sadd-do-in-steps
CommunityOrchestrate complex tasks with AI agents.
Software Engineering#workflow automation#verification#agent#orchestration#task decomposition#llm-as-a-judge
AuthorGamezar
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill automates the execution of complex, multi-step tasks by intelligently decomposing them, assigning subtasks to specialized AI agents, and verifying each step's completion before proceeding.
Core Features & Use Cases
- Task Decomposition: Breaks down large tasks into manageable, sequential subtasks.
- Agent Orchestration: Dispatches appropriate AI agents (e.g., developer, architect) for each subtask.
- LLM-as-a-Judge Verification: Uses an independent AI to verify the correctness and integration of each step.
- Iterative Refinement: Automatically retries failed steps with feedback up to two times.
- Context Management: Passes relevant information between steps to maintain continuity.
- Use Case: Refactoring a large codebase by first updating interfaces, then implementations, then consumers, and finally tests, with each phase verified by an AI judge.
Quick Start
Use the sadd-do-in-steps skill to refactor the user service by first updating its interface, then its implementation, and finally its consumers.
Dependency Matrix
Required Modules
None requiredComponents
scripts
💻 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/Gamezar/opencode-cek/archive/main.zip#sadd-do-in-steps Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.