sadd:do-and-judge

Community

Orchestrate tasks with judge verification.

Authordalawwa
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill orchestrates task execution by dispatching an implementation sub-agent, validating results with an independent judge, and iterating with feedback until success or a maximum retry limit is reached.

Core Features & Use Cases

  • Fresh context: Implementation agent works with a clean context window to avoid information leakage from prior runs.
  • External verification: A separate judge catches blind spots and provides structured feedback.
  • Feedback loop: Judge-provided issues are used to iteratively improve the outcome.
  • Quality gate: Work is not considered complete until it passes the judge score threshold or the retry limit is reached.

Quick Start

Dispatch an implementation sub-agent to complete the task and verify the result with an independent judge, retrying up to two times if needed.

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-and-judge
Download link: https://github.com/dalawwa/labor-methods/archive/main.zip#sadd-do-and-judge

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.