Updated 3mo ago
by YouGram-001
legal-empirical-research-skills
裁判文书实证研究 Claude Code Skills 套件 — 对话驱动的法学实证研究工具包
20 GitHub stars (20)
Steady at 20 stars — no new stars in the 3 days since Oct 28.
- 7 skills (7 skills found in its SKILL.md files)
- 1 forks (1 forks)
- 3mo ago last update (Last updated 3mo ago)
Install
Skills CLI
npx skills add YouGram-001/legal-empirical-research-skills
Asks which skills and agents to install. Just one: npx skills add YouGram-001/legal-empirical-research-skills --skill data-cleaner — add -g for every project.
Claude Code
git clone https://github.com/YouGram-001/legal-empirical-research-skillscp -r "legal-empirical-research-skills/.claude/skills/data-cleaner" ~/.claude/skills/
Copies the data-cleaner skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add YouGram-001/legal-empirical-research-skills
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
data-cleaner
清洗裁判文书数据集。当用户提起以下关键词时触发：清洗数据、去重、数据清洗、 排除无效样本、关联案件归总、同案归总、事件归总ID、审级标注。 自动排除重复和残缺文书，生成事件归总ID，标注审级关系。
.claude/skills/data-cleaner/SKILL.md on GitHub (opens in a new tab) -
doc-converter
将裁判文书（.doc/.docx）批量转化为干净的纯文本（.txt）。 当用户提起以下任何关键词时触发：转格式、doc转文本、文档预处理、 格式转化、文书转化、word转txt、裁判文书处理。 自动检测文件格式，用 antiword/python-docx 转化，移除页眉页脚， 按裁判文书结构分段，提取元数据（案号、法院、日期等），生成索引表。
.claude/skills/doc-converter/SKILL.md on GitHub (opens in a new tab) -
generate-factors
从文献和数据中生成法学实证研究的主要因素。当用户提起以下关键词时触发： 分析主要因素、生成研究因素、文献分析、变量设计、研究方法、 设计变量框架、建立假设、确定自变量因变量、文献蒸馏、方法论分析。 从参考论文中蒸馏研究方法论，从清洗后的数据中做探索性分析， 交叉验证后生成推荐变量框架和可检验假设。
.claude/skills/generate-factors/SKILL.md on GitHub (opens in a new tab) -
info-extractor
从裁判文书中批量抽取结构化信息。当用户提起以下关键词时触发：信息抽取、 提取字段、批量提取、结构化数据、抽取关键信息、填充数据表、生成变量。 使用 Workflow 并行处理，自动生命周期管理，支持断点续传。
.claude/skills/info-extractor/SKILL.md on GitHub (opens in a new tab) -
label-unifier
统一开放文本字段的标签表述。当用户提起以下关键词时触发：统一标签、 合并同类表述、标签标准化、同义词归并、分类统一、规范标签。 对开放字段做频次统计，辅助识别同义词，生成 label_mapping.json。
.claude/skills/label-unifier/SKILL.md on GitHub (opens in a new tab) -
quality-checker
检验数据质量。当用户提起以下关键词时触发：质量检验、数据质量、 缺失率、准确率验证、质量报告、数据验证、抽样检查、幻觉检测。 统计缺失率 + 随机抽样对比原文检测 AI 幻觉 + 用户逐案确认编造， 发现编造自动加倍抽样迭代直到连续两轮清零。
.claude/skills/quality-checker/SKILL.md on GitHub (opens in a new tab) -
start-research
启动一个法学实证研究项目。当用户提起以下任何关键词时触发：做实证研究、 实证分析、处理裁判文书、分析判决书、法律实证、法学定量研究、法实证、 启动实证研究、开始处理文书。对话式引导用户完成研究设计、字段规划、 清洗规则确认，然后编排格式转化→数据清洗→信息抽取→标签统一→质量检验的全流程。
.claude/skills/start-research/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.
Similar skills
-
reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries.
-
ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod…
-
andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
-
ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
-
ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
-
graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs…