create-meta-prompts

Generate structured meta-prompts for Claude-to-Claude pipelines with XML metadata.

Updated Feb 14, 2026
One-click install
npx skills add https://github.com/DYAI2025/MOD_shark-engine --skill create-meta-prompts-dyai2025
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-meta-prompts
Source: https://github.com/DYAI2025/MOD_shark-engine/tree/main/sharkengine/.claude/skills/create-meta-prompts
Command: npx skills add https://github.com/DYAI2025/MOD_shark-engine --skill create-meta-prompts-dyai2025

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This skill automates the creation and orchestration of meta-prompts designed for Claude-to-Claude pipelines. It enables structured, multi-stage workflows that can be chained with explicit dependencies and provenance.

Core Features & Use Cases

  • Reference chaining: Detects and references existing research/plans to build on prior work.
  • Dependency-aware prompts: Generates prompts that coordinate Do/Plan/Research tasks with clear execution order.
  • Structured outputs: Outputs echo XML metadata and maintain provenance under a standardized .prompts directory.
  • Provenance tracking: Each prompt has its own folder with completed artifacts for easy audit and rollback.

Quick Start

Describe the task and topic to generate a new meta-prompt chain.

Frequently Asked Questions about create-meta-prompts

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

FAQPage Schema
How do I automate Claude-to-Claude prompt chains for multi-stage workflows?

You can automate Claude-to-Claude prompt chains by generating structured meta-prompts that define objective, context, requirements, and XML metadata. This coordinates multi-stage workflows like research, plan, and implement sequences with explicit execution order.

What is a meta-prompt pipeline and when do I need dependency tracking?

A meta-prompt pipeline orchestrates sequential Claude-to-Claude tasks. You need dependency tracking when chaining multi-stage workflows, ensuring outputs from prior research or planning stages are automatically detected and referenced to maintain provenance.

How do I generate structured prompts that maintain provenance across execution stages?

Generate structured prompts that include XML metadata and place artifacts under a standardized .prompts directory. Each prompt receives its own folder for completed artifacts, ensuring easy audit, rollback, and provenance tracking across execution stages.

Can I use automated meta-prompts to coordinate research and implementation tasks?

Yes, automated meta-prompts coordinate Do, Plan, and Research tasks by generating dependency-aware instructions. This enforces a sequential execution order with an explicit completion workflow, directly linking research outputs to implementation steps.

Does generating prompt chains require manual reference linking between workflow stages?

No, generating prompt chains includes automatic reference chaining. The system detects existing research and plans to build on prior work automatically, eliminating the need for manual reference linking between workflow stages.