agentsclimarketplace

Atomic decomposition

Skill Mark393295827/house-maint-ai/skills/atomic-decomposition

MECE+ methodology for breaking problems into independently-solvable atomic tasksFrom its SKILL.md

Install
npx -y skills add Mark393295827/house-maint-ai --skill atomic-decomposition

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.7 KB, as published. Nobody here has run it

Atomic Decomposition Skill

Break complex problems into atomic, AI-solvable units with dependency tracking.

MECE+ Principles

PrincipleDescription
Mutually ExclusiveNo overlapping responsibilities
Collectively ExhaustiveComplete coverage of the problem
AtomicIndivisible units of work
IndependentSolvable without coordination

Decomposition Template

problem: "[Problem statement]"

atomic_tasks:
  - id: T1
    action: "[Verb] [Object]"
    input: "[What's needed]"
    output: "[What's produced]"
    agent: "[Assigned agent]"
    deps: []
    
  - id: T2
    deps: [T1]
    # ...

Validation Checklist

Each atomic task must satisfy:

  • Single responsibility (one action verb)
  • Clear input/output contract
  • No implicit dependencies
  • Testable completion criteria
  • < 100 word description

Dependency Graph Generation

graph LR
    subgraph "Parallel Group 1"
        T1[Task 1]
        T2[Task 2]
    end
    subgraph "Sequential"
        T3[Task 3]
    end
    T1 --> T3
    T2 --> T3

Common Patterns

Feature Implementation

Analyze → Design → Implement → Test → Document

Bug Fix

Reproduce → Diagnose → Fix → Verify → Regress

Refactoring

Audit → Plan → Extract → Transform → Validate

Usage

Called by manager-agent during objective decomposition:

skill: atomic-decomposition
input:
  objective: "[User goal]"
  constraints: "[Limitations]"
output:
  tasks: [atomic task list]
  graph: [dependency mermaid]

Keep looking

Skills are one crate of 608,475. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.