Home / Skills / 02-ref-hallucination-arena

02-ref-hallucination-arena

agentscope-ai/OpenJudgeSkill

Benchmark LLM reference recommendation capabilities by verifying every cited

ScannedSkillSource: GitHub
881 stars +8 this week Updated 2mo ago License Apache-2.0 Context ≈26 tokens always loaded
63popular

Why this score

Stars14/35
Usage (forks)4/15
Upkeep20/25
License15/15
Owner history10/10

This repo hosts 10 skills, so its 881 stars are split between them (about 88 each) for scoring.

Popularity score: 63/100 from public GitHub signals only. It shows how widely used and maintained this is, not how well it works. Not included yet: the fake-star check. The security scan is shown separately and doesn't change the score. How we rank

Security

Scanned Oct 20, 2026 at commit d1e06420bac4, with Cisco's open-source skill-scanner.

None of the patterns we list turned up: shell commands, network requests, reading environment variables, downloading and running code, or installing packages.

A scan lists patterns in the code. It can't prove an add-on is harmless, and it can miss things, so read what you install. How we scan

Alternatives

Other makers' add-ons that do the same job, next to this one.

NameScoreStarsContextUpdated
This one02-ref-hallucination-arena agentscope-ai/OpenJudge · Skill 63★ 881≈26 always2mo ago
arena Jakeschincariol/arena-skill · Skill Both about arena 74★ 786≈20 always1mo ago
character-refs eternityspring/shuohao-skills · Skill Both about ref 78★ 4.8k≈16 always21d ago
find-refs androguard/androguard · Skill Both about ref and reference 83★ 6.4k≈22 always23d ago
ref-tools-ref-tools-mcp ref-tools/ref-tools-mcp · MCP server Both about ref 85★ 1.2knot measured12d ago
nsfc-ref-alignment huangwb8/ChineseResearchLaTeX · Skill Both about ref 73★ 3.0k≈40 always18d ago