Skill collection

agentscope-ai/OpenJudge

18 agent skills across 8 categories, read straight from the repository tree.

AgentScope-AI33,120★ across the radarProfile →
18
Skills published
8
Categories
5
Ship scripts
764
Stars on the repo
Tracked on the radar · 764★Repository facts and velocity →
Data & Analytics · 4
All in category →
align-humanUse when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees…scriptsopenjudgeBuild custom LLM evaluation pipelines using the OpenJudge framework. Covers selecting and configuring graders…rl-rewardBuild RL reward signals using the OpenJudge framework. Covers choosing between pointwise and pairwise reward…metric-designUse when the user has evaluation principles or a dataset but needs help choosing the right graders, designing…
Security · 4
All in category →
redteamUse when the user wants to test their LLM/agent application for safety and security vulnerabilities —…scriptseval-reportUse when the user has run multiple evaluation skills and wants a comprehensive analysis — maturity…claude-authenticityDetect whether an API endpoint is backed by genuine Claude (not a wrapper, proxy, or impersonator) using 9…bib-verifyVerify a BibTeX file for hallucinated or fabricated references by cross-checking every entry against…
Code Review & Quality · 4
All in category →
rag-evalUse when the user has a RAG (Retrieval-Augmented Generation) system and wants to evaluate its quality —…scriptspaper-reviewReview academic papers for correctness, quality, and novelty using OpenJudge's multi-stage pipeline. Supports…meta-evalUse when the user wants to build an evaluation system for an LLM/agent application but doesn't know where to…find-skills-comboDiscover and recommend **combinations** of agent skills to complete complex, multi-faceted tasks. Provides…
Testing & QA · 2
All in category →
eval-designUse when the user needs to design evaluation datasets, create test cases, stratify samples, generate…scriptsauto-arenaAutomatically evaluate and compare multiple AI models or agents without pre-existing test data. Generates…
Design & Presentation · 1
All in category →
prompt-regressionUse when the user has changed a prompt (system prompt, RAG template, agent instruction, etc.) and wants to…scripts
Content & Marketing · 1
All in category →
mmx-cliGenerate text, images, video, speech, and music via the MiniMax AI platform. Covers text generation…
Frontend · 1
All in category →
ref-hallucination-arenaBenchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed…
Other · 1
bootstrapUse when the user has nothing — no traces, no labels, no eval set — and needs to build a v0 evaluation from…
About this collection
How many skills does agentscope-ai/OpenJudge publish?

18 that pass our gate — each has a real description and a SKILL.md we could read.

How do I install one?

Every skill page carries its own command — `npx skills add agentscope-ai/OpenJudge --skill <name> --agent claude-code`. Swap the agent for codex, cursor or copilot.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these collections come from.
More from agentscope-ai →
Everything this maker publishes.