# OpenJudge > Evaluate AI apps with your agent: design test sets and graders, check judges against people, test RAG and prompts, and red-team them. OpenJudge is AgentScope's open-source framework for evaluating AI applications such as agents and chatbots. This skill pack teaches your agent its evaluation workflows, from a first test set to a full report, plus workflows for academic papers and for comparing models. What you can do with it - Start an evaluation from nothing, or from the traces, prompts or RAG pipeline you already have - Design evaluation datasets: test cases, stratified samples and adversarial examples - Pick graders and metrics, write LLM-as-judge prompts and combine scores into one - Measure how well a judge agrees with human labels and spot its biases - Evaluate a RAG system, separating retrieval problems from generation problems - Compare a changed prompt with the baseline, and red-team an app for jailbreaks, prompt injection and PII leaks - Compare models or agents arena-style on your task, with test queries and rubrics generated for you - Review academic papers, and check a BibTeX file for made-up references against CrossRef, arXiv and DBLP - Build graders and RL reward signals with the OpenJudge Python library How it connects - Most skills use the OpenJudge Python library (pip install py-openjudge) and an LLM you choose as the judge, through an OpenAI-compatible endpoint. - You can also try its graders in the browser at openjudge.me without installing anything. Good to know - The pack also has three stand-alone skills: one that checks whether an API endpoint is really backed by Claude, one for MiniMax's mmx command-line tool, and one that suggests combinations of skills for a multi-part task. - It's open source under the Apache 2.0 licence. - Type: Skill - Made by: agentscope-ai - Category: Research - Formats: Skills - Version: latest - Website: https://openjudge.me - Source: https://github.com/agentscope-ai/OpenJudge - Page: https://pluginboard.ai/skills/openjudge ## Works with - ChatGPT - Claude - Gemini - GitHub Copilot - Cursor - Claude Code - Codex - Antigravity - Gemini CLI - Replit - OpenClaw - OpenCode - Hermes Agent ## Install ### ChatGPT In ChatGPT: Download the OpenJudge folder and zip it, then Plugins → Skills → Create → Upload from your computer. Business and Enterprise plans. View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### Claude In Claude (web or desktop): Download each skill’s folder and zip it, then upload them one at a time in Customize → Skills. View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### Gemini In Gemini: Download the OpenJudge folder, then at gemini.google.com click Customize → Skills → Create → Upload and pick the folder (or a .zip of it). View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### GitHub Copilot Copy all 21 skills, in your terminal: ```shell npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/00-academic-router ~/.copilot/skills/00-academic-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/00-arena-router ~/.copilot/skills/00-arena-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/01-auto-arena ~/.copilot/skills/01-auto-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/01-graders-and-pipeline ~/.copilot/skills/01-graders-and-pipeline npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/01-paper-review ~/.copilot/skills/01-paper-review npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/02-bib-verify ~/.copilot/skills/02-bib-verify npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/02-ref-hallucination-arena ~/.copilot/skills/02-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.copilot/skills/02-rl-reward npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/03-ref-hallucination-arena ~/.copilot/skills/03-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/03-align-human ~/.copilot/skills/03-align-human npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/08-bootstrap ~/.copilot/skills/08-bootstrap npx -y degit agentscope-ai/OpenJudge/skills/claude-authenticity ~/.copilot/skills/claude-authenticity npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/01-eval-design ~/.copilot/skills/01-eval-design npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/04-eval-report ~/.copilot/skills/04-eval-report npx -y degit agentscope-ai/OpenJudge/skills/find-skills-combo ~/.copilot/skills/find-skills-combo npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/00-meta-eval ~/.copilot/skills/00-meta-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/02-metric-design ~/.copilot/skills/02-metric-design npx -y degit agentscope-ai/OpenJudge/skills/mmx-cli ~/.copilot/skills/mmx-cli npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/06-prompt-regression ~/.copilot/skills/06-prompt-regression npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/05-rag-eval ~/.copilot/skills/05-rag-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/07-redteam ~/.copilot/skills/07-redteam ``` View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### Cursor Copy all 21 skills, in your terminal: ```shell npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/00-academic-router ~/.cursor/skills/00-academic-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/00-arena-router ~/.cursor/skills/00-arena-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/01-auto-arena ~/.cursor/skills/01-auto-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/01-graders-and-pipeline ~/.cursor/skills/01-graders-and-pipeline npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/01-paper-review ~/.cursor/skills/01-paper-review npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/02-bib-verify ~/.cursor/skills/02-bib-verify npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/02-ref-hallucination-arena ~/.cursor/skills/02-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.cursor/skills/02-rl-reward npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/03-ref-hallucination-arena ~/.cursor/skills/03-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/03-align-human ~/.cursor/skills/03-align-human npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/08-bootstrap ~/.cursor/skills/08-bootstrap npx -y degit agentscope-ai/OpenJudge/skills/claude-authenticity ~/.cursor/skills/claude-authenticity npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/01-eval-design ~/.cursor/skills/01-eval-design npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/04-eval-report ~/.cursor/skills/04-eval-report npx -y degit agentscope-ai/OpenJudge/skills/find-skills-combo ~/.cursor/skills/find-skills-combo npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/00-meta-eval ~/.cursor/skills/00-meta-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/02-metric-design ~/.cursor/skills/02-metric-design npx -y degit agentscope-ai/OpenJudge/skills/mmx-cli ~/.cursor/skills/mmx-cli npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/06-prompt-regression ~/.cursor/skills/06-prompt-regression npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/05-rag-eval ~/.cursor/skills/05-rag-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/07-redteam ~/.cursor/skills/07-redteam ``` View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### Claude Code Copy all 21 skills, in your terminal: ```shell npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/00-academic-router ~/.claude/skills/00-academic-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/00-arena-router ~/.claude/skills/00-arena-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/01-auto-arena ~/.claude/skills/01-auto-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/01-graders-and-pipeline ~/.claude/skills/01-graders-and-pipeline npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/01-paper-review ~/.claude/skills/01-paper-review npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/02-bib-verify ~/.claude/skills/02-bib-verify npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/02-ref-hallucination-arena ~/.claude/skills/02-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.claude/skills/02-rl-reward npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/03-ref-hallucination-arena ~/.claude/skills/03-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/03-align-human ~/.claude/skills/03-align-human npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/08-bootstrap ~/.claude/skills/08-bootstrap npx -y degit agentscope-ai/OpenJudge/skills/claude-authenticity ~/.claude/skills/claude-authenticity npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/01-eval-design ~/.claude/skills/01-eval-design npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/04-eval-report ~/.claude/skills/04-eval-report npx -y degit agentscope-ai/OpenJudge/skills/find-skills-combo ~/.claude/skills/find-skills-combo npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/00-meta-eval ~/.claude/skills/00-meta-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/02-metric-design ~/.claude/skills/02-metric-design npx -y degit agentscope-ai/OpenJudge/skills/mmx-cli ~/.claude/skills/mmx-cli npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/06-prompt-regression ~/.claude/skills/06-prompt-regression npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/05-rag-eval ~/.claude/skills/05-rag-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/07-redteam ~/.claude/skills/07-redteam ``` View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### Codex Copy all 21 skills, in your terminal: ```shell npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/00-academic-router ~/.agents/skills/00-academic-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/00-arena-router ~/.agents/skills/00-arena-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/01-auto-arena ~/.agents/skills/01-auto-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/01-graders-and-pipeline ~/.agents/skills/01-graders-and-pipeline npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/01-paper-review ~/.agents/skills/01-paper-review npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/02-bib-verify ~/.agents/skills/02-bib-verify npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/02-ref-hallucination-arena ~/.agents/skills/02-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.agents/skills/02-rl-reward npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/03-ref-hallucination-arena ~/.agents/skills/03-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/03-align-human ~/.agents/skills/03-align-human npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/08-bootstrap ~/.agents/skills/08-bootstrap npx -y degit agentscope-ai/OpenJudge/skills/claude-authenticity ~/.agents/skills/claude-authenticity npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/01-eval-design ~/.agents/skills/01-eval-design npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/04-eval-report ~/.agents/skills/04-eval-report npx -y degit agentscope-ai/OpenJudge/skills/find-skills-combo ~/.agents/skills/find-skills-combo npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/00-meta-eval ~/.agents/skills/00-meta-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/02-metric-design ~/.agents/skills/02-metric-design npx -y degit agentscope-ai/OpenJudge/skills/mmx-cli ~/.agents/skills/mmx-cli npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/06-prompt-regression ~/.agents/skills/06-prompt-regression npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/05-rag-eval ~/.agents/skills/05-rag-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/07-redteam ~/.agents/skills/07-redteam ``` View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### Antigravity In Antigravity: Copy the OpenJudge folder into ~/.gemini/config/skills (Antigravity app and IDE) or ~/.gemini/antigravity-cli/skills (Antigravity CLI). View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### Gemini CLI Copy all 21 skills, in your terminal: ```shell npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/00-academic-router ~/.gemini/skills/00-academic-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/00-arena-router ~/.gemini/skills/00-arena-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/01-auto-arena ~/.gemini/skills/01-auto-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/01-graders-and-pipeline ~/.gemini/skills/01-graders-and-pipeline npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/01-paper-review ~/.gemini/skills/01-paper-review npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/02-bib-verify ~/.gemini/skills/02-bib-verify npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/02-ref-hallucination-arena ~/.gemini/skills/02-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.gemini/skills/02-rl-reward npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/03-ref-hallucination-arena ~/.gemini/skills/03-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/03-align-human ~/.gemini/skills/03-align-human npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/08-bootstrap ~/.gemini/skills/08-bootstrap npx -y degit agentscope-ai/OpenJudge/skills/claude-authenticity ~/.gemini/skills/claude-authenticity npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/01-eval-design ~/.gemini/skills/01-eval-design npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/04-eval-report ~/.gemini/skills/04-eval-report npx -y degit agentscope-ai/OpenJudge/skills/find-skills-combo ~/.gemini/skills/find-skills-combo npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/00-meta-eval ~/.gemini/skills/00-meta-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/02-metric-design ~/.gemini/skills/02-metric-design npx -y degit agentscope-ai/OpenJudge/skills/mmx-cli ~/.gemini/skills/mmx-cli npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/06-prompt-regression ~/.gemini/skills/06-prompt-regression npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/05-rag-eval ~/.gemini/skills/05-rag-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/07-redteam ~/.gemini/skills/07-redteam ``` View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### Replit Copy all 21 skills, in your terminal: ```shell npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/00-academic-router .agents/skills/00-academic-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/00-arena-router .agents/skills/00-arena-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/01-auto-arena .agents/skills/01-auto-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/01-graders-and-pipeline .agents/skills/01-graders-and-pipeline npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/01-paper-review .agents/skills/01-paper-review npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/02-bib-verify .agents/skills/02-bib-verify npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/02-ref-hallucination-arena .agents/skills/02-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward .agents/skills/02-rl-reward npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/03-ref-hallucination-arena .agents/skills/03-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/03-align-human .agents/skills/03-align-human npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/08-bootstrap .agents/skills/08-bootstrap npx -y degit agentscope-ai/OpenJudge/skills/claude-authenticity .agents/skills/claude-authenticity npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/01-eval-design .agents/skills/01-eval-design npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/04-eval-report .agents/skills/04-eval-report npx -y degit agentscope-ai/OpenJudge/skills/find-skills-combo .agents/skills/find-skills-combo npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/00-meta-eval .agents/skills/00-meta-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/02-metric-design .agents/skills/02-metric-design npx -y degit agentscope-ai/OpenJudge/skills/mmx-cli .agents/skills/mmx-cli npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/06-prompt-regression .agents/skills/06-prompt-regression npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/05-rag-eval .agents/skills/05-rag-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/07-redteam .agents/skills/07-redteam ``` View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### OpenClaw Copy all 21 skills, in your terminal: ```shell npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/00-academic-router ~/.openclaw/skills/00-academic-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/00-arena-router ~/.openclaw/skills/00-arena-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/01-auto-arena ~/.openclaw/skills/01-auto-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/01-graders-and-pipeline ~/.openclaw/skills/01-graders-and-pipeline npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/01-paper-review ~/.openclaw/skills/01-paper-review npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/02-bib-verify ~/.openclaw/skills/02-bib-verify npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/02-ref-hallucination-arena ~/.openclaw/skills/02-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.openclaw/skills/02-rl-reward npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/03-ref-hallucination-arena ~/.openclaw/skills/03-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/03-align-human ~/.openclaw/skills/03-align-human npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/08-bootstrap ~/.openclaw/skills/08-bootstrap npx -y degit agentscope-ai/OpenJudge/skills/claude-authenticity ~/.openclaw/skills/claude-authenticity npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/01-eval-design ~/.openclaw/skills/01-eval-design npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/04-eval-report ~/.openclaw/skills/04-eval-report npx -y degit agentscope-ai/OpenJudge/skills/find-skills-combo ~/.openclaw/skills/find-skills-combo npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/00-meta-eval ~/.openclaw/skills/00-meta-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/02-metric-design ~/.openclaw/skills/02-metric-design npx -y degit agentscope-ai/OpenJudge/skills/mmx-cli ~/.openclaw/skills/mmx-cli npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/06-prompt-regression ~/.openclaw/skills/06-prompt-regression npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/05-rag-eval ~/.openclaw/skills/05-rag-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/07-redteam ~/.openclaw/skills/07-redteam ``` View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### OpenCode Copy all 21 skills, in your terminal: ```shell npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/00-academic-router ~/.config/opencode/skills/00-academic-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/00-arena-router ~/.config/opencode/skills/00-arena-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/01-auto-arena ~/.config/opencode/skills/01-auto-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/01-graders-and-pipeline ~/.config/opencode/skills/01-graders-and-pipeline npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/01-paper-review ~/.config/opencode/skills/01-paper-review npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/02-bib-verify ~/.config/opencode/skills/02-bib-verify npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/02-ref-hallucination-arena ~/.config/opencode/skills/02-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.config/opencode/skills/02-rl-reward npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/03-ref-hallucination-arena ~/.config/opencode/skills/03-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/03-align-human ~/.config/opencode/skills/03-align-human npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/08-bootstrap ~/.config/opencode/skills/08-bootstrap npx -y degit agentscope-ai/OpenJudge/skills/claude-authenticity ~/.config/opencode/skills/claude-authenticity npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/01-eval-design ~/.config/opencode/skills/01-eval-design npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/04-eval-report ~/.config/opencode/skills/04-eval-report npx -y degit agentscope-ai/OpenJudge/skills/find-skills-combo ~/.config/opencode/skills/find-skills-combo npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/00-meta-eval ~/.config/opencode/skills/00-meta-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/02-metric-design ~/.config/opencode/skills/02-metric-design npx -y degit agentscope-ai/OpenJudge/skills/mmx-cli ~/.config/opencode/skills/mmx-cli npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/06-prompt-regression ~/.config/opencode/skills/06-prompt-regression npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/05-rag-eval ~/.config/opencode/skills/05-rag-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/07-redteam ~/.config/opencode/skills/07-redteam ``` View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge ### Hermes Agent Copy all 21 skills, in your terminal: ```shell npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/00-academic-router ~/.hermes/skills/00-academic-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/00-arena-router ~/.hermes/skills/00-arena-router npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/01-auto-arena ~/.hermes/skills/01-auto-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/01-graders-and-pipeline ~/.hermes/skills/01-graders-and-pipeline npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/01-paper-review ~/.hermes/skills/01-paper-review npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/02-bib-verify ~/.hermes/skills/02-bib-verify npx -y degit agentscope-ai/OpenJudge/skills/arena-eval/02-ref-hallucination-arena ~/.hermes/skills/02-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/openjudge-core/02-rl-reward ~/.hermes/skills/02-rl-reward npx -y degit agentscope-ai/OpenJudge/skills/academic-eval/03-ref-hallucination-arena ~/.hermes/skills/03-ref-hallucination-arena npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/03-align-human ~/.hermes/skills/03-align-human npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/08-bootstrap ~/.hermes/skills/08-bootstrap npx -y degit agentscope-ai/OpenJudge/skills/claude-authenticity ~/.hermes/skills/claude-authenticity npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/01-eval-design ~/.hermes/skills/01-eval-design npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/04-eval-report ~/.hermes/skills/04-eval-report npx -y degit agentscope-ai/OpenJudge/skills/find-skills-combo ~/.hermes/skills/find-skills-combo npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/00-meta-eval ~/.hermes/skills/00-meta-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/02-metric-design ~/.hermes/skills/02-metric-design npx -y degit agentscope-ai/OpenJudge/skills/mmx-cli ~/.hermes/skills/mmx-cli npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/06-prompt-regression ~/.hermes/skills/06-prompt-regression npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/05-rag-eval ~/.hermes/skills/05-rag-eval npx -y degit agentscope-ai/OpenJudge/skills/eval_pipeline/07-redteam ~/.hermes/skills/07-redteam ``` View the skills on GitHub: https://github.com/agentscope-ai/OpenJudge --- From Pluginboard (https://pluginboard.ai).