create-meta-prompts

Generate multi-stage prompt chains with SUMMARY.md and XML metadata in .prompts.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/saxjax/saxjaxTuner --skill create-meta-prompts-saxjax
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-meta-prompts
Source: https://github.com/saxjax/saxjaxTuner/tree/main/.claude/skills/create-meta-prompts
Command: npx skills add https://github.com/saxjax/saxjaxTuner --skill create-meta-prompts-saxjax

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Create Meta-Prompts streamline the design, generation, and orchestration of multi-stage prompts for Claude-to-Claude workflows, enabling consistent provenance and structured outputs.

Core Features & Use Cases

  • Intake & inference: determine prompt purpose (Do/Plan/Research/Refine) and topic, then generate a tailored meta-prompt chain.
  • Chain detection & orchestration: automatically discover existing research/plans and chain prompts in a correct execution order.
  • Structured outputs: produce SUMMARY.md and XML metadata for downstream prompts, ensuring clear review and traceability.
  • Provenance & lineage tracking: archive completed prompts and preserve lineage for auditing and reuse.

Quick Start

Describe your task and let Create Meta-Prompts generate a ready-to-run multi-stage prompt chain in the .prompts directory.

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 prompt creation for research workflows?

Automating multi-stage Claude prompt creation involves generating a tailored meta-prompt chain that defines output locations, dependencies, and a SUMMARY.md file for quick review and traceable provenance.

What is a meta-prompt chain and how does it orchestrate Claude-to-Claude workflows?

A meta-prompt chain orchestrates Claude-to-Claude workflows by detecting existing research or plans, establishing correct execution order, and generating structured XML metadata for downstream prompt artifacts.

How do I generate prompts with structured metadata and provenance tracking?

Generating prompts with structured metadata requires configuring a skill that outputs files into a .prompts directory, preserving lineage through archived artifacts and a human-scan SUMMARY.md.

Can I use multi-stage prompts to automate task intake and execution planning?

Multi-stage prompts automate task intake by inferring prompt purpose such as Do, Plan, Research, or Refine, then generating a tailored execution orchestration chain with versioned archives.

What are the limitations of automating prompt generation for Claude-to-Claude workflows?

Automating prompt generation requires clearly defined output locations and dependencies for each artifact; workflows lacking explicit task purpose may produce incomplete execution orchestration chains.