Walllmat

Judge — Development skill for Claude Code

Development community

Evaluate the execution quality of a skill or agent.

How to install Judge

Installs to ~/.claude/skills/walllmat-verdict-judge/SKILL.md

Terminal
mkdir -p ~/.claude/skills/walllmat-verdict-judge && curl -fsSL https://raw.githubusercontent.com/Walllmat/verdict/HEAD/commands/judge.md -o ~/.claude/skills/walllmat-verdict-judge/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Judge does

name: judge description: "Evaluate the execution quality of a skill or agent" usage: "/judge [skill-name] [--rubric RUBRIC] [--verbose]"

/judge — Manual Skill Quality Evaluation

You are Verdict, the universal quality evaluator for Claude Code skills and agents.

Your Task

When the user invokes `/judge`, evaluate the most recent skill or agent execution using the 7-dimension scoring system.

Arguments

  • skill-name (optional): The name of the skill to judge. If omitted, detec

Alternatives in Development

  • Skill Creator — Create new skills, modify existing skills, and measure skill performance 94.1k ★
  • Route Eval — /route-eval — Evaluate a project and set its routing profile 705 ★
  • Evaluate Quality — Evaluate Quality of New Examples 570 ★

Full documentation available on GitHub

View Source Repository

Related Skills

Hackathon Judge — Development skill for Claude Code

Hackathon Judge

Evaluate a hackathon project against the official "Built with Opus 4.6" judging criteria. Scores demo, impact,

Development community
Loop Execution Evaluator — Development skill for Claude Code

Loop Execution Evaluator

Verify implementation quality. Evaluate-Loop Step 4.

Development community
Evaluate Execution — Development skill for Claude Code

Evaluate Execution

Development community
Loop Planner — Development skill for Claude Code

Loop Planner

Create execution plan from specification. Evaluate-Loop Step 1.

Development community
Vibememo Eval — Development skill for Claude Code

Vibememo Eval

Periodic VibeMemo evaluation and capture. Runs on a loop (default 30m) to assess whether significant decisions

Development community
Harness Review — Development skill for Claude Code

Harness Review

Full qualitative review of the agent setup. Read every file, evaluate quality, redundancy, and optimization op

Development community

Related Agents

Judge Agent — Development agent for Claude Code

Judge Agent

Read-only isolated agent that evaluates skill/agent execution quality

Development community
Adversarial Judge.Agent — Development agent for Claude Code

Adversarial Judge.Agent

Use to adversarially evaluate a proposal or implementation against its repository profile and specs, returning

Development community
Task Plan Verifier — Testing & QA agent for Claude Code

Task Plan Verifier

Phase 4 - LLM-as-judge verification of task definitions during planning. Evaluates tasks against spec, strateg

Testing & QA community