Claude Code skill for verifying OpenEvidence biomedical citations against PubMed with parallel accuracy scoring and audit reports
Evidence-disciplined AI workflow skills for investor-style company research, diligence planning, versioned updates, and evidence review.
Codex skill for auditing battery and materials-science claims against supplied or verified evidence.
Fail-closed Codex plugin for NAS-first medical guideline search and jurisdiction-aware, privacy-guarded evidence-card validation.
Offline audit passport separating announcements, models, animal behavioral evidence, hypotheses, and unsupported inferences.
TrustRAG — local-first RAG reliability workbench: claim-level NLI verification, SHA-256 evidence audit and self-healing retrieval over hybrid dense+BM25, fully offline by default
Evidence-first biomedical manuscript review framework for for biomedical research manuscripts. Agent Skill for ChatGPT, Codex, Claude Code, and OpenClaw.
Reproducibility package and methodological dossier for RIEC-L1, an evidence-led conflict-resolution layer for finite candidate libraries in engineering data.
Multimodal evidence audit pipeline powered by Vision-Language Models. Adjudicates physical damage claims across vehicles, packages, and consumer electronics using chat transcripts, historical risk flags, and visual verification guardrails.
AegisDesk — Evidence-Constrained Multi-Agent Trading Decision Stress Test
Frozen public projection of RIEC-Core v1.0 protocol-to-claim governance.
🔍 Evidence-gated chemical engineering literature search and DOI verification skill for HanaAgent.
给想法、方案和报告做证据化审查：定位关键漏洞、核查来源，交付可用的修订。支持合理放行与证据更新。
To associate your repository with the evidence-audit topic, visit your repo's landing page and select "manage topics."