pkulaw-mcp-case-number
Skill65 starsChanged 4 months agoMITView on GitHub
案号识别与溯源,用于从文书、备忘、聊天记录或其他长文本中提取案号并回源案件线索。Use when:用户已经有一段文本,想识别其中的案号、批量抽取案号,或核查案号对应案件信息。NOT for:按争议主题检索案例、法条识别、法规主题检索。要求不得编造案号、法院名称与日期,全部基于当次 MCP 返回。
In this repository28 other files it gives its agents.
- case-retrieval-display-tableSkill
- docx-cnSkill
- docx-editingSkill
- docx-toolkitSkill
- evidence-catalog-generatorSkill
- legal-citation-automatorSkill
- legal-citation-comprehensiveSkill
- legal-fact-checkerSkill
- legal-homework-formatterSkill
- legal-toa-formatterSkill
- pkulaw-legal-searchSkill
- pkulaw-mcp-batch-contract-screeningSkill
- pkulaw-mcp-case-memoSkill
- pkulaw-mcp-case-retrievalSkill
- pkulaw-mcp-citation-validatorSkill
- pkulaw-mcp-contract-review-liteSkill
- pkulaw-mcp-doc-linkSkill
- pkulaw-mcp-fatiao-preciseSkill
- pkulaw-mcp-governance-research-memoSkill
- pkulaw-mcp-grounded-answerSkill
- pkulaw-mcp-installerSkill
- pkulaw-mcp-labor-employment-answerSkill
- pkulaw-mcp-law-recognitionSkill
- pkulaw-mcp-law-retrievalSkill
- pkulaw-mcp-legal-researchSkill
- pkulaw-mcp-opinion-citation-checkSkill
- pkulaw-mcp-regulatory-reply-checkSkill
- pkulaw-mcp-semantic-nlsqlSkill
The file
Files
北大法宝 MCP:案号识别与溯源(case-number)
这个 Skill 只负责一件事:从现有文本里识别案号,并给出可核查的案件线索。
它不负责替代案例实体分析。 如果用户真正要的是“找类似案例怎么判”,应转到案例检索或类案备忘 Skill。
先看边界
- 输出应理解为案号线索,而不是已经完成实体分析。
- 对格式不完整、年份缺失、法院简称缺失、OCR 噪声、批量文本混杂等情况,只能标成待核查线索。
- 不能把疑似案号写成已确认案件信息。
默认路由
- 文本里疑似包含案号:
- 走
case-number
- 走
- 用户只描述争议点,想找类案:
- 转
pkulaw-mcp-case-retrieval
- 转
推荐工作流
- 确认输入是待识别文本,而不是案例检索需求。
- 用
tools确认真实<toolName>与参数名。 - 提交文本进行案号识别。
- 输出识别到的案号列表和溯源命中情况。
- 对格式异常或歧义项标记“待人工确认”。
失败与降级
允许的失败输出
当前未拿到案号识别结果。
失败原因:
- [未认证 / 无订阅 / 无结果 / 工具不存在 / 命令报错]
建议动作:
- 检查 `pkulaw-mcp` 配置
- 检查文本中的案号格式和完整度
- 如真正需求是找类案,请改走案例检索路径允许的保守输出
- 对歧义项标记“待人工确认”
- 不得把疑似案号写成已确认事实
输出结构
- 识别到的案号列表
- 溯源命中情况
- 待人工确认项
终端复现与排障
如需在终端复现,请先安装 @pkulaw/mcp-cli;安装后命令为 pkulaw-mcp。
pkulaw-mcp tools case-number
pkulaw-mcp case-number <toolName> ... --json补充材料
- 示例见 examples.md
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.

