sadd:do-in-steps

Community

Coordinate multi-step AI tasks with sub-agents.

Authordalawwa
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Complex tasks often require decomposing a request into sequential subtasks, distributing work to specialized sub-agents, and verifying each step with an independent judge to ensure reliability and alignment.

Core Features & Use Cases

  • Task decomposition: Break down complex objectives into ordered subtasks with clear inputs/outputs.
  • Sub-agent orchestration: Dispatch focused agents with scoped context, models chosen per subtask, and controlled data flow.
  • Independent verification: Use judge agents to validate each step before proceeding, with retry loops for failures.
  • Context-aware progression: Pass concise, relevant context between steps to maintain continuity without leaking unnecessary details.
  • Workflow reliability: Enforce sequential execution, error handling, and clear pass/fail criteria for robust automation.

Quick Start

Provide a high-level task description and let the system decompose, dispatch sub-agents, and verify each step via an internal judge.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: sadd:do-in-steps
Download link: https://github.com/dalawwa/labor-methods/archive/main.zip#sadd-do-in-steps

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.