  • Use Case: When developing complex code or detailed documentation, this Skill ensures that each iteration builds upon the last, leading to a more robust and accurate final product than a single-shot prompt.

Quick Start

Use the meta-prompting skill to improve the output for writing a function to validate email addresses.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: meta-prompting
Download link: https://github.com/HermeticOrmus/hermetic-claude/archive/main.zip#meta-prompting

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.