planning-and-task-breakdown

Breaks specifications into ordered, verifiable tasks with acceptance criteria and checkpoints.

2|Updated Jul 6, 2026
One-click install
npx skills add https://github.com/NAMEWTA/learning-open-code --skill planning-and-task-breakdown-namewta
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: planning-and-task-breakdown
Source: https://github.com/NAMEWTA/learning-open-code/tree/main/translator/open-ai-skills/addyosmani-agent-skills/skills/planning-and-task-breakdown
Command: npx skills add https://github.com/NAMEWTA/learning-open-code --skill planning-and-task-breakdown-namewta

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Large or vague implementation requests cause agents to produce disorganized code and unfinished work. This Skill turns a specification or clear requirement into a written plan of small, verifiable tasks with acceptance criteria, dependency ordering, and checkpoints, so implementation stays on track. ## Core Features & Use Cases - Structured Planning Workflow: Read-only planning mode that maps dependencies, identifies risks, and produces a plan document saved to tasks/plan.md plus a task list in tasks/todo.md. - Vertical Slice Task Design: Splits work into end-to-end feature slices (schema + API + UI) rather than horizontal layers, with task sizing guidance from XS to XL and rules for when to split further. - Checkpoints and Parallelization: Defines verification checkpoints every 2-3 tasks, orders high-risk work first, and identifies which tasks can run in parallel across agents or sessions. - Use Case: Given a spec for a user authentication feature, produce a phased plan where Task 1 delivers account creation end-to-end, Task 2 delivers login, each with testable acceptance criteria and explicit dependencies. ## Quick Start Ask the agent to read the feature specification and create an implementation plan with ordered tasks, acceptance criteria, and checkpoints saved to tasks/plan.md and tasks/todo.md.

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 tasks for an AI coding agent?▼

Map the dependency graph first, then split work into vertical slices where each task delivers one working end-to-end feature path. Give every task acceptance criteria, verification steps, and a size estimate, keeping tasks to about five files or fewer.

What is vertical slicing in task breakdown?▼

Vertical slicing builds one complete feature path at a time, covering schema, API, and UI together, instead of building the entire database, then all endpoints, then all UI. Each slice delivers testable functionality on its own.

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

Tasks of size S (1-2 files) or M (3-5 files) work best. Split any task that needs more than one focused session, touches multiple independent subsystems, has more than three acceptance criteria bullets, or contains the word 'and' in its title.

When should I not use a formal task breakdown?▼

Skip it for single-file changes with obvious scope, or when the specification already contains clearly defined tasks. Writing a plan for trivial work adds overhead without reducing risk.

Which tasks can run in parallel across multiple agents?▼

Independent feature slices, tests for completed features, and documentation can run in parallel. Database migrations, shared state changes, and dependency chains must run sequentially, and features sharing API contracts need the contract defined first.