create-meta-prompts

Generate structured prompts for multi-stage Claude-to-Claude workflows.

2|Updated Jul 13, 2025
One-click install
npx skills add https://github.com/krzemienski/shannon --skill create-meta-prompts-krzemienski
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-meta-prompts
Source: https://github.com/krzemienski/shannon/tree/main/skills/create-meta-prompts
Command: npx skills add https://github.com/krzemienski/shannon --skill create-meta-prompts-krzemienski

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires askuserquestion, file, task, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the creation of structured, optimized prompts for Claude-to-Claude workflows, streamlining research, planning, and execution stages. It's ideal for building multi-stage workflows that require precise communication and coordination between different Claude instances.

Core Features & Use Cases

  • Prompt Generation: Automatically create prompts for research, planning, and execution stages with structured outputs.
  • Workflow Coordination: Orchestrate multi-stage workflows with dependencies and validation.
  • Data Extraction: Extract structured data from research outputs for downstream processing.
  • Use Case: When building a complex Claude-to-Claude pipeline that involves research, planning, and execution stages, this Skill can generate the required prompts, ensuring that each stage has the necessary information to proceed.

Quick Start

To create a research prompt, use the command: /shannon:plan "Research the latest trends in AI."

Frequently Asked Questions about create-meta-prompts

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

FAQPage Schema
How do I generate prompts for a multi-stage Claude-to-Claude workflow?

To generate prompts for a Claude-to-Claude workflow, you automate the creation of structured outputs for research, planning, and execution stages. This ensures precise communication and coordination between different Claude instances.

What is the best way to orchestrate research and execution automation with Claude?

The best way to orchestrate research and execution automation is by generating optimized prompts that structure multi-stage workflows. This approach manages dependencies, validation, and data extraction from research outputs for downstream processing.

Can I extract structured data from research outputs for downstream Claude processing?

Yes, you can extract structured data from research outputs for downstream processing. By generating coordinated prompts, each execution stage receives the necessary structured information to proceed automatically.

Does this prompt generation approach support dependencies and validation across stages?

Yes, this prompt generation approach supports dependencies and validation across workflow stages. It structures Claude-to-Claude pipelines to ensure each phase validates inputs before passing structured data to the next execution step.

Do I need specific dependencies to coordinate multi-stage Claude workflows?

You need specific dependencies like askuserquestion, file, and task components to coordinate multi-stage Claude workflows. These components facilitate user input, file operations, and task execution automation across the pipeline stages.