Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NEU-ZHA/legal-ai-skills --skill pkulaw-mcp-law-retrievalgit clone --depth 1 https://github.com/NEU-ZHA/legal-ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/neu-zha/legal-ai-skills/pkulaw-mcp-law-retrieval)<a href="https://agentmods.dev/skills/neu-zha/legal-ai-skills/pkulaw-mcp-law-retrieval"><img src="https://agentmods.dev/badge/skills/neu-zha/legal-ai-skills/pkulaw-mcp-law-retrieval/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/neu-zha/legal-ai-skills/pkulaw-mcp-law-retrieval"><img src="https://agentmods.dev/badge/skills/neu-zha/legal-ai-skills/pkulaw-mcp-law-retrieval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00119 | $0.01737 |
| Opus 5.5 | $0.00048 | $0.00695 |
| Sonnet 5.5 | $0.00024 | $0.00347 |
| Haiku 4.5 | $0.00012 | $0.00174 |
Grade A, and why
pkulaw-mcp-law-retrieval scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
北大法宝 MCP：法律法规检索
这个 Skill 只负责一件事：把法规资料找出来，并按可复核的方式交给后续分析或答复环节。
它和 pkulaw-legal-search 不重复：本 Skill 只走原生 MCP 的法规/法条能力；MCP 不通、当前会话没加载对应工具、返回 401/403/超时/无结果、结果不足、需要网页详情页、登录态或 Computer Use 时，立即转 pkulaw-legal-search。
当前覆盖三个原生 MCP 服务：
| 路径 | serverId | 什么时候优先用 |
|---|---|---|
| 关键词检索 | law-keyword |
用户已给出法规标题词、正文关键词、概念词，希望返回列表 |
| 精准法条 | fatiao |
用户已给出法规名 + 条号，或需要核对条文原文 |
| 语义检索 | law-semantic |
两轮合理关键词仍无法覆盖自然语言问题，作为升级路径 |
如果任务已经明确是“只查案例”，请转到 pkulaw-mcp-case-retrieval。如果任务是“已知法规名 + 条号取全文”，优先走 fatiao；如果当前会话尚未暴露该 MCP，再用 law-keyword 找法规线索并转网页端详情页核对条号和原文。
先看边界
- 本 Skill 的目标是找依据，不是直接形成最终法律意见。
- 返回到的法规材料，仍需结合时效、层级、适用范围、特别法与一般法关系继续判断。
- 若用户要求形成可交付答复，应把检索结果继续交给组合型 Skill，而不是在这里直接扩写结论。
必须遵守的规则
- 具体法规名称、文号、条号或效力判断须有实际取得的可靠原文支持，用户材料和官方网页也可作为来源。
- 按实际取得的来源做摘要，不得用模型记忆补齐缺失依据，也不得将网页结果称为 MCP 返回。
- 关键词路径下，
title与fulltext至少有一项；具体参数名仍以tools输出为准。 - 认证失败、超时或工具不存在时停止该接口，按需用用户材料、官方网页或其他已授权来源继续；没有依据的部分标待核。正常返回但召回不足时按下列成本路由补检。
- 不得把
law-semantic当默认入口；它约 125 积分，只能在关键词路径不足且能说明缺口时升级一次。 - MCP 路由失败或结果不足时，默认转
pkulaw-legal-search的网页/Computer Use 流程继续核查。
默认路由
按下面顺序判断：
- 用户给的是明确词组、法规标题、正文关键词：
- 先走
law-keyword
- 先走
- 用户给的是明确法规名 + 条号：
- 先走
fatiao，当前实测工具名为get_law_item_content，参数为title和tiao_num
- 先走
- 用户给的是案情描述、业务问题、咨询问题：
- 先提炼 1-3 个关键词，再走
law-keyword
- 先提炼 1-3 个关键词，再走
- 关键词结果太少、过窄：
- 换法律全称/简称、制度名、核心行为、责任类型或相关主体再检索
- 两轮有理由的关键词仍缺少相关规范：
- 只升级调用一次
law-semantic，并记录为什么升级
- 只升级调用一次
不要因用户输入是自然语言就直接走语义检索。AI 本身可以先提炼关键词，通常 25 积分路径已经足够。
推荐工作流
- 先把用户需求收敛成“要找哪一类法规依据”。
- 选择
law-keyword。 - 用
tools确认真实<toolName>与参数名。 - 完成一次检索。
- 只整理当次返回里的标题、摘要、时效、链接等信息。
- 若结果不足，先做一次有理由的关键词补检索；仍不足才升级语义，不并发调用。
失败与降级
允许的失败输出
只允许类似下面的结构：
当前未拿到法宝法规检索结果。
失败原因：
- [未认证 / Token 失效 / 无订阅 / 无结果 / 工具不存在 / 命令报错]
建议动作：
- 检查 `pkulaw-mcp` 配置与 Token
- 检查对应服务是否已订阅
- 将问题改写得更具体后重试
允许的降级方式
law-keyword结果过宽 -> 增加标题词、正文词或限定法律部门law-keyword结果过窄 -> 换同义词、法律全称/简称、核心制度词后重试- 仍无结果 -> 尝试用户材料或可靠网页原文；仍无可靠依据时说明缺口，不生成无据结论
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 17d ago Changed 4273e75c174b
- 1mo ago First seen · 134 lines · 119 tokens per session scan A 5339789a8baa
pkulaw-mcp-law-retrieval is a skill published in the GitHub repository NEU-ZHA/legal-ai-skills (68 stars, last pushed 18d ago), licensed MIT. It adds 119 tokens to every session and 1,737 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
fto-triage
Freedom-to-operate triage — a structured first look at potentially blocking patents, not an FTO opinion. Use when a product, process, or feature is being evaluated for blocking patents, when asked whether anything stops a launch, or to build a claim-chart first pass against the most plausible patents before patent…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
terms-of-service
Draft terms of service and a companion privacy notice matched to the product's form and feature modules, not legal advice, delivered as a Word document.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
ai-risk-management
Apply the NIST AI Risk Management Framework (AI RMF 1.0) and adjacent guidance to AI / ML systems — model lifecycle governance, fairness and bias evaluation, robustness, transparency, accountability, third-party model risk, monitoring for drift, and AI incident response. Broader than prompt-injection (which is the…