mthds-build

Build AI methods into validated `.mthds` bundles using the MTHDS standard.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/mthds-ai/skills --skill mthds-build
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: mthds-build
Source: https://github.com/mthds-ai/skills/tree/main/skills/mthds-build
Command: npx skills add https://github.com/mthds-ai/skills --skill mthds-build

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the creation of new AI methods using the MTHDS standard, guiding users from initial requirements to a fully structured and validated .mthds bundle.

Core Features & Use Cases

  • Guided Workflow Creation: Step-by-step assistance through 10 phases of method development.
  • Automated Structuring: Leverages the mthds-agent CLI for converting drafts into valid TOML and .mthds files.
  • Use Case: When you need to create a new AI pipeline to process customer feedback, analyze sentiment, and categorize issues, this Skill will help you define the inputs, structure the processing steps, and generate the final .mthds bundle.

Quick Start

Use the mthds-build skill to create a new AI method for summarizing user feedback.

Frequently Asked Questions about mthds-build

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

FAQPage Schema
How do I build an AI pipeline from scratch using a structured workflow?

To build an AI pipeline from scratch, this Skill guides you through requirement gathering, plan drafting, and flow design to assemble a fully structured `.mthds` bundle using the MTHDS standard.

What is a .mthds bundle and when do I need it for AI method development?

A `.mthds` bundle is a structured file format generated by the MTHDS standard to define new AI methods. You need it when creating structured AI pipelines to process inputs like customer feedback or sentiment analysis tasks.

Can I validate my AI method drafts automatically using CLI?

Yes, you can validate AI method drafts automatically using the `mthds-agent` CLI, which converts your drafts into valid TOML and `.mthds` files during the automated or interactive workflow phases.

Does the MTHDS standard support interactive method construction workflows?

The MTHDS standard supports both automatic and interactive modes for method construction, guiding users step-by-step through 10 phases of development including concept structuring and bundle assembly.

What is the best way to structure an AI method for categorizing issues?

The best way to structure an AI method for categorizing issues is using phase-based construction, which helps you define inputs, structure processing steps, and generate a validated `.mthds` bundle.

What are the limitations of using automated structuring for AI pipelines?

The automated structuring relies on the `mthds-agent` CLI for TOML conversion and bundle assembly, meaning users must align their drafts with the 10-phase MTHDS standard to avoid validation errors during the workflow.