step-by-step

Guide agents through incremental, human-approved changes with stepwise validation.

Updated Feb 24, 2026
One-click install
npx skills add https://github.com/bartolomeomueller/hr --skill step-by-step-bartolomeomueller
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: step-by-step
Source: https://github.com/bartolomeomueller/hr/tree/main/.agents/skills/step-by-step
Command: npx skills add https://github.com/bartolomeomueller/hr --skill step-by-step-bartolomeomueller

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill guides agents to make incremental, human-approved changes, preventing large overhauls and preserving human oversight.

Core Features & Use Cases

  • Enforces stepwise edits: propose the smallest change first.
  • Human-in-the-loop validation: requires human confirmation before applying each step.
  • Use cases: code reviews, document edits, design iterations.

Quick Start

Provide the smallest, human-approved change and outline the next concrete step.

Frequently Asked Questions about step-by-step

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

FAQPage Schema
How do I enforce human-in-the-loop validation for AI agent edits?

Human-in-the-loop validation for AI agent edits requires explicit human confirmation before applying each step. This approach enforces deterministic step proposals, preventing large overhauls and preserving human oversight.

What is the best way to make minimal iterative changes during collaborative coding?

The best way to make minimal iterative changes during collaborative coding is to propose the smallest change first and outline the next concrete step. This ensures changes remain incremental and human-approved.

Can I use step-by-step guidance for document editing and design workflows?

Yes, step-by-step guidance works for document editing and design workflows where changes must be incremental and reviewed. It provides non-destructive guidance for edits across these collaborative environments.

How do AI agents propose changes to prevent large overhauls in version control?

AI agents prevent large overhauls in version control by enforcing stepwise edits and requiring human confirmation before applying each step. This approach guides agents to make incremental, human-approved changes.

Does human-approved change management work with non-destructive editing?

Yes, human-approved change management works with non-destructive editing by providing deterministic step proposals and explicit human prompts. This ensures changes are incremental and reviewed before application.