Skip to content
Back to skills

Decompose

ASecurity

Task decomposition skill. When triggered by '/decompose', '작업 분해', 'break down this task', or '서브태스크로 나눠줘', this skill takes a complex task and recursively decomposes it into atomic, testable subtasks with tier assignments and parallelization opportunities.

  • 9 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 23, 2026
ai-agents

Security analysis

A100/100

Scanned October 23, 2026

npx -y skills add johnfkoo951/cmdspace-plugins --skill decompose --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Decompose?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Decompose
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/johnfkoo951-decompose/badge)](https://www.skillsdirectory.com/skills/johnfkoo951-decompose)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: decompose
description: >
  Task decomposition skill. When triggered by '/decompose', '작업 분해', 'break down this task',
  or '서브태스크로 나눠줘', this skill takes a complex task and recursively decomposes it
  into atomic, testable subtasks with tier assignments and parallelization opportunities.
---

# Decompose — Task Decomposition

Breaks complex tasks into atomic, executable subtasks.

## Workflow

### Step 1: Understand the Task

Read the user's request and any related files. If the task is ambiguous, use `AskUserQuestion` to clarify:

```json
{
  "questions": [
    {
      "question": "What granularity do you need?",
      "header": "Granularity",
      "options": [
        {"label": "Coarse (Recommended)", "description": "5-10 high-level subtasks, each ~1 agent session"},
        {"label": "Fine", "description": "10-30 atomic tasks, each ~1 function or file change"},
        {"label": "Sprint-sized", "description": "Grouped into workable chunks with effort estimates"}
      ],
      "multiSelect": false
    }
  ]
}
```

### Step 2: Decompose

Dispatch **planner** (Opus) to decompose the task:

1. Identify the major components of the task
2. For each component, break into subtasks
3. For each subtask, determine:
   - Description (specific and actionable)
   - Agent type and tier
   - Dependencies (what must complete first)
   - Parallel group (what can run simultaneously)
   - Estimated complexity (1-10)

### Step 3: Output Decomposition

```markdown
## Task Decomposition: [Original Task]

### Dependency Graph
```mermaid
graph TD
    A[Task 1.1] --> C[Task 2.1]
    B[Task 1.2] --> C
    C --> D[Task 3.1]
    C --> E[Task 3.2]
```

### Parallel Groups

**Group 1** (can run simultaneously):
| # | Task | Agent | Tier | Complexity |
|---|------|-------|------|------------|
| 1.1 | [Task] | [agent] | [tier] | [1-10] |
| 1.2 | [Task] | [agent] | [tier] | [1-10] |

**Group 2** (depends on Group 1):
| # | Task | Agent | Tier | Complexity |
|---|------|-------|------|------------|
| 2.1 | [Task] | [agent] | [tier] | [1-10] |

### Total Estimates
- Subtasks: [N]
- Parallel groups: [N]
- Estimated total complexity: [Sum]
- Tier distribution: Opus [N] / Sonnet [N] / Haiku [N]
```

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.