AI & ML

Execute And Judge Loop

Single-task execution with LLM-as-Judge verification in an iterative loop, supporting auto-retry and strict orchestrator role separation

AuthorNeoLabHQ

Version1.0.0

LicenseMIT

Token count~565

UpdatedJun 5, 2026

Install

Quick install

via npx skills · works with 57+ agents

npx skills add https://github.com/NeoLabHQ/context-engineering-kit/tree/master/plugins/sadd/skills/do-and-judge

Or pick agent:

npx skills add NeoLabHQ/context-engineering-kit --skill "Execute and Judge Loop" --agent claude-code

npx skills add NeoLabHQ/context-engineering-kit --skill "Execute and Judge Loop" --agent cursor

npx skills add NeoLabHQ/context-engineering-kit --skill "Execute and Judge Loop" --agent codex

npx skills add NeoLabHQ/context-engineering-kit --skill "Execute and Judge Loop" --agent opencode

npx skills add NeoLabHQ/context-engineering-kit --skill "Execute and Judge Loop" --agent github-copilot

npx skills add NeoLabHQ/context-engineering-kit --skill "Execute and Judge Loop" --agent windsurf

More install options

Shorthand — useful for multi-skill repos:

npx skills add NeoLabHQ/context-engineering-kit --skill "Execute and Judge Loop"

Manual — clone the repo and drop the folder into your agent's skills directory:

git clone https://github.com/NeoLabHQ/context-engineering-kit.git

cp -r context-engineering-kit/plugins/sadd/skills/do-and-judge ~/.claude/skills/

How to use: Once installed, ask your agent to "use the Execute and Judge Loop skill" or describe what you want (e.g. "Single-task execution with LLM-as-Judge verification in an iterative loop, suppo"). Requires Node.js 18+.

Execute and Judge Loop

Single-task execution with LLM-as-Judge verification in an iterative loop, supporting auto-retry and strict orchestrator role separation

What is it?
Single-task execution with LLM-as-Judge verification in an iterative loop, supporting auto-retry and strict orchestrator role separation Built for use cases involving execute-verify, llm-as-judge, retry-loop, quality-gate, orchestration.

How to use it?

Install this skill in your Claude environment to enhance execute and judge loop capabilities. Once installed, Claude will automatically apply the skill's guidelines when relevant tasks are detected. You can also explicitly invoke it by referencing its name in your prompts.

The full source and documentation is available on GitHub.

Key Features

Single-task execution with LLM-as-Judge verification in an iterative loop, supporting auto-retry and strict orchestrator role separation
Seamless integration with Claude's development workflow
Comprehensive guidelines and best practices for execute and judge loopView on GitHub

GitHub Stats

StarsForksLast UpdateAuthorNeoLabHQLicenseGPL-3.0Version1.0.0

Features

Related Skills

Agent Evaluation Framework

Comprehensive Claude Code agent evaluation framework with multi-dimensional scoring, LLM-as-Judge mode, and research-backed performance variance analysis

433NeoLabHQAI & MLDeveloper Tools00

Self-Reflection Framework

Iterative self-improvement system with task complexity grading, strict quality gatekeeper role, confidence thresholds, and verification checklists

433NeoLabHQAI & MLDeveloper Tools00

Multi-Perspective Critique

Multi-perspective review system using Multi-Agent Debate and LLM-as-Judge patterns with 3 specialized judges, debate rounds, and consensus building

433NeoLabHQAI & MLDeveloper Tools00

---

Source: https://github.com/NeoLabHQ/context-engineering-kit/tree/master/plugins/sadd/skills/do-and-judge
Author: NeoLabHQ
License: https://www.gnu.org/licenses/gpl-3.0.html
GitHub Stars: 433
Tags: execute-verify, llm-as-judge, retry-loop, quality-gate, orchestration

SKILL.md source

---
name: Execute and Judge Loop
description: Single-task execution with LLM-as-Judge verification in an iterative loop, supporting auto-retry and strict orchestrator role separation
---

# Execute and Judge Loop

Single-task execution with LLM-as-Judge verification in an iterative loop, supporting auto-retry and strict orchestrator role separation

What is it?
Single-task execution with LLM-as-Judge verification in an iterative loop, supporting auto-retry and strict orchestrator role separation Built for use cases involving execute-verify, llm-as-judge, retry-loop, quality-gate, orchestration.

## How to use it?
Install this skill in your Claude environment to enhance execute and judge loop capabilities. Once installed, Claude will automatically apply the skill's guidelines when relevant tasks are detected. You can also explicitly invoke it by referencing its name in your prompts.

The full source and documentation is available on GitHub.

## Key Features

* Single-task execution with LLM-as-Judge verification in an iterative loop, supporting auto-retry and strict orchestrator role separation
* Seamless integration with Claude's development workflow
* Comprehensive guidelines and best practices for execute and judge loopView on GitHub

### GitHub Stats
StarsForksLast UpdateAuthorNeoLabHQLicenseGPL-3.0Version1.0.0

### Categories
AI & MLDeveloper Tools

### Tags
execute-verifyllm-as-judgeretry-loopquality-gateorchestration

### Features

## Related Skills
More from AI & ML

### Agent Evaluation Framework
Comprehensive Claude Code agent evaluation framework with multi-dimensional scoring, LLM-as-Judge mode, and research-backed performance variance analysis

433NeoLabHQAI & MLDeveloper Tools00

### Self-Reflection Framework
Iterative self-improvement system with task complexity grading, strict quality gatekeeper role, confidence thresholds, and verification checklists

433NeoLabHQAI & MLDeveloper Tools00

### Multi-Perspective Critique
Multi-perspective review system using Multi-Agent Debate and LLM-as-Judge patterns with 3 specialized judges, debate rounds, and consensus building

433NeoLabHQAI & MLDeveloper Tools00

---

**Source**: https://github.com/NeoLabHQ/context-engineering-kit/tree/master/plugins/sadd/skills/do-and-judge
**Author**: NeoLabHQ
**License**: https://www.gnu.org/licenses/gpl-3.0.html
**GitHub Stars**: 433
**Tags**: execute-verify, llm-as-judge, retry-loop, quality-gate, orchestration

AI & ML