planning-and-task-breakdown
This skill provides a structured framework for decomposing complex software development projects into small, verifiable tasks. It guides agents through planning, dependency mapping, vertical slicing, and task documentation to ensure reliable implementation.
Is planning-and-task-breakdown safe to install?
Review before installing: our audit of planning-and-task-breakdown's source files found 2 shell commands, 0 external URLs, file reads and writes (medium risk). Every command and URL listed appears verbatim in the skill's source. The skill requires writing files to the local filesystem, specifically creating and updating tasks/plan.md and tasks/todo.md.
How we audit skills: our security review methodology.
Who is this skill for?
AI agents and developers who need to break down large or vague project requirements into manageable, testable units of work.
What can you do with it?
- Breaking down large or vague project specifications into implementable units
- Mapping dependencies for complex software features
- Communicating project scope to human stakeholders
- Organizing parallel work across multiple agents or sessions
- Establishing verification checkpoints for long-running development tasks
How good is this skill?
Quality score: 5/10. The skill provides clear, actionable templates and specific guidelines for task sizing and dependency management. It effectively addresses common pitfalls in agentic workflows.
What does the skill file contain?
# Planning and Task Breakdown ## Overview Decompose work into small, verifiable tasks with explicit acceptance criteria. Good task breakdown is the difference between an agent that completes work reliably and one that produces a tangled mess. Every task should be small enough to implement, test, and verify in a single focused session. ## When to Use - You have a spec and need to break it into implementable units - A task feels too large or vague to start - Work needs to be parallelized across multiple agents or sessions - You need to communicate scope to a human - The implementation order ...
Frequently asked questions
Where does the agent save the output?
The agent saves the implementation plan to tasks/plan.md and the task list to tasks/todo.md.
How should an agent handle tasks that are too large?
If a task is classified as Large (L) or larger, the agent must break it down into smaller, more manageable tasks.
What is the recommended implementation order?
Implementation should follow the dependency graph bottom-up, building foundations before higher-level components.
Should the agent write code during the planning phase?
No, the planning phase is strictly read-only. The agent must not write code until the plan is complete.
Related skills
brainstorming
256.4KDevelopers and project managers who need to define requirements, architecture, and design for software projects before writing code
A structured brainstorming framework that guides users through project exploration, design proposal, and specification before implementation. It enforces a strict design-first workflow, requiring user approval for designs and documentation before transitioning to the writing-plans skill.
simple
221.4KDevelopers and project managers who need a fast, lightweight decision-making process for feature design or component creation
A structured brainstorming framework for architectural and creative tasks that guides users from discovery to decision-making through a defined process flow.
writing-plans
174.7KSoftware engineers and AI agents tasked with implementing complex features from specifications
The writing-plans skill generates structured, task-based implementation plans for software development projects. It enforces a specific markdown format that includes architecture, tech stack, global constraints, and granular, test-driven development steps for each task.
repo-intake-and-plan
139.8KAI agents performing repository-based research and reproduction tasks
The repo-intake-and-plan skill scans repositories to identify project structure and documented commands. It classifies tasks into inference, evaluation, and training categories to generate a reproduction plan for an orchestrator.