sadd:judge
CommunityLaunch a focused sub-agent judge for evaluation.
Authordalawwa
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill enables rapid, isolated evaluation of work produced during a conversation by deploying a sub-agent judge that provides structured, evidence-based feedback and scoring.
Core Features & Use Cases
- Context Isolation: Judge runs in a fresh context to prevent prior session biases from influencing assessment.
- Evidence-Based Scoring: Every score requires citations from the work (file locations and line references).
- Multi-Dimensional Rubric: Uses weighted criteria with clear level descriptions to guide evaluation.
- Self-Verification: Includes dynamic verification questions and documented adjustments.
- Report-Only Output: Findings are provided without making automatic changes.
Quick Start
Launch the judge sub-agent to evaluate the latest work produced in the conversation.
Dependency Matrix
Required Modules
None requiredComponents
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:judge Download link: https://github.com/dalawwa/labor-methods/archive/main.zip#sadd-judge 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 471,000+ vetted skills library on demand.