optimize-anything

Optimize text artifacts through iterative LLM-powered search and evaluation feedback.

18|1|Updated Mar 2, 2026

Search Tags:#prompt engineering #optimization #llm #code improvement #agent architecture #configuration tuning

Ready to run

npx skills add https://github.com/rachittshah/optimize-anything --skill optimize-anything

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: optimize-anything
Source: https://github.com/rachittshah/optimize-anything/tree/main/skill
Command: npx skills add https://github.com/rachittshah/optimize-anything --skill optimize-anything

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of improving any text-based artifact, such as prompts, code, configurations, or agent architectures, by using an iterative, LLM-powered search with feedback.

Core Features & Use Cases

Iterative Optimization: Refines text artifacts through cycles of evaluation and LLM-driven improvement.
Versatile Application: Can optimize prompts, code, configurations, and agent architectures.
Use Case: Improve a system prompt to be more helpful and concise by iteratively refining it based on LLM feedback and evaluation scores.

Quick Start

Use the optimize-anything skill to optimize the provided system prompt for clarity and conciseness.

Frequently Asked Questions about optimize-anything

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

FAQPage Schema

How do I iteratively improve a system prompt using LLM feedback?▼

To iteratively improve a system prompt, define the candidate prompt, an evaluator (Python, shell, or LLM judge), and an objective. The optimization process refines the text artifact through cycles of evaluation and LLM-driven improvement.

Can I optimize code and configurations automatically through evaluation?▼

Yes, you can optimize code and configurations by defining the text artifact as a candidate and providing an evaluation script. The system uses LLM-powered search and evaluation feedback to iteratively refine the configuration or code.

What is needed to set up an evaluator for iterative text optimization?▼

Setting up an evaluator for text optimization requires defining an objective and specifying an evaluator, which can be a Python script, a shell command, or an LLM judge. You also need a candidate artifact to evaluate.

Does prompt engineering optimization support multi-task and generalization modes?▼

Prompt engineering optimization supports single-task, multi-task, and generalization optimization modes. These modes allow you to refine text artifacts for specific tasks or broader applicability using iterative LLM-powered search.

What is the best way to automate agent architecture refinement?▼

The best way to automate agent architecture refinement is treating the architecture as a text artifact, defining an objective, and using an evaluator. The iterative LLM-driven search evaluates and modifies the architecture to improve performance.

Why does iterative text optimization require a defined objective?▼

Iterative text optimization requires a defined objective because it serves as the target for the evaluator (Python, shell, or LLM judge). The objective guides the LLM-powered search to effectively refine the candidate artifact through feedback.