What is the purpose of the generated SUMMARY.md?

While the primary outputs are optimized for AI parsing, the SUMMARY.md provides a human-readable overview of actionable takeaways, decisions made, and blockers found.

What is a Claude-to-Claude pipeline?

It is a workflow where the output of one Claude prompt is specifically structured with XML and metadata to be consumed and processed by a subsequent Claude prompt, reducing errors in multi-step tasks.

Where are the prompts and artifacts stored?

All prompts, archived versions, and outputs are organized within a standardized .prompts/ directory, categorized by topic and purpose for easy tracking.

How does this skill handle task dependencies?

It scans prompts for file references to build a dependency graph, automatically determining if prompts should be executed sequentially or in parallel.

Meta-Prompt Pipeline Architect

Name: Meta-Prompt Pipeline Architect
Author: utahdws

byutahdws

0•

Productivity & Workflow

Automates the creation and execution of structured multi-stage Claude-to-Claude pipelines for research, planning, and implementation.

This skill streamlines complex AI workflows by generating optimized meta-prompts designed for multi-stage pipelines. It manages the entire lifecycle of a task—from gathering requirements and detecting dependencies to executing sequential or parallel prompts and generating human-readable summaries. By enforcing structured XML outputs and a clear folder hierarchy in the .prompts directory, it ensures high-quality Claude-to-Claude communication while maintaining a transparent audit trail of the reasoning process for developers.

Key Features

010 GitHub stars

02XML-structured outputs optimized for efficient Claude-to-Claude parsing

03Automated SUMMARY.md generation for quick human scanning of AI outputs

04Standardized folder structure for clear prompt provenance and chain detection

05Automated dependency-aware execution engine for sequential or parallel tasks

06Multi-stage workflow generation (Research, Plan, Implement, Refine)

Use Cases

01Creating high-fidelity documentation pipelines with automated verification and refinement steps

02Building complex features requiring distinct research and architectural planning phases

03Automating multi-step code refactoring where one agent analyzes and another implements

Key Features

010 GitHub stars

02XML-structured outputs optimized for efficient Claude-to-Claude parsing

03Automated SUMMARY.md generation for quick human scanning of AI outputs

04Standardized folder structure for clear prompt provenance and chain detection

05Automated dependency-aware execution engine for sequential or parallel tasks

06Multi-stage workflow generation (Research, Plan, Implement, Refine)

Use Cases

01Creating high-fidelity documentation pipelines with automated verification and refinement steps

02Building complex features requiring distinct research and architectural planning phases

03Automating multi-step code refactoring where one agent analyzes and another implements