ref-hallucination-arena
agentscope-ai
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accu…
809GitHub
OPENAGENTSKILL / DIRECTORY
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Find a skill for your next task. Preview examples where available.
Page 1 · 2 shown · 2 public entries
Results: 2
agentscope-ai
Benchmark LLM reference recommendation capabilities by verifying every cited paper against Crossref, PubMed, arXiv, and DBLP. Measures hallucination rate, per-field accu…
NEU-ZHA
法律产出事实核查技能。当用户需要撰写、编辑、分析任何法律文件(法律文书、案例分析、法条评析、合同审查、法律意见书、法学作业等)时触发此技能。核心原则:一切法律产出必须有事实依据,禁止编纂案例、法规或事实。触发词:法律文件、案例分析、法条分析、合同审查、法律意见、法学作业、案例检索、法规验证、事实核查、凶宅案、合同纠纷、民法作业、法律写作…