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 legal-fact-checkergit 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/legal-fact-checker)<a href="https://agentmods.dev/skills/neu-zha/legal-ai-skills/legal-fact-checker"><img src="https://agentmods.dev/badge/skills/neu-zha/legal-ai-skills/legal-fact-checker/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/legal-fact-checker"><img src="https://agentmods.dev/badge/skills/neu-zha/legal-ai-skills/legal-fact-checker.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 | $0.00147 | $0.03097 |
| Opus 5 | $0.00073 | $0.01548 |
| Sonnet 5 | $0.00029 | $0.00619 |
| Haiku 4.5 | $0.00015 | $0.00310 |
Grade A, and why
legal-fact-checker 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.
How it starts
The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legal Fact Checker — 法律产出事实核查技能
核心原则
一切法律产出必须有事实依据。禁止编纂案例、法规或事实。
本技能在法律相关任务中强制执行三道防线:
- 用户材料锚定——优先核对用户放在任务文件夹里的法规、案例、PDF、网页截图、数据库结果和 Word 文档
- 可用时回源——有北大法宝 MCP 或网页权限时再做回源核验;没有权限时标
[待补: 来源],不得声称已验证 - 无据声明——提交前自检,单独输出无据内容清单
工作流程
阶段一:文档转换与锚定(Document Anchoring)
当用户提供包含 PDF 或 Word 文件的文件夹时:
- 扫描文件夹:识别所有
.pdf、.docx、.doc文件 - 逐个转换:
- PDF 文件 → 优先使用
markitdown(对长文档更可靠,不易截断);如需版面还原则用PaddleOCR Document Parsing补充 - Word 文件 → 使用
docx或Docx Cnskill 转为 Markdown
- PDF 文件 → 优先使用
- ⚠️ 转换完整性验证(强制):转换完成后必须执行以下检查,不得跳过:
- 章节覆盖检查:提取 MD 中所有章节标题(
## Chapter、## 第X章等),与 PDF 目录页对照,确认最后一章在 MD 中存在 - 长度合理性检查:如果 MD 长度明显偏短(如只有预期的 60%),必须怀疑截断,用 markitdown 交叉验证
- 关键词锚定检查:如果用户问的是特定内容,搜索该内容是否在 MD 中出现;搜索未命中时,先怀疑解析不完整,再怀疑原文确实没有
- 双工具交叉验证:长 PDF(>30页)必须同时用 markitdown 和 PaddleOCR 转换,取内容更完整的版本
- 章节覆盖检查:提取 MD 中所有章节标题(
- 保留引用位置:转换后的 Markdown 必须标注原文出处位置(页码、段落号、章节标题),格式示例:
<!-- 来源:某某判决书.pdf 第3页 --> 原告[当事人A]于[日期]通过[交易/行为]取得[标的物]…… - 存储转换结果:将所有转换后的 MD 文件存放在工作目录的
_source_md/子文件夹中 - 锚定声明:在后续所有工作中,凡引用文件夹内容,必须能在
_source_md/中找到对应原文。不得凭记忆或推测补充细节。
⚠️ 如果文档转换失败或内容不完整,必须明确告知用户哪些部分未能转换,不得跳过此步骤直接开始写作。
🚫 绝对禁止:在未验证转换完整性的情况下,基于不完整的转换结果下"原文没有"的结论。这是已发生过的严重错误(2026-04-26:PaddleOCR 丢失 PDF 后半部分,直接得出"Outline 不含 Chapter 7-9"的错误结论)。
阶段二:内容撰写与引用纪律
在撰写法律文件时:
- 严格引用:所有事实陈述必须可追溯到
_source_md/中的原文、用户提供的数据库/网页材料,或经可用 PKULaw MCP/网页回源的来源 - 案例引用规则:
- 案号必须完整准确(如
(20XX)XX民初XXXXX号) - 当事人姓名必须与原文一致
- 判决结果、赔偿金额等数字必须逐字核对
- 不得凭印象编写案例细节
- 案号必须完整准确(如
- 法规引用规则:
- 法条编号必须准确(如《民法典》第148条,不是第147条)
- 法条内容必须与原文一致,不得意译后当作原文引用
- 引用具体款项时必须标注(如第1款、第2项)
- 标注来源:在写作过程中,对每个关键事实标注来源:
[来源:_source_md/判决书.md 第5页]—— 来自文件夹文档[来源:PKULaw MCP/网页回源通过]—— 经用户可用的法宝权限回源[待补: 来源]—— 未能找到来源或当前没有可用回源权限(必须在最终提交前处理)
阶段三:PKULaw 回源(可用时)
北大法宝是增强回源工具,不是使用本 skill 的安装前提。核验顺序如下:
-
先核用户给出的来源:
- 如果用户已经把法规、案例、PDF、网页截图、数据库结果放进文件夹,先逐字核对这些材料。
- 不要因为没有联网或没有 MCP,就重新编造来源或跳过本地来源核验。
-
有基础 PKULaw MCP 时再回源:
- 法规或规范性文件:用
law-keyword/get_law_list找法规线索。 - 已知法规名和条号:用
fatiao/get_law_item_content核对条文原文。 - 案例线索:用
case-keyword/get_case_list检索案例列表,并核对案名、法院、案号、日期和相关段落。
- 法规或规范性文件:用
What ships with it
1 file 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 · 200 lines · 147 tokens per session scan A 222997230a1b
legal-fact-checker is a skill published in the GitHub repository NEU-ZHA/legal-ai-skills (64 stars, last pushed 23d ago), licensed MIT. It adds 147 tokens to every session and 3,097 once invoked, about $0.0007 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…