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-semantic-nlsqlgit 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-semantic-nlsql)<a href="https://agentmods.dev/skills/neu-zha/legal-ai-skills/pkulaw-mcp-semantic-nlsql"><img src="https://agentmods.dev/badge/skills/neu-zha/legal-ai-skills/pkulaw-mcp-semantic-nlsql/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-semantic-nlsql"><img src="https://agentmods.dev/badge/skills/neu-zha/legal-ai-skills/pkulaw-mcp-semantic-nlsql.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 | $0.00102 | $0.01170 |
| Opus 5 | $0.00051 | $0.00585 |
| Sonnet 5 | $0.00020 | $0.00234 |
| Haiku 4.5 | $0.00010 | $0.00117 |
Grade A, and why
pkulaw-mcp-semantic-nlsql 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 12d 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.
What it actually says
北大法宝 MCP：语义检索（semantic-nlsql）
这个 Skill 只负责一件事：用一次自然语言检索，先把跨库候选材料召回出来。
它适合做经济型检索后的升级路径，不替代法规检索、案例检索、精准法条回源或引用核验。默认先尝试拆分问题，分别调用 law-keyword 和 case-keyword；只有无法可靠拆分或仍有关键缺口时才使用本 Skill。
使用前必须检查
- 已配置
serverPaths.semantic-nlsql pkulaw-mcp tools semantic-nlsql能正常返回- 控制台已开启对应服务、Token 可用
如果上面任何一点不成立，必须停止继续使用本 Skill，并提示用户先配置或改走其他 Skill。
先看边界
- 本 Skill 的长处是综合召回，不是最终结论生成器。
- 召回结果必须继续做分流、核验、收窄，不得直接包装成确定法律意见。
- 如果问题本来就只是查法规或只是查案例，优先用更窄的 Skill，而不是为了“高级”强行走 NL-SQL。
默认路由
符合下面条件时才用 semantic-nlsql：
- 问题同时跨法规、案例、法条或多类材料，而且无法可靠拆成定向关键词路径
- 已用
law-keyword/case-keyword做过有理由的检索，仍有影响结论的关键缺口
不符合时，直接改走：
- 法规问题 -> pkulaw-mcp-law-retrieval
- 案例问题 -> pkulaw-mcp-case-retrieval
推荐工作流
- 先确认经济型定向检索不足，并写明尚缺什么。
- 确认配置与工具可用。
- 用自然语言完整表达问题，完成一次综合检索。
- 按返回内容分成法规、案例、法条或其他候选。
- 明确告诉用户：这是“综合召回结果”，不是最终定论。
- 必要时把候选继续转交给更窄的 Skill 做二次检索。
失败与降级
配置缺失
只允许输出类似下面的结构：
当前无法使用 `semantic-nlsql`，因为实例路径尚未完成配置。
建议动作：
- 先配置 `serverPaths.semantic-nlsql`
- 执行 `pkulaw-mcp tools semantic-nlsql` 验证
- 如暂不配置，可改用法规语义检索与案例语义检索分别完成
401/403 或无结果
当前未拿到 semantic-nlsql 的有效检索结果。
失败原因：
- [未认证 / 无订阅 / 无结果 / 命令报错]
建议动作：
- 检查 Token 与订阅状态
- 调整自然语言问题表述
- 改走法规或案例的窄路径检索
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 semantic-nlsql
pkulaw-mcp semantic-nlsql <toolName> --json
说明：
<toolName>必须以tools输出为准- 不要在文档中写死
ai_pkulaw_search等工具名
输出结构
按下面结构输出最稳：
- 问题重述
- 前置检查结果
- 综合召回摘要
- 建议的下一步分流
- 局限说明
补充材料
- 示例见 examples.md
- 法规检索见 pkulaw-mcp-law-retrieval
- 案例检索见 pkulaw-mcp-case-retrieval
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.
- 12d ago First seen · 118 lines · 102 tokens per session scan A 1dcc6fc14551
pkulaw-mcp-semantic-nlsql is a skill published in the GitHub repository NEU-ZHA/legal-ai-skills (64 stars, last pushed 23d ago), licensed MIT. It adds 102 tokens to every session and 1,170 once invoked, about $0.0005 per session on Opus 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
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.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
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.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…