プロトタイプ · プレビュー版:公式レジストリのすべてのサーバーを掲載し、30分ごとに同期しています。Google でログインするとレビューを書けます。プロトタイプ · 30分ごとに更新
PopNx MCPAIを使う人のためのMCPサーバー · やさしい言葉で解説

OpenJudge Skill

リポジトリ ↗

作者:agentscope-ai★ 1,113 (whole repo)21 個の skill

★ Stars are for the whole repo, not each skill

Pick the skill to install

What it does

This repo is a collection of 21 skills

  • Connects Instruction files the AI reads, with steps that call an outside service
  • Account or key Some steps need a key for MINIMAX_API_KEY (per the README)
  • Category 自動化とエージェント
Maker’s original description
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
作者向け:README にバッジを付ける

作者の方は、このコードを README に貼れます。バッジはこのページにリンクします。

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/agentscope-ai-openjudge.svg)](https://mcp.popnx.com/en/skills/agentscope-ai-openjudge)

似た Skill

同じ種類の作業。Skill 一覧と同じ並び

似たものと比べる
これ
OpenJudge
skillsnacosanatomyleon
作者agentscope-aivercel-labsalibabawheresryan22leon-ai
Skill 数211111
GitHub スター1,11339,90833,52827,99617,693
最終コード更新2026年11月18日2026年11月17日2026年11月18日2026年10月19日2026年11月13日
ライセンスApache-2.0MITApache-2.0MITMIT

agentscope-ai による 21 個の Skill(指示セット)。AI が読んでそのとおりに作業します · MCP server ではありません

Pick the skill to install

Install only the ones you use. Open a skill to see how to install it

Install the whole set (21)

If you want every one, let the AI install them in one go. Know 2 things first

  • Every installed skill’s description is loaded into every chat. The more you install, the easier it is for the AI to pick the wrong one
  • Some skills duplicate tools the AI already has built in. Installing only the ones you use works better
Where to install
Please install all 21 skills from https://github.com/agentscope-ai/openjudge: 00-academic-router, 00-arena-router, 00-meta-eval, 01-auto-arena, 01-eval-design, 01-graders-and-pipeline, 01-paper-review, 02-bib-verify, 02-metric-design, 02-ref-hallucination-arena, 02-rl-reward, 03-align-human, 03-ref-hallucination-arena, 04-eval-report, 05-rag-eval, 06-prompt-regression, 07-redteam, 08-bootstrap, claude-authenticity, find-skills-combo, mmx-cli, for all my projects, putting each at ~/.claude/skills/<skill name> (in Codex use ~/.agents/skills/<skill name>, in Cursor ~/.cursor/skills/<skill name>). Folders in the repo: 00-academic-router = skills/academic-eval/00-academic-router · 00-arena-router = skills/arena-eval/00-arena-router · 00-meta-eval = skills/eval_pipeline/00-meta-eval · 01-auto-arena = skills/arena-eval/01-auto-arena · 01-eval-design = skills/eval_pipeline/01-eval-design · 01-graders-and-pipeline = skills/openjudge-core/01-graders-and-pipeline · 01-paper-review = skills/academic-eval/01-paper-review · 02-bib-verify = skills/academic-eval/02-bib-verify · 02-metric-design = skills/eval_pipeline/02-metric-design · 02-ref-hallucination-arena = skills/arena-eval/02-ref-hallucination-arena · 02-rl-reward = skills/openjudge-core/02-rl-reward · 03-align-human = skills/eval_pipeline/03-align-human · 03-ref-hallucination-arena = skills/academic-eval/03-ref-hallucination-arena · 04-eval-report = skills/eval_pipeline/04-eval-report · 05-rag-eval = skills/eval_pipeline/05-rag-eval · 06-prompt-regression = skills/eval_pipeline/06-prompt-regression · 07-redteam = skills/eval_pipeline/07-redteam · 08-bootstrap = skills/eval_pipeline/08-bootstrap · claude-authenticity = skills/claude-authenticity · find-skills-combo = skills/find-skills-combo · mmx-cli = skills/mmx-cli. First show me every file and tell me whether any has scripts or changes machine settings, then tell me the full path you will install each one to and wait for me to agree.
Please install all 21 skills from https://github.com/agentscope-ai/openjudge: 00-academic-router, 00-arena-router, 00-meta-eval, 01-auto-arena, 01-eval-design, 01-graders-and-pipeline, 01-paper-review, 02-bib-verify, 02-metric-design, 02-ref-hallucination-arena, 02-rl-reward, 03-align-human, 03-ref-hallucination-arena, 04-eval-report, 05-rag-eval, 06-prompt-regression, 07-redteam, 08-bootstrap, claude-authenticity, find-skills-combo, mmx-cli, into the project this chat is open in (at .claude/skills/<skill name>; in Codex use .agents/skills/<skill name>, in Cursor .cursor/skills/<skill name>). Folders in the repo: 00-academic-router = skills/academic-eval/00-academic-router · 00-arena-router = skills/arena-eval/00-arena-router · 00-meta-eval = skills/eval_pipeline/00-meta-eval · 01-auto-arena = skills/arena-eval/01-auto-arena · 01-eval-design = skills/eval_pipeline/01-eval-design · 01-graders-and-pipeline = skills/openjudge-core/01-graders-and-pipeline · 01-paper-review = skills/academic-eval/01-paper-review · 02-bib-verify = skills/academic-eval/02-bib-verify · 02-metric-design = skills/eval_pipeline/02-metric-design · 02-ref-hallucination-arena = skills/arena-eval/02-ref-hallucination-arena · 02-rl-reward = skills/openjudge-core/02-rl-reward · 03-align-human = skills/eval_pipeline/03-align-human · 03-ref-hallucination-arena = skills/academic-eval/03-ref-hallucination-arena · 04-eval-report = skills/eval_pipeline/04-eval-report · 05-rag-eval = skills/eval_pipeline/05-rag-eval · 06-prompt-regression = skills/eval_pipeline/06-prompt-regression · 07-redteam = skills/eval_pipeline/07-redteam · 08-bootstrap = skills/eval_pipeline/08-bootstrap · claude-authenticity = skills/claude-authenticity · find-skills-combo = skills/find-skills-combo · mmx-cli = skills/mmx-cli. First show me every file and tell me whether any has scripts or changes machine settings, then tell me the project name and the full path you will install each one to and wait for me to agree.

Uploading to Claude on the web and apps: you need 21 uploads, one ZIP per skill. Open each skill in the list below to download it

Checked against official docs 2026年11月12日 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com

  • 00-academic-router

    Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review…

  • 00-arena-router

    Use when the user wants to compare or benchmark multiple LLMs/agents arena-style but it's unclear which specific workflow fits — a general-purpose win-rate comparison on a custom task, or a benchmark specifically about reference/citation hallucination rate. Also use when the user mentions model are…

  • 00-meta-eval

    Use when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to start — they have traces, prompts, RAG pipelines, or nothing at all. Also use when the user mentions evaluation, eval, benchmarking, testing LLM quality, measuring agent performance, assessi…

  • 01-auto-arena

    Automatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates test queries from a task description, collects responses from all target endpoints, auto-generates evaluation rubrics, runs pairwise comparisons via a judge model, and produces win-rate ranking…

  • 01-eval-design

    Use when the user needs to design evaluation datasets, create test cases, stratify samples, generate adversarial examples, extract eval dimensions from traces/specs, or build a labeled evaluation set. Also use when the user mentions test data design, eval coverage, difficulty stratification, synthe…

  • 01-graders-and-pipeline

    Build custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders (LLM-based, function-based, agentic), running batch evaluations with GradingRunner, combining scores with aggregators, applying evaluation strategies (voting, average), auto-generating grad…

  • 01-paper-review

    Review academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports PDF files and LaTeX source packages (.tar.gz/.zip). Covers 10 disciplines: cs, medicine, physics, chemistry, biology, economics, psychology, environmental_science, mathematics, social_scien…

  • 02-bib-verify

    Verify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against CrossRef, arXiv, and DBLP. Reports each reference as verified, suspect, or not found, with field-level mismatch details (title, authors, year, DOI). Use when the user wants to check a .bib file for…

  • 02-metric-design

    Use when the user has evaluation principles or a dataset but needs help choosing the right graders, designing evaluation metrics, creating LLM-as-judge prompts, combining multiple metrics into a composite score, or building an automated evaluation pipeline. Also use when the user mentions grader se…

  • 02-ref-hallucination-arena

    Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) m…

  • 02-rl-reward

    Build RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward strategies based on RL algorithm, task type, and cost; aggregating multi-dimensional pointwise scores into a scalar reward; pairwise tournament reward for GRPO on subjective tasks (net win r…

  • 03-align-human

    Use when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic evaluation can replace human review, or build a human-reduction roadmap. Also use when the user mentions calibration, TPR/TN…

  • 03-ref-hallucination-arena

    Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accuracy (title/author/year/DOI), discipline breakdown, and year constraint compliance. Supports tool-augmented (ReAct + web search) m…

  • 04-eval-report

    Use when the user has run multiple evaluation skills and wants a comprehensive analysis — maturity assessment, cross-skill signals, trends, prioritized actions, and an executive summary. Also use when the user mentions eval health check, evaluation audit, ship readiness, evaluation maturity, or "ho…

  • 05-rag-eval

    Use when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality — separating retrieval issues from generation issues. Also use when the user mentions RAG evaluation, faithfulness checking, hallucination detection in RAG, retrieval quality, chunking optimization…

  • 06-prompt-regression

    Use when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to know whether the candidate is better or worse than the baseline. Also use when the user mentions prompt A/B testing, prompt comparison, prompt optimization validation, "did my prompt change he…

  • 07-redteam

    Use when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content generation, or evaluator gaming. Also use when the user mentions security testing, adversarial testing, red teaming, safety evaluation,…

  • 08-bootstrap

    Use when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from scratch. Also use when the user says "I need to start evaluating my app but don't know where to begin," "I want to set up eval for a new product," or has just identified failure modes and nee…

  • claude-authenticity

    Detect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9 weighted rule-based checks that mirror the claude-verify project. Also extracts injected system prompts from providers that override Claude's identity. Fully self-contained — copy the code bel…

  • find-skills-combo

    Discover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides two recommendation strategies — **Maximum Quality** (best skill per subtask) and **Minimum Dependencies** (fewest installs). Use this skill whenever the user wants to find skills, asks "how do…

  • mmx-cli

    Generate text, images, video, speech, and music via the MiniMax AI platform. Covers text generation (MiniMax-M3 model), image generation (image-01), video generation (Hailuo-2.3), speech synthesis (speech-2.8-hd, 300+ voices), music generation (music-2.6 with lyrics, cover, and instrumental), and w…

Skill と MCP の違い

MCP = 手

AI を外部のサービスやデータにつなぎます(例:Notion を読む、請求書を作る)。プログラムやサーバーが動いている必要があります。

Skill = 手順書

作業のやり方を AI に教えるテキストファイル。どのサービスにもつながりません。

重なる部分もあります。ツールを呼ぶスクリプト付きの Skill や、知識だけを渡す MCP もあります。やりたい作業から選んでください。

使えるアプリ

提供元の記載なし · SKILL.md 形式の Skill は Claude Code、Codex、Cursor など Agent Skills 対応アプリで使えます

インストール

Pick a skill first

This repo has 21 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP

Let the AI install it
Upload to claude.ai

Go to the skill list ↑

話し合い

質問、コツの共有、使えないことの報告ができます。「役に立った」の多い順です。

まだ投稿はありません。最初の質問や共有をどうぞ。

ここの投稿は利用者によるもので、PopNx チームのものではありません。

ログインして投稿

GitHub の情報

GitHub スター
1,113
Stars are for the whole repo, not each skill
提供元
agentscope-ai
ライセンス
Apache-2.0
最終コード更新
2026年11月18日
repo 内の SKILL.md(翻訳版とテンプレートを含む)
21
トピック
agent, agent-skills, ai-agent, alignment, evaluation, grader, llm, reward, reward-model, rlhf, skill-md, skills