write-judge-prompt

write-judge-prompt is a skill for Claude Code from hamelsmu/evals-skills. It costs 82 tokens per session (1,608 once invoked), scanned A, original, MIT.

A guide for writing an AI evaluator that judges one subjective quality of a language-model answer, such as whether it is relevant, faithful to its sources, or complete.

In plain words
What is it for?
Use it after error analysis to design a judge prompt for one specific failure type, based on examples already labeled by people.
Why use it?
It helps create focused Pass/Fail checks for qualities that ordinary code cannot reliably measure, while avoiding AI judges where simple rules would work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the evals-skills plugin — 7 skills shipped together

Good fit Use it after error analysis to design a judge prompt for one specific failure type, based on examples already labeled by people.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hamelsmu/evals-skills/write-judge-prompt
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add hamelsmu/evals-skills --skill write-judge-prompt
Clone the repo
git clone --depth 1 https://github.com/hamelsmu/evals-skills

Made for: Claude Code.

Or install evals-skills, the plugin that ships this one along with the rest of its 7 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for write-judge-prompt

README.md
[![agentmods](https://agentmods.dev/badge/skills/hamelsmu/evals-skills/write-judge-prompt/github.svg)](https://agentmods.dev/skills/hamelsmu/evals-skills/write-judge-prompt)
Your own site
<a href="https://agentmods.dev/skills/hamelsmu/evals-skills/write-judge-prompt"><img src="https://agentmods.dev/badge/skills/hamelsmu/evals-skills/write-judge-prompt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for write-judge-prompt

Your own site · 80×15
<a href="https://agentmods.dev/skills/hamelsmu/evals-skills/write-judge-prompt"><img src="https://agentmods.dev/badge/skills/hamelsmu/evals-skills/write-judge-prompt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,608 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 18 Mar 2026
  • Snyk pass 3 Mar 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00082 $0.01608
Opus 5 $0.00041 $0.00804
Sonnet 5 $0.00016 $0.00322
Haiku 4.5 $0.00008 $0.00161

Measured 11d ago against content hash aa28d26c731e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

write-judge-prompt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/write-judge-prompt/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write LLM-as-Judge Prompt

Design a binary Pass/Fail LLM-as-Judge evaluator for one specific failure mode. Each judge checks exactly one thing.

Prerequisites

  • Error analysis is complete. The failure mode is identified.
  • You have human-labeled traces for this failure mode (at least 20 Pass and 20 Fail examples).
  • A code-based evaluator cannot check this failure mode. Exhaust code-based options before reaching for a judge — many failure modes that seem subjective reduce to keyword checks, regex, or API calls when you understand the domain. Example: detecting whether an AI interviewing coach suggests "general" questions (asking about typical behavior instead of a specific past event) seems to require semantic understanding, but in practice a keyword check for words like "usually," "typical," and "normally" could work quite well.

The Four Components

Every judge prompt requires exactly four components:

1. Task and Evaluation Criterion

State what the judge evaluates. One failure mode per judge.

You are an evaluator assessing whether a real estate assistant's email
uses the appropriate tone for the client's persona.

Not: "Evaluate whether the email is good" or "Rate the email quality from 1-5."

2. Pass/Fail Definitions

Outcomes are strictly binary: Pass or Fail. No Likert scales, no letter grades, no partial credit. Define exactly what constitutes Pass and Fail. These definitions come from your error analysis failure mode descriptions.

## Definitions

PASS: The email matches the expected communication style for the client persona:
- Luxury Buyers: formal language, emphasis on exclusive features, premium
  market positioning, no casual slang
- First-Time Homebuyers: warm and encouraging tone, educational explanations,
  avoids jargon, patient and supportive
- Investors: data-driven language, ROI-focused, market analytics, concise
  and professional

FAIL: The email uses a tone mismatched to the client persona. Examples:
- Using casual slang ("hey, check out this pad!") for a luxury buyer
- Using heavy financial jargon for a first-time homebuyer
- Using overly emotional language for an investor

Read the full file on GitHub · 145 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 145 lines · 82 tokens per session scan A aa28d26c731e

Subscribe to this mod's changes

write-judge-prompt is a skill published in the GitHub repository hamelsmu/evals-skills (1,664 stars, last pushed 26d ago), licensed MIT. It adds 82 tokens to every session and 1,608 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

prompt-optimization

Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…

langwatch/langwatch · 105 tokens

enhance-prompt

Transforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.

google-labs-code/stitch-skills · 41 tokens

prompt-engineer

Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…

Jeffallan/claude-skills · 93 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens

ideogram4

Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…

digitalsamba/claude-code-video-toolkit · 99 tokens