26.5.15论文自动化文献匹配+审稿风险检查/reviewer-simulator/SKILL.md
Simulate a strict academic reviewer and produce a manuscript risk report without editing the draft. Use when the user asks to act as a reviewer, find weaknesses before submission, inspect evidence gaps, check overclaims, evaluate manuscript readiness, combine advisor notes or meeting minutes into revision priorities, or generate a 审稿人模拟检查 report.
npx skillsauth add adoresever/agi_ananas reviewer-simulatorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
这个技能像严厉审稿人一样检查论文草稿,但默认不直接改正文。
它的目标是发现投稿风险:证据不足、引用不成立、实验缺失、方法说不清、结论过强、结构不闭合,以及导师或审稿人已经指出但尚未解决的问题。
当用户想做以下事情时使用:
可接受材料:
如果没有草稿,只能做修改任务整理,不能模拟完整审稿。
执行时优先读取已经生成的中间文本和报告,避免反复直接解析原文件。
find . -maxdepth 3 -type f | sort
重点查看:
04_中间文本/
05_输出报告/
导师意见.md
会议纪要.md
审稿意见.md
目标期刊要求.md
如果已有:
04_中间文本/论文初稿.extracted.md
优先读取它。没有中间文本时,再从 Word 或 Markdown 草稿提取。
用全文搜索工具定位风险词:
rg -n "待补充|估算|预计|缺失|待插入|需检索|不完整|约|TODO|TBD" .
这些命中不是结论,只是审稿风险候选,需要读上下文后判断。
如果有文献证据匹配报告,先读取:
05_输出报告/文献证据匹配报告.md
若没有该报告,但草稿依赖大量引用,应建议先运行文献证据匹配技能。
默认写入:
05_输出报告/审稿人模拟检查报告.md
多轮测试可写为:
05_输出报告/审稿人模拟检查报告_第一轮.md
检查:
检查:
检查:
检查:
检查:
默认输出到:
05_输出报告/审稿人模拟检查报告.md
报告结构:
# 审稿人模拟检查报告
## 输入材料
## 总体判断
## 高优先级问题
| 问题 | 位置 | 风险 | 建议 |
|---|---|---|---|
## 证据和引用问题
## 实验和方法问题
## 结构问题
## 需要作者确认的问题
## 下一稿修改优先级
使用这些风险等级:
高:会严重影响投稿可信度,例如实验缺失、数据为估算值、核心公式缺失、关键引用不成立。中高:会明显削弱论文说服力,例如相关工作覆盖不足、图表缺失、研究问题和结论不对应。中:需要修改,但通常不单独构成拒稿理由。低:格式、表达、局部清晰度问题。paper-workbench。literature-evidence-matcher。development
Build or reorganize an academic paper project workspace with clear folders and local instructions for literature, drafts, feedback, extracted text, and output reports. Use when the user wants to set up a论文工作台, organize mixed manuscript materials, create project rules, or prepare a stable workflow before citation checking, evidence matching, reviewer simulation, or manuscript revision.
testing
Match manuscript claims against user-provided literature and produce a traceable claim-evidence table. Use when the user asks to add references, check whether PDFs support manuscript statements, find supporting or opposing evidence from a literature folder, distinguish strong support from background support, or create a 论点-证据匹配 report for an academic draft.
development
Twitter/X data via the 6551 API. Supports user profiles, tweet search, user tweets, follower events, deleted tweets, and KOL followers.
development
Crypto news search, AI ratings, trading signals, and real-time updates via the OpenNews 6551 API. Supports keyword search, coin filtering, source filtering, AI score ranking, and WebSocket live feeds.