planning-and-task-breakdown

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

Updated Aug 11, 2026
One-click install
npx skills add https://github.com/Kunj-Sharma03/agent-contextify --skill planning-and-task-breakdown-kunj-sharma03
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: planning-and-task-breakdown
Source: https://github.com/Kunj-Sharma03/agent-contextify/tree/main/templates/skills/planning-and-task-breakdown
Command: npx skills add https://github.com/Kunj-Sharma03/agent-contextify --skill planning-and-task-breakdown-kunj-sharma03

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Large or vague work items cause agents to produce tangled, unverifiable implementations. This Skill turns a spec or clear requirements into small, ordered tasks with explicit acceptance criteria, dependencies, and checkpoints so implementation stays on track. ## Core Features & Use Cases - Structured Planning Process: Guides read-only plan mode, dependency graph mapping, and vertical slicing so each task delivers working, testable functionality. - Task Templates and Sizing: Provides a task format with acceptance criteria, verification steps, dependencies, and size guidelines (XS through XL) to keep tasks small enough for a single focused session. - Plan and Todo Outputs: Produces a plan document at tasks/plan.md and a checklist at tasks/todo.md, including phases, checkpoints, risks, and open questions. - Use Case: Given a spec for a user authentication feature, generate a phased task list covering schema, API, and UI slices with checkpoints after each phase before any code is written. ## Quick Start Ask the agent to break your feature spec into an ordered task list with acceptance criteria and save the plan 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 smaller tasks?

Map the dependency graph first, then slice vertically so each task delivers one complete feature path across schema, API, and UI. Keep tasks to 1-5 files with acceptance criteria you can state in three or fewer bullet points.

What is vertical slicing in task planning?

Vertical slicing builds one complete feature path at a time, such as user registration covering schema, API, and UI together. It contrasts with horizontal slicing, which builds all of one layer before the next and delays testable functionality.

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

Tasks should be Small (1-2 files) or Medium (3-5 files), completable in one focused session. Anything touching 5 or more files or spanning two subsystems should be broken down further.

When should I not write a task breakdown plan?

Skip formal 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, parallelized, or has unclear implementation order.

Which tasks can run in parallel across multiple agents?

Independent feature slices, tests for already-implemented features, and documentation are safe to parallelize. Database migrations, shared state changes, and dependency chains must remain sequential.