dr-reconstruct
Skill0 starsChanged 6 months agoLicence not identifiedView on GitHub
Deep Research 报告重构与独立验证助手。支持两种模式：**轻量模式**针对纯学术 DR（<30 claim，PubMed 可查），通过 Entrez API 三重匹配独立验证；**战略模式**针对多域 DR（学术+FDA+财报+市场+临床+监管），通过 Phase 0/1/2/3 多层交叉 pipeline（Phase 1 并行 subagent 按域分工 + Phase 2 B/C 可选纠错/扩展 + Phase 3 主报告+URL 表+claim-diff+MANIFEST 多产物输出）。触发条件：用户提到"DR重构""deep research验证""核查DR报告""DR文献核查""验证deep research""重构报告""DR线索提取""侦察→验证""deep research可靠性""DR置信度""DR战略核查""战略地图核查""DR数字核查""多域DR核查"等关键词。也适用于"我有一份deep research报告，帮我验证里面的文献/数字/产品码/对标""这个DR报告靠谱吗""把DR的结果重新查一遍""用entrez重新搜一下这些文献"等场景。即使用户只说"这个DR报告靠谱吗"，也应触发本技能。
In this repository7 other files it gives its agents.
- ielts-sprint-coachSkill
- literature-managerSkill
- literature-search-omfsSkill
- ref-verifierSkill
- self-verifySkill
- thesis-critical-reviewSkill
- thesis-qcSkill
The file
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.