6 tagged bibliography, measured the same way as everything else here.
stephenlzc/AI-Powered-Literature-Review-Skills
Agent
A browser-driven literature search agent for academic databases such as CNKI, Web of Science, ScienceDirect, and PubMed. It searches for papers using supplied keywords, filters, and search expressions, then returns structured paper details.
stephenlzc/AI-Powered-Literature-Review-Skills
Agent
Agent "orchestrator" from stephenlzc/AI-Powered-Literature-Review-Skills, covering orchestrator agent 模板, agent 信息, 核心原则, 系统架构 and 8阶段工作流.
stephenlzc/AI-Powered-Literature-Review-Skills
Agent
Agent "synthesize-agent" from stephenlzc/AI-Powered-Literature-Review-Skills, covering synthesize agent 模板, agent 信息, 核心原则, 任务描述 and 输入格式.
Agent
Verify figure caption numerics against their summary.json sidecars. For each figure section in an INDEX.md, walks the linked stats dump, extracts numerics from the caption prose, and matches them. Catches stale prose where a value drifted between figure regeneration and caption update. Sibling to citation-audit…
Agent
Review research artifacts for scientific rigor before they're committed or pushed. Catches framing errors (nulls as detection limits, p-values without effect+CI, undefined metrics), unsupported claims, and presentation problems. Sibling to citation-audit (which checks citation structure) and the planned claim-audit…