Help us improve
Share bugs, ideas, or general feedback.
From basics
Creates, reviews, and optimizes prompts for AI like Claude and GPT using genius intern framework, prompt types, and best practices.
npx claudepluginhub nityeshaga/claude-code-essentials --plugin basicsHow this skill is triggered — by the user, by Claude, or both
Slash command
/basics:prompt-engineerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill helps create high-quality prompts and instructions for AI systems by treating AI as a genius human teammate who needs clear, context-rich communication.
Generates optimized, production-grade prompts for LLMs like Claude, GPT, Gemini using frameworks such as RTF, Chain of Thought, RISEN. Activates on requests to create, improve, or optimize prompts.
Crafts or updates LLM prompts from first principles by discovering goals, constraints, and context through targeted questions. Use for new prompts, updates, or reviews.
Rewrites user requests into detailed, structured prompts optimized for AI model consumption. Useful when users explicitly ask for prompt improvement or engineering.
Share bugs, ideas, or general feedback.
This skill helps create high-quality prompts and instructions for AI systems by treating AI as a genius human teammate who needs clear, context-rich communication.
This skill is built on two foundational principles:
Modern AI models have both high intelligence and high emotional intelligence. They don't need tricks or "prompt engineering hacks"—they need what any smart remote teammate needs: clear written communication with sufficient context.
This skill includes three core reference documents. Read them in full as needed:
Writing for AI Teammates - Core philosophy covering:
Load this file at the start of every prompt creation task. It's your primary reference.
Prompt Framework - Comprehensive guide covering:
Always load read this detailed framework to understand best practices based on how Anthropic writes their prompts.
GPT-5 Prompting Guide - GPT-5-specific patterns:
Only load this file if the user explicitly mentions they're targeting GPT-5, OpenAI models, or asks for GPT-5 optimization after seeing the initial draft.
When the user asks for help with a prompt, quickly assess:
Type of prompt needed:
Available context:
Be smart about asking questions. Ask if:
Don't ask if:
Load the Prompt Framework reference first, then:
Choose the right structure based on prompt type:
Apply universal principles:
Avoid anti-patterns:
Always create the prompt as a markdown file.
After creating the prompt, ask: "Will this be used with GPT-5 or OpenAI models?"
If yes, you MUST load the GPT-5 Prompting Guide and perform a revision pass:
Official GPT-5 prompting guide
You're not doing "prompt engineering"—you're helping someone communicate clearly with an intelligent teammate. Focus on clarity, context, and decisiveness. Trust the AI to be smart; give them what they need to be effective in your specific context.