skills.rest
hupyy-labs
hupyy-labsOFFICIAL
Explore all skills by this author →
GitHub

create-meta-prompts

Generate multi-stage Claude prompts with research, planning, and implementation artifacts.

2|Updated Nov 18, 2025
Search Tags:#automation#workflow#planning#research#claude#metadata#prompt
One-click install
npx skills add https://github.com/hupyy-labs/verticalslice-smt-service --skill create-meta-prompts-hupyy-labs
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: create-meta-prompts
Source: https://github.com/hupyy-labs/verticalslice-smt-service/tree/main/.claude/skills/create-meta-prompts/skills/create-meta-prompts
Command: npx skills add https://github.com/hupyy-labs/verticalslice-smt-service --skill create-meta-prompts-hupyy-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a structured approach to creating Claude-to-Claude prompts by orchestrating research, planning, and execution prompts into a coherent, reusable workflow. It enables consistent artifact naming, metadata, and output formats to enable automated chaining and provenance.

Core Features & Use Cases

  • Structured prompt templates for research, plan, and do prompts that can be reused across projects.
  • Automated artifact organization under a .prompts directory with numbered folders to maintain provenance.
  • Dependency-aware chaining that allows multi-stage workflows where outputs feed the next step.
  • Provenance and metadata capture for downstream audit and reproducibility.

Quick Start

Provide a project goal and topic, and I will generate a complete multi-stage prompt chain ready for execution.

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 multi-stage Claude workflows with research and planning prompts?▼

Automate multi-stage Claude workflows by generating structured prompt chains that orchestrate research, planning, and implementation stages into reusable artifacts with dependency-aware chaining.

What is a Claude-to-Claude prompt chain and how does it handle metadata?▼

A Claude-to-Claude prompt chain uses XML-like metadata structures to pass research, plan, and implementation outputs between stages, enabling downstream parsing, provenance capture, and reproducibility.

How do I organize prompt artifacts to maintain provenance across automated workflows?▼

Organize prompt artifacts by storing structured outputs like research.md, plan.md, and implement.md under a numbered .prompts directory to maintain consistent provenance across automated workflows.

Can I generate structured XML outputs for downstream prompt parsing and execution?▼

Yes, you can generate XML or XML-like metadata structures specifically designed for parsing and chaining by downstream prompts during the research, planning, and implementation stages.

Do I need any external dependencies to build automated prompt generation workflows?▼

No external dependencies are required to build automated prompt generation workflows; the process relies on structured prompt templates and metadata extraction to enable internal Claude-to-Claude automation.

When should I use dependency-aware chaining for prompt automation?▼

Use dependency-aware chaining when a multi-stage workflow requires outputs from the research phase to feed directly into the planning and implementation steps for consistent artifact generation.

Related Skills

Explore More Content & Communication Skills→
b566776b566776

bmad-market-research

Define market research scope, methodology, and data sources with web-verified evidence.

Community
Advanced
emptistemptist

create-meta-prompts

Create prompts for Claude-to-Claude multi-stage workflows with XML metadata.

Community
Advanced
jinglemansweepjinglemansweep

jp-quick

Orchestrate end-to-end planning pipelines from prompt to summary.

Community
Advanced
dhruvbaldawadhruvbaldawa
31

engineering-prompts

Design structured Claude prompts with clarity, context, and XML formatting.

Community
Advanced