iteration-rules

Decompose features into atomic tasks and generate execution plans for developer confirmation.

3|Updated Apr 12, 2026
One-click install
npx skills add https://github.com/mauriciodelrio/delriodev-skills --skill iteration-rules
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: iteration-rules
Source: https://github.com/mauriciodelrio/delriodev-skills/tree/main/es-skills/agent-workflow/iteration-rules
Command: npx skills add https://github.com/mauriciodelrio/delriodev-skills --skill iteration-rules

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The agent follows a complete iteration workflow to decompose a feature into tasks, present a plan for developer confirmation, execute with checkpoints, handle deviations via no-drift rules, verify acceptance criteria, and close with updated context and memory.

Core Features & Use Cases

  • Task decomposition into atomic, verifiable steps ordered by dependency
  • Plan-first execution with explicit confirmation before implementation
  • Execution with per-task checkpoints and context/memory updates
  • Drift handling via no-drift rules to prevent scope creep
  • Individual acceptance criteria verification and regression checks

Quick Start

Outline and execute a full feature iteration plan, including task decomposition, plan presentation, execution with checkpoints, drift handling, acceptance criteria verification, and final context/memory updates.

Frequently Asked Questions about iteration-rules

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

FAQPage Schema
How do I decompose a feature into atomic tasks for developer execution?

Feature decomposition breaks down work into atomic, verifiable steps ordered by dependency, generating a plan for developer confirmation before execution begins.

How do I prevent scope creep during feature execution?

Drift handling prevents scope creep during feature execution by applying no-drift rules at per-task checkpoints, catching deviations before they affect backend or frontend work.

What's the best way to plan feature iterations with checkpoints?

Plan-first execution presents a full iteration plan for developer confirmation, then executes with deterministic per-task checkpoints, context updates, and memory updates across the workflow.

Can I apply task decomposition for both backend and frontend work?

Task decomposition applies across backend and frontend work, ordering atomic steps by dependency and verifying acceptance criteria for each side before closing the iteration.

Why does my feature iteration drift from the original plan?

Feature iteration drifts when deviations go unchecked, but applying no-drift rules at per-task checkpoints handles scope creep, verifies acceptance criteria, and ensures safe closure with state persistence.