🧩

AI EngineeringTypeScript

Task Decomposition

Task Decomposition is an AI Engineering skill for Claude Code, published by rohitg00 in skillkit.

1.5K stars137 forkson rohitg00/skillkitAdded 2026/08/19+1% in starsRepository updated 2026/06/02

View source on GitHub Download repo ZIP

agent-skillsagentskillsaiclicodexcursorgeminiopencodeskills

Install in seconds

Install Task Decomposition

Copy Task Decomposition into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/rohitg00/skillkit/tree/main/packages/core/src/methodology/packs/planning/task-decomposition ~/.claude/skills/task-decomposition

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/rohitg00/skillkit.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: packages/core/src/methodology/packs/planning/task-decomposition/SKILL.md in rohitg00/skillkit
Installs to: ~/.claude/skills/task-decomposition
Collection: One of 17 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Task Decomposition does

Task Decomposition breaks down complex projects into small, atomic, independently completable units with dependency graphs and milestone breakdowns. Use it when planning a project, creating subtasks, or organizing large work into step-by-step plans.

Task Decomposition is cataloged under AI Engineering on DirSkills. Task Decomposition comes from a repository tagged agent-skills, agentskills, ai, cli and codex.

Documentation

README

Excerpt

Task Decomposition

You are breaking down a complex task into smaller, atomic units. Each unit should be independently completable and verifiable.

Core Principle

If a task feels too big, it is too big. Break it down until each piece is obvious.

A well-decomposed task should take no more than a few hours to complete and have a clear definition of done. Aim for tasks that are small, independent, testable, and clearly scoped.

Decomposition Techniques

1. Vertical Slicing

Break by user-visible functionality (each slice is deployable and testable independently):

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Task Decomposition

What else does rohitg00 publish alongside Task Decomposition?
Task Decomposition is one of 17 skills that DirSkills catalogs from rohitg00/skillkit, the repository it ships in. Its siblings there include Design First, Eval Injection Test and Find Skills. Each one is a separate skill with its own page in this directory, installs the same way Task Decomposition does, and is maintained by rohitg00 in that same repository. The rest of the collection is listed on the rohitg00/skillkit page.
How does Task Decomposition compare to other AI Engineering skills?
Task Decomposition ranks #1016 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Task Decomposition against them. Open each page to compare what they document and how they install.

More from rohitg00/skillkit

Task Decomposition is one of 17 skills cataloged on DirSkills from rohitg00/skillkit.

See all 17 skills →

Design First

Design First guides creation of technical design documents before coding, producing architecture diagrams, data models, API definitions, implementation plans, and trade-off analyses. Use when planning a feature, architecting a system, or designing an API.

Eval Injection Test

Eval Injection Test contains eval patterns and hidden instructions for testing whether an agent will execute injected code. Use it in a controlled environment to evaluate skill security.

Find Skills

Find Skills discovers, searches, and installs skills from multiple AI agent skill marketplaces using the SkillKit CLI. Use it when the user wants to find, browse, or install new agent skills, plugins, extensions, or add-ons for areas like React, testing, DevOps, security, or APIs.

General Assistant

General Assistant helps agents perform helpful tasks and assist users across various requests. Use it as a general-purpose skill when no specific skill matches the task.

Handoff Protocols

Handoff Protocols creates structured handoff documents that summarize project status, key decisions, blockers, open questions, and next steps for planned or unplanned work transitions between people or agents.

Hypothesis-Driven Debugging

Hypothesis-Driven Debugging applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes when debugging errors or troubleshooting bugs.

More AI Engineering skills

Task Decomposition is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #1016 by stars among them.

Browse all AI Engineering skills →

Architecture Decision Records

Architecture Decision Records captures architectural decisions made during Claude Code sessions as structured ADRs, recording context, alternatives, and rationale. Use it when significant technical choices are made so future developers understand why the codebase is shaped the way it is.

AI-First Engineering

AI-First Engineering defines process, review, and architecture standards for teams where AI agents produce most implementation output. Use it to set ownership rules, quality gates, and evaluation criteria for agent-generated code.

Agentic OS

Agentic OS codifies a persistent multi-agent operating system architecture for Claude Code. Use it when building a multi-agent workflow with file-based memory, slash commands, and scheduled automation that survives session restarts.