update-implementation-plan

Update Markdown implementation plans with new requirements and standardized task structures.

Updated Mar 8, 2026
One-click install
npx skills add https://github.com/tamago0224/kuroshio-mta --skill update-implementation-plan-tamago0224
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: update-implementation-plan
Source: https://github.com/tamago0224/kuroshio-mta/tree/main/.agents/skills/update-implementation-plan
Command: npx skills add https://github.com/tamago0224/kuroshio-mta --skill update-implementation-plan-tamago0224

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill updates existing implementation plan Markdown files to reflect new or changed requirements and transforms them into deterministic, machine-readable plans that can be executed by AI agents or humans without ambiguity.

Core Features & Use Cases

  • Machine-readable Templates: Enforces strict front matter fields, prescribed section headers, identifier prefixes (REQ-, TASK-, etc.), and naming conventions for automated validation.
  • Deterministic Task Decomposition: Converts high-level requirements into atomic phases and tasks with explicit file paths, completion criteria, and validation checks suitable for autonomous execution.
  • AI-to-AI & Human Integration: Produces outputs that are directly consumable by other AI agents or engineers for feature implementation, refactors, package upgrades, or infrastructure changes.
  • Use Case: Given an implementation plan and new requirements, generate a validated /plan/ Markdown file named per the required convention that lists phased, verifiable tasks ready for automated workers.

Quick Start

Update the implementation plan file at /plan/feature-auth-module-1.md to add REQ-002 and TASK-007 using the mandated template and validation rules.

Frequently Asked Questions about update-implementation-plan

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

FAQPage Schema
How do I update an implementation plan for AI agent execution?

To update an implementation plan for AI agent execution, the plan file must be modified to enforce explicit front matter, standardized identifier prefixes like REQ- and TASK-, and atomic phase structures. This ensures the resulting Markdown file is deterministic and machine-readable for automated validation.

What is a deterministic implementation plan in Markdown?

A deterministic implementation plan in Markdown is a machine-readable document that enforces strict front matter fields, prescribed section headers, and naming conventions. It converts high-level requirements into atomic phases and verifiable tasks with precise file paths for autonomous execution.

How do I structure Markdown implementation plans for automated validation?

You structure Markdown implementation plans for automated validation by applying standardized identifier prefixes, explicit front matter, and atomic task decomposition with precise file paths. This format allows automated workers to execute phased, verifiable tasks without ambiguity.

Can I use existing Markdown implementation plans for automated task execution?

Existing Markdown implementation plans can be used for automated task execution if they are updated to include mandated front matter, standardized identifier prefixes, and atomic phase structures. Precise file paths and completion criteria must be added for automated validation.

Why does my implementation plan fail automated validation?

Implementation plans fail automated validation when they lack explicit front matter, mandated naming conventions, or standardized identifier prefixes like REQ- and TASK-. Missing precise file paths, atomic task structures, or completion criteria also prevent deterministic machine-readable execution.

Does automated implementation plan generation work for infrastructure changes?

Automated implementation plan generation works for infrastructure changes by converting high-level requirements into atomic phases with explicit file paths and validation checks. The deterministic Markdown output is directly consumable by AI agents or engineers for infrastructure refactors.