sub-agent-decompose-worker-review — sub-agent-decompose-worker-review install sub-agent-decompose-worker-review, MB-migration, community, sub-agent-decompose-worker-review install, ide skills, sub-agent-decompose-worker-review for developers, Claude Code, Cursor, Windsurf

v1.0.0
GitHub

About this Skill

Ideal for Advanced AI Agents requiring task decomposition, automated execution, and review capabilities for streamlined workflow optimization. sub-agent-decompose-worker-review is a pipeline automation skill that decomposes tasks, executes them, and reviews the results using a chain of three agents: task-decomposer, task-worker, and reviewer.

Features

Decomposes tasks into subtasks with order and readiness criteria using the task-decomposer agent
Executes subtasks with minimal safe changes and adherence to main.m rules using the task-worker agent
Supports separate execution of each step in the pipeline
Allows for analysis of codebases and decomposition of tasks into manageable parts
Enables review of task execution results for quality assurance
Utilizes a chain of three agents for automated task management

# Core Topics

sub-agent-decompose-worker-review install sub-agent-decompose-worker-review for developers
bagrinsergiu bagrinsergiu
[0]
[0]
Updated: 3/2/2026

Agent Capability Analysis

The sub-agent-decompose-worker-review skill by bagrinsergiu is an open-source community AI agent skill for Claude Code and other IDE workflows, helping agents execute tasks with better context, repeatability, and domain-specific guidance. Optimized for sub-agent-decompose-worker-review install, sub-agent-decompose-worker-review for developers.

Ideal Agent Persona

Ideal for Advanced AI Agents requiring task decomposition, automated execution, and review capabilities for streamlined workflow optimization.

Core Value

Empowers agents to decompose tasks into sub-tasks with defined order and readiness criteria, execute them with minimal safe changes, and review code quality, leveraging pipeline sub-agents like Decomposer, Worker, and Reviewer, and integrating with codebases for improved development efficiency.

↓ Capabilities Granted for sub-agent-decompose-worker-review

Decomposing complex tasks into manageable sub-tasks with defined workflows
Automating code execution with the Worker agent for minimal safe changes
Reviewing code quality with the Reviewer agent for improved development standards

! Prerequisites & Limits

  • Requires separate commands or contexts for each sub-agent step
  • Dependent on the functionality of the Decomposer, Worker, and Reviewer sub-agents
Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

sub-agent-decompose-worker-review

Install sub-agent-decompose-worker-review, an AI agent skill for AI agent workflows and automation. Works with Claude Code, Cursor, and Windsurf with...

SKILL.md
Readonly

Pipeline суб-агентов: Decomposer → Worker → Reviewer

Три агента работают по цепочке. Каждый шаг можно запускать отдельно (отдельная команда/контекст).

Порядок запуска

ШагАгентДействие
1task-decomposerПолучает задачу, анализирует кодовую базу, декомпозирует в подзадачи с порядком и критериями готовности.
2task-workerПолучает подзадачи (или одну задачу) и выполняет их: минимальные безопасные изменения, соблюдение правил main.mdc.
3work-reviewerПроверяет результат работы воркера: корректность, архитектура, стиль, полнота.

После шага 3 возможен цикл исправлений: если ревьювер нашёл проблемы → передать замечания воркеру → воркер вносит правки → снова запустить work-reviewer. Повторять до «принято» или до разумного лимита раундов (например, 3).

Детали по шагам

1. task-decomposer

  • Вход: формулировка задачи (от пользователя или из предыдущего контекста).
  • Выход: список подзадач с зависимостями, порядком выполнения и критериями готовности; контекст анализа; неясности и риски.
  • Когда вызывать: задача сложная, большая или размытая — сначала декомпозиция, потом реализация.

2. task-worker

  • Вход: одна подзадача или упорядоченный список подзадач (результат decomposer); при цикле исправлений — замечания от work-reviewer.
  • Выход: изменения в коде/артефактах; кратко: что изменено, зачем, минимальный diff.
  • Когда вызывать: после decomposer для реализации; после reviewer — для исправлений по замечаниям.

3. work-reviewer

  • Вход: изменённый код, документы или артефакты после работы task-worker.
  • Выход: краткий вывод; замечания по приоритету (критичные / важные / рекомендации); конкретные предложения правок.
  • Когда вызывать: после завершения работы воркера по задаче или подзадаче.

Цикл исправлений (fix loop)

  1. work-reviewer выдал замечания (критичные или важные).
  2. Пользователь (или оркестратор) передаёт эти замечания в task-worker как новую «задачу на исправление».
  3. task-worker вносит правки.
  4. Снова запускается work-reviewer по обновлённому коду.
  5. Повторять шаги 2–4, пока ревью не пройдено или не достигнут лимит раундов.

Правила для оркестрации

  • Каждый агент лучше запускать в своём контексте (одна команда = один агент), чтобы не смешивать роли.
  • Передавать между шагами: результат decomposer → worker; результат worker (дифф/файлы) → reviewer; вывод reviewer → worker при fix loop.
  • Не пропускать decomposer для сложных задач: сначала разбивка, потом выполнение.
  • Язык: если пользователь общается на русском — ответы и артефакты можно на русском; task-worker часто на английском в коде и коммитах — по конвенциям проекта.

Краткий чеклист

  • Задача передана в task-decomposer, получены подзадачи и порядок.
  • task-worker выполнил подзадачи (по одной или батчем по договорённости).
  • work-reviewer проверил результат.
  • Если есть замечания — передать воркеру, повторить правки и ревью (fix loop).
  • Ревью пройдено или достигнут лимит раундов.

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is sub-agent-decompose-worker-review?

Ideal for Advanced AI Agents requiring task decomposition, automated execution, and review capabilities for streamlined workflow optimization. sub-agent-decompose-worker-review is a pipeline automation skill that decomposes tasks, executes them, and reviews the results using a chain of three agents: task-decomposer, task-worker, and reviewer.

How do I install sub-agent-decompose-worker-review?

Run the command: npx killer-skills add bagrinsergiu/MB-migration/sub-agent-decompose-worker-review. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for sub-agent-decompose-worker-review?

Key use cases include: Decomposing complex tasks into manageable sub-tasks with defined workflows, Automating code execution with the Worker agent for minimal safe changes, Reviewing code quality with the Reviewer agent for improved development standards.

Which IDEs are compatible with sub-agent-decompose-worker-review?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for sub-agent-decompose-worker-review?

Requires separate commands or contexts for each sub-agent step. Dependent on the functionality of the Decomposer, Worker, and Reviewer sub-agents.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add bagrinsergiu/MB-migration/sub-agent-decompose-worker-review. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use sub-agent-decompose-worker-review immediately in the current project.

Related Skills

Looking for an alternative to sub-agent-decompose-worker-review or another community skill for your workflow? Explore these related open-source skills.

View All

widget-generator

Logo of f
f

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

flags is a Next.js feature management skill that enables developers to efficiently add or modify framework feature flags, streamlining React application development.

★ 138.4k
⑂ 0
Browser

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

★ 72.8k
⑂ 0
AI