legal-research-authorship
Skill2 starsChanged 3 months agoMITView on GitHub
审查并修订法律论文中的模板化、机械化和无依据表达,强化作者真实判断、材料来源与论证过程。用户要求降低AI感、减少模型腔、润色学术中文、检查作者性或投稿前表达时使用;不得用于伪造人类作者身份或承诺绕过AI检测。
In this repository9 other files it gives its agents.
The file
Files
论文作者性与表达审查
开始前完整读取并遵守 ../legal-research/references/interaction-protocol.md,先解释当前步骤,结束时说明结果、作用和下一步,不向用户粘贴原始 JSON。
目标是让论文忠实呈现作者的材料、立场和推理,而不是模仿某种“人类文本”表面特征。开始前完整读取 references/authorship-protocol.md。
边界
- 不输出“AI生成概率”,不保证通过任何检测器,也不针对某个检测器调词。
- 不采用同义词轮换、故意错别字、虚构个人经历、伪造访谈或假造细节来掩饰文本来源。
- 不改变法律结论、规范立场、数据、引文含义和专业术语以换取所谓“低AI率”。
- 如果学校、期刊或机构要求披露AI辅助,提醒作者按适用规则如实披露。
工作流
- 读取全文、项目命题、证据台账和目标体例,区分来源事实、文献观点、作者推论、作者规范判断和待核内容。
- 建立
artifacts/author-decisions.md,记录四项必须由作者确认的内容:核心命题、规范立场、对最强反方的回应、研究局限。 - 逐段检查是否有新材料或新推理。只有复述提纲、重复结论或使用空泛过渡的段落应删除、合并或补证。
- 在不损害准确性的前提下调整句法和节奏。优先明确“谁依据什么作出何种判断”,保留必要法律术语。
- 对所有新增事实、数字、引语、判例评价和因果判断回到来源核验。无法核验时标记
[待核验],不得用流畅表达掩盖证据缺口。 - 运行表面机械性扫描:
legal-research prose audit "{draft}" --json- 对每条提示作语境判断,不机械全改。完成后登记作者决定文件与修订稿:
legal-research --workspace "{workspace}" artifact set --name author-decisions --path "{decisions}" --copy
legal-research --workspace "{workspace}" artifact set --name draft --path "{revised-draft}" --copy- 转入
legal-research-review做来源、论证、方法和引注审查。
扫描器只识别预设的表面模式。低分不能证明文本由人撰写,高分也不能证明文本由AI生成。
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.

