One-click install
npx skills add https://github.com/MichaelSolati/mkai --skill prompt-master-michaelsolati
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prompt-master
Source: https://github.com/MichaelSolati/mkai/tree/main/profiles/productivity/skills/prompt-master
Command: npx skills add https://github.com/MichaelSolati/mkai --skill prompt-master-michaelsolati

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill eliminates the wasted time and API credits caused by vague, poorly structured prompts that require multiple re-prompts to get the desired output from any AI tool, ensuring you get the right result on the first attempt.

Core Features & Use Cases

  • Tool-Specific Prompt Generation: Creates optimized prompts for 30+ AI tools including LLMs (Claude, ChatGPT, Gemini), coding agents (Claude Code, Cursor, Copilot), image/video generators (Midjourney, Stable Diffusion, Sora), and workflow automation tools (Zapier, Make).
  • Automatic Failure Pattern Fixing: Silently detects and corrects 35 common credit-killing prompt mistakes like vague task verbs, missing scope boundaries, and incorrect template usage for the target tool.
  • Long-Session Context Retention: Includes a memory block system that carries forward prior project decisions and constraints so the AI never contradicts earlier work in extended conversations.
  • Use Case Example: If you need a prompt for Claude Code to build a React landing page matching Notion's design, the skill will generate a scoped prompt with exact hex codes, animation specs, and stop conditions so it works on the first try with no extra re-prompts.

Quick Start

Use the prompt-master skill to write an optimized prompt for Midjourney to generate a photorealistic samurai standing in the rain at night with neon-lit cobblestone streets.

Frequently Asked Questions about prompt-master

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

FAQPage Schema
How do I write a prompt that gets the right output from AI on the first try?

To get the right output first try, you need prompt engineering that uses scoped task verbs, explicit boundaries, and tool-specific templates. This eliminates vague instructions and prevents the multiple re-prompts that drain API credits and time.

Why does my AI coding agent ignore earlier constraints during long sessions?

AI coding agents ignore earlier constraints during long sessions due to context loss. Implementing a context retention memory block carries forward prior project decisions and scope boundaries, preventing the AI from contradicting earlier work.

Does prompt engineering work for both text LLMs and image generators?

Yes, prompt engineering works for both text LLMs and image generators. Tool-specific prompt generation optimizes inputs for various platforms by applying distinct templates and pattern fixes tailored to each tool's processing logic.

What is the best way to stop wasting API credits on vague AI prompts?

The best way to stop wasting API credits on vague AI prompts is to apply automatic failure pattern fixing. This process detects and corrects 35 common prompt mistakes like missing scope boundaries and incorrect template usage before submission.

Can I use optimized prompts for workflow automation platforms?

Yes, you can use optimized prompts for workflow automation platforms. The prompt generation process supports over 30 AI tools, including workflow automation platforms like Zapier and Make, ensuring precise automated triggers and actions.

How do I generate a prompt for Claude Code to build a React landing page?

To generate a prompt for Claude Code to build a React landing page, you must define exact specifications like hex codes, animation specs, and stop conditions. This scoped approach ensures the coding agent completes the task without requiring re-prompts.