{"skill":{"slug":"wei-cross-research","displayName":"Wei Cross Research","summary":"Cross-validate research answers by querying multiple LLMs in parallel with judge-based synthesis. Reduces hallucination and surfaces model disagreements for...","tags":{"consensus":"1.0.0","latest":"1.0.0","multi-model":"1.0.0","reasoning":"1.0.0","research":"1.0.0"},"stats":{"comments":0,"downloads":114,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1776609743133,"updatedAt":1776610007512},"latestVersion":{"version":"1.0.0","createdAt":1776609743133,"changelog":"wei-cross-research v1.0.0\n\n- Initial release.\n- Enables robust cross-validation of research answers by querying multiple large language models (LLMs) in parallel and using a judge model to synthesize results.\n- Highlights model disagreement for high-stakes or ambiguous questions, reducing hallucination risk.\n- Supports role-based domain specialization (e.g., financial, technical, social); judge model adapts synthesis to query domain.\n- Offers domain-specific financial analysis format covering base, bull, bear scenarios and key risks.\n- Flexible configuration via roles in config.json; environment variable support for model provider keys (OpenRouter, DashScope).","license":"MIT-0"},"metadata":null,"owner":{"handle":"mikehankk","userId":"s17740h3taw84fgmg8d1t4m07n83g6y3","displayName":"Wei Han","image":"https://avatars.githubusercontent.com/u/123093985?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.env_credential_access","suspicious.llm_suspicious"],"summary":"Detected: suspicious.env_credential_access, suspicious.llm_suspicious","engineVersion":"v2.4.0","updatedAt":1776610007512}}