본문으로 건너뛰기
cccskills
무료GitHub에 공개

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 arena, agent arena, pairwise model comparison, win-rate ranking, or comparing models on a task and hasn't specified whether that task is generic or about citation accuracy. This skill is the entry router for the arena-eval suite: it asks one diagnostic question when needed, then recommends the workflow or workflows needed to cover the request.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

agentscope-ai/OpenJudge
설치 방법 보기

포함된 파일(1)

  • SKILL.md4.0 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Arena Eval Router

Entry router for the arena-eval suite. You diagnose what the user wants to compare models on and route them to the appropriate sub-skill or both when the request spans both evaluation goals. You don't run comparisons yourself — you're the triage desk.

Each sub-skill is self-contained: it carries inline everything it needs, so it can be installed and used on its own.

Diagnostic Question

Ask (unless the user's request already makes the answer obvious):

To route you correctly: what are you comparing the models on?

a) A custom task of your own choosing (chatbot quality, summarization,
   coding, anything) — you'll get win-rate rankings from a judge model
b) Specifically how often each model fabricates or hallucinates references
   when asked to recommend citations

Shortcut rule: if the user already said "run an arena eval on my chatbot task" or "benchmark reference hallucination across these models", skip the question — the routing is already clear from their phrasing. Also skip the question when they explicitly ask for both general quality and citation accuracy; recommend both workflows.

Triage Table

User says / hasUse workflowWhat it does
"Compare/benchmark/rank these models on [any custom task]"01-auto-arenaGenerates queries from a task description, collects responses, auto-generates rubrics, runs pairwise judge comparisons, produces win-rate rankings
"Which model hallucinates citations least?" / "benchmark reference recommendation accuracy"02-ref-hallucination-arenaRuns reference-recommendation queries per model, verifies every returned citation against CrossRef/PubMed/arXiv/DBLP, ranks by verified accuracy
"Compare general helpfulness AND citation accuracy"01-auto-arena, then 02-ref-hallucination-arenaRuns separate evaluations for judge preference and verified citation accuracy, preserving both goals
"I want to review one paper's existing bibliography, not compare models"—Not this suite — see the academic-eval suite's 01-paper-review / 02-bib-verify instead

Key distinction

Both workflows produce model rankings from head-to-head-style evaluation, but differ in what "correct" means:

  • 01-auto-arena: correctness is judge opinion — an LLM judge scores pairwise which response is better for an arbitrary task. Works for any task, needs no ground truth.
  • 02-ref-hallucination-arena: correctness is externally verifiable — every cited reference is checked against real bibliographic databases (CrossRef/PubMed/arXiv/DBLP), so the ranking reflects factual accuracy, not judge preference. Narrower scope (citation recommendation only) but higher ground-truth confidence.

If the user cares only about citation accuracy, prefer 02-ref-hallucination-arena over 01-auto-arena even if they phrase it as "which model is better."

Output

Recommended workflow: `[skill-name]`

Why: [one sentence tying the user's request to the triage table row]

Recommend one workflow when it covers the request. If the user asks for both general quality and citation accuracy, recommend 01-auto-arena followed by 02-ref-hallucination-arena as separate runs (or follow the user's requested order). Explain that the two runs measure different things and report their results separately; neither ranking substitutes for the other.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

00-academic-router

무료

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, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

agentscope-ai/OpenJudge8772026년 9월 11일 업데이트

01-auto-arena

무료

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 rankings with reports and charts. Supports checkpoint resume, incremental endpoint addition, and judge model hot-swap. Use when the user asks to compare, benchmark, or rank multiple models or agents on a custom task, or run an arena-style evaluation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

agentscope-ai/OpenJudge8772026년 9월 11일 업데이트

01-graders-and-pipeline

무료

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 graders from data, and analyzing results (pairwise win rates, statistics, validation metrics). Use when the user wants to evaluate LLM outputs, compare multiple models, design scoring criteria, or build an automated evaluation system.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

agentscope-ai/OpenJudge8772026년 9월 11일 업데이트

01-paper-review

무료

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_sciences. Use when the user asks to review, evaluate, critique, or assess a research paper, check references, or verify a BibTeX file.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

agentscope-ai/OpenJudge8772026년 9월 11일 업데이트

02-bib-verify

무료

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 fake citations, validate references in a paper, or audit bibliography entries for accuracy.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

agentscope-ai/OpenJudge8772026년 9월 11일 업데이트

02-ref-hallucination-arena

무료

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) mode. Use when the user asks to evaluate, benchmark, or compare models on academic reference hallucination, literature recommendation quality, or citation accuracy.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

agentscope-ai/OpenJudge8772026년 9월 11일 업데이트

agentscope-ai의 스킬 모두 보기

이 스킬의 문제 신고