legal-research-empirical
Skill2 starsChanged 3 months agoMITView on GitHub
为裁判文书和法律文本设计实证研究方案,批量导入DOCX、TXT或Markdown语料,建立编码手册、样本台账和可复现数据。用户要求裁判文书实证、内容分析或案例量化时使用。
In this repository9 other files it gives its agents.
The file
Files
法律实证研究
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。
读取 references/empirical-protocol.md。必须先固定研究方案和编码手册,再进行全量编码。
语料导入
legal-research --workspace "{workspace}" empirical ingest "{文件或目录}"
legal-research --workspace "{workspace}" empirical status --json导入器支持 UTF-8 TXT、Markdown 和 DOCX,按 SHA-256 去重。旧版 .doc、扫描PDF和加密文件应先转换或OCR,并保留原始文件映射。
编码要求
- 明确总体、抽样框、时间范围、法院层级、检索式和纳入排除规则。
- 编码本包含变量名、定义、类型、允许值、缺失值和判断例子。
- 先做小样本试编码;含主观判断的变量至少抽样双人复核并报告一致性。
- 原始语料只读保存,清洗、编码、分析和图表分别产出版本化文件。
- 模型抽取结果不能直接视为事实,关键变量必须进行抽样或全量人工核验。
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.

