Prompting

Generate dynamic prompts using Handlebars templates and TypeScript utilities.

12|Updated Aug 16, 2019

Search Tags:#prompt engineering #ai optimization #template generation #meta-prompting #handlebars #llm composition

Ready to run

npx skills add https://github.com/phatblat/dotfiles --skill prompting-phatblat

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Prompting
Source: https://github.com/phatblat/dotfiles/tree/main/.claude/skills/Prompting
Command: npx skills add https://github.com/phatblat/dotfiles --skill prompting-phatblat

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines prompt engineering by providing a robust system for dynamic prompt generation, optimization, and composition, ensuring AI interactions are efficient and effective.

Core Features & Use Cases

Meta-Prompting: Generate complex prompts programmatically using templates and standards.
Template Generation: Create reusable prompt structures for agents, workflows, and evaluations.
Prompt Optimization: Leverage best practices and research to improve AI response quality and token efficiency.
Use Case: Automatically generate a specialized agent briefing prompt by combining a standard template with specific task details and agent personality traits.

Quick Start

Use the prompting skill to render the 'Primitives/Briefing.hbs' template with provided agent and task data.

Frequently Asked Questions about Prompting

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

FAQPage Schema

How do I generate dynamic AI prompts using Handlebars templates?▼

Meta-prompting generates complex AI prompts programmatically by combining standard templates with specific task details and variables. This technique streamlines prompt engineering by automating the composition of structured, reusable prompt structures for agents and workflows.

What is meta-prompting and how does it improve LLM composition?▼

Meta-prompting improves LLM composition by applying context engineering principles and Claude 4.x best practices to programmatically assemble prompt components. This method enhances AI response quality and token efficiency through structured, template-driven generation.

Can I use YAML for prompt template data management with this system?▼

YAML parsing is required for data management alongside Handlebars templating for rendering. The system uses YAML to manage standards and structured data inputs, enabling programmatic composition of prompt variables for dynamic generation.

Does this prompt engineering approach follow Anthropic Claude best practices?▼

The prompt engineering approach adheres to Anthropic's Claude 4.x best practices and context engineering principles. It applies these standards to optimize AI response quality, ensure token efficiency, and guide dynamic prompt generation.

What's the best way to create reusable prompt structures for AI agents?▼

The best way to create reusable prompt structures is through template generation using Handlebars. By rendering standard templates with specific agent personality traits and task details, you can efficiently produce specialized agent briefings and workflows.

When do I need programmatic prompt optimization for AI interactions?▼

Programmatic prompt optimization is needed when AI interactions require improved response quality and token efficiency. It leverages best practices and research to dynamically refine prompts, ensuring effective communication with large language models.