planning-and-task-breakdown

Decomposes specifications into ordered, verifiable implementation tasks with acceptance criteria.

Updated Aug 22, 2026
One-click install
npx skills add https://github.com/MSC72m/DevForge --skill planning-and-task-breakdown-msc72m
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: planning-and-task-breakdown
Source: https://github.com/MSC72m/DevForge/tree/main/skills/planning-and-task-breakdown
Command: npx skills add https://github.com/MSC72m/DevForge --skill planning-and-task-breakdown-msc72m

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Large or vague work items cause agents and developers to produce tangled, incomplete implementations. This Skill turns a spec or clear requirements into small, ordered tasks with explicit acceptance criteria, verification steps, and checkpoints so work can be executed and reviewed reliably. ## Core Features & Use Cases - Dependency-aware task ordering: Maps the dependency graph and slices work vertically so each task delivers working, testable functionality. - Structured task format: Every task includes acceptance criteria, verification commands, dependencies, files likely touched, and a size estimate (XS through XL). - Plan and task list outputs: Writes a plan document to tasks/plan.md and a checklist to tasks/todo.md, or maps tasks onto an external tracker like GitHub Issues, Jira, or Linear. - Use Case: Given a spec for a task management app, produce a phased plan where Task 1 is user registration (schema + API + UI), Task 2 is login, and checkpoints verify tests and builds after every phase. ## Quick Start Ask the agent to read the spec and break the work into an ordered task list saved to tasks/todo.md with acceptance criteria and verification steps for each task.

Frequently Asked Questions about planning-and-task-breakdown

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

FAQPage Schema
How do I break a large feature into implementable tasks?▼

Map the dependency graph first, then slice vertically so each task delivers one complete working feature path rather than a horizontal layer. Give every task acceptance criteria, verification steps, dependencies, and a size estimate.

What is vertical slicing in task breakdown?▼

Vertical slicing builds one complete feature path at a time, such as registration covering schema, API, and UI together. It avoids horizontal slicing where the entire database, then all endpoints, then all UI are built separately and only connected at the end.

How big should a single task be for an AI agent?▼

Tasks should be Small (1-2 files) or Medium (3-5 files), completable in one focused session. Anything Large (5-8 files) or bigger should be broken down further, especially if the title contains 'and' or touches multiple subsystems.

Can tasks be tracked in GitHub Issues or Jira instead of a markdown file?▼

Yes. If the project's agent rules or the user designate an external tracker, create one tracker item per task with acceptance criteria in the body and dependencies via the tracker's linking mechanism. Note the tracker in tasks/plan.md so future sessions know where to look.

When should I not write a task breakdown plan?▼

Skip planning for single-file changes with obvious scope, or when the spec already contains well-defined tasks. Planning adds value when work is large, vague, parallelizable, or has non-obvious implementation order.

What happens if tasks/plan.md already exists with unchecked tasks?▼

The Skill never overwrites an incomplete plan. If it is the same work being revised, update in place; if it is different work, stop and ask the user, since unchecked tasks may be mid-build in another session.