skills.rest
yanochka11
yanochka11COMMUNITY
Explore all skills by this author →
GitHub

prompt-optimizer

Refine prompts by analyzing structure and evaluating variants for clarity.

Updated May 5, 2026
Search Tags:#prompt engineering#prompt optimization#claude#evaluation#gemini#openai#agent prompts
One-click install
npx skills add https://github.com/yanochka11/harness_bro --skill prompt-optimizer-yanochka11
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: prompt-optimizer
Source: https://github.com/yanochka11/harness_bro/tree/main/.claude/skills/ported/prompt-optimizer
Command: npx skills add https://github.com/yanochka11/harness_bro --skill prompt-optimizer-yanochka11

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps improve unreliable, unclear, or inefficient prompts by applying structured optimization methods, evaluation practices, and model-specific guidance.

Core Features & Use Cases

  • Prompt Refinement: Analyze and rewrite existing prompts while preserving intent, constraints, and required behaviors.
  • Prompt Evaluation Strategy: Build evaluation criteria, compare prompt variants, and diagnose failures through iterative optimization loops.
  • Model Adaptation: Adjust prompts for different model families such as OpenAI, Claude, and Gemini while maintaining a portable core structure.
  • Use Case: Improve a coding agent system prompt by identifying failure patterns, restructuring instructions, and validating the revised version against representative tasks.

Quick Start

Ask the prompt-optimizer skill to refine an existing agent prompt for better reliability and clearer behavior.

Frequently Asked Questions about prompt-optimizer

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

FAQPage Schema
How do I optimize prompts for better reliability and clearer behavior?▼

Prompt evaluation criteria help diagnose failures by comparing prompt variants through iterative optimization loops. You build specific evaluation metrics, test revised versions against representative tasks, and validate reliability improvements before deployment.

Can I adapt existing agent prompts for different model families like OpenAI, Claude, and Gemini?▼

To debug an unreliable agent system prompt, you identify failure patterns, restructure instructions for clarity, and validate the revised version against representative tasks. This systematic refinement isolates specific failure triggers and improves instruction reliability.

What is the best way to create reusable prompt templates for agent workflows?▼

Creating reusable prompt templates requires structured prompt analysis and external context tracking to separate fixed logic from variable inputs. This approach yields portable templates that maintain consistent behavior across different agent workflow scenarios.

Why does my prompt produce inconsistent results across different tasks?▼

Inconsistent prompt results often stem from unclear instructions or missing constraints. Systematic prompt optimization addresses this by analyzing failure patterns, restructuring instruction hierarchy, and validating refined variants against representative tasks to ensure reliable execution.

Related Skills

Explore More Software Engineering Skills→
steipetesteipete
385.7k

openai-whisper-api

Transcribe audio files into text using the OpenAI Whisper API.

Community
Basic
flatrickflatrick
1

eval-harness

Define, measure, and track AI behavior with pass@k metrics.

Community
Advanced
magnus919magnus919
40

dspy

Compile typed signatures and modules against defined metrics to optimize language model prompt programs.

Community
Advanced
Dianshu-LiaoDianshu-Liao
2

llm-evaluation

Implement LLM evaluation with automated metrics and LLM-as-judge patterns.

Community
Advanced