planning-and-task-breakdown

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

Updated Apr 6, 2026
One-click install
npx skills add https://github.com/QT-7274/dotfiles --skill planning-and-task-breakdown-qt-7274
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: planning-and-task-breakdown
Source: https://github.com/QT-7274/dotfiles/tree/main/planning-and-task-breakdown
Command: npx skills add https://github.com/QT-7274/dotfiles --skill planning-and-task-breakdown-qt-7274

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Large or vague work items cause agents and developers to produce tangled, unreliable implementations. This Skill turns a spec or clear requirements into small, ordered tasks with explicit acceptance criteria, verification steps, and dependency mapping. ## Core Features & Use Cases - Structured Planning Process: Read-only plan mode, dependency graph mapping, and vertical slicing so each task delivers working, testable functionality. - Task Templates and Sizing: A standard task format with acceptance criteria, verification commands, dependencies, and sizing guidelines (XS through XL) that force oversized work to be split. - Flexible Output Targets: Writes plans to tasks/plan.md and task lists to tasks/todo.md by default, or maps tasks onto external trackers like GitHub Issues, Jira, or Linear, with safeguards against overwriting incomplete plans. - Use Case: Given a spec for a user authentication feature, produce a plan document plus an ordered checklist of tasks (schema, API, UI slices) with checkpoints after each phase. ## Quick Start Ask the agent to read the attached spec and break the work into an ordered task list with acceptance criteria 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 spec into implementable tasks?▼

Map the dependency graph first, then slice vertically so each task delivers one complete feature path across schema, API, and UI. Write each task with acceptance criteria, verification steps, dependencies, and files likely touched.

What is vertical slicing in task breakdown?▼

Vertical slicing builds one complete feature path at a time, such as user registration end to end, instead of building all database, then all API, then all UI layers. Each slice leaves the system in a working, testable state.

How big should a single implementation task be?▼

Tasks should be Small (1-2 files) or Medium (3-5 files). Anything touching 5 or more files, spanning two subsystems, or needing more than three acceptance criteria bullets should be broken down further.

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

Yes. If project 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, and note the tracker in tasks/plan.md.

When should I not use a formal task breakdown process?▼

Skip it for single-file changes with obvious scope or when the spec already contains well-defined tasks. The planning overhead only pays off when work is large, vague, parallelized, or has non-obvious ordering.

What happens if a tasks/plan.md file 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.