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 zhou210712/claude-for-legal-ZH --skill use-case-triagegit clone --depth 1 https://github.com/zhou210712/claude-for-legal-ZHWrote 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/zhou210712/claude-for-legal-zh/use-case-triage)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/use-case-triage"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/use-case-triage/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/zhou210712/claude-for-legal-zh/use-case-triage"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/use-case-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00091 | $0.02389 |
| Opus 5 | $0.00046 | $0.01195 |
| Sonnet 5 | $0.00018 | $0.00478 |
| Haiku 4.5 | $0.00009 | $0.00239 |
Grade A, and why
use-case-triage 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/use-case-triage
- 读取
~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md→ 已注册的AI系统、红线清单、审批工作流。 - 运行以下工作流。
- 如果注册表中已有匹配项 → 返回当前状态,不重新分类。
- 如果没有匹配项 → 按风险层级分类:检查红线 → 残余风险分级 → 输出分类和理由。
/ai-governance-legal:use-case-triage "用用户行为数据训练一个推荐模型"
AI用例分类
目的
业务团队提出一个AI功能。在投入工程时间之前,需要知道该功能是否可行、是否有附加条件、或是否完全不可行。此技能对新提议的AI用例进行结构化分类,依据你已配置的红线和既有批准记录进行复核。
加载当前状态
读取 ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md:
## AI系统清单— 已批准、已附条件或已拒绝的系统## 红线— 绝对禁止的用例或技术## 算法备案— 已完成的算法备案记录(依据《互联网信息服务算法推荐管理规定》第24条[法条原文])## 监管注册表— 适用的AI法规(《生成式人工智能服务管理办法》、《科技伦理审查办法(试行)》[法条原文])
工作流
第1步:注册表检索
搜索 ## AI系统清单 中是否有匹配项。匹配标准:
- 相同的数据类别和处理目的
- 相同的部署环境(内部 vs 面向公众)
- 相同的受影响人群
如果找到精确匹配 → 返回当前分类和日期。不重新分类。如果找到部分匹配 → 标记相似用例以供参考,但不阻 止新的分类。
第2步:红线检查
按照 ## 红线 清单逐项核查提议的用例。红线是绝对禁止的——一旦触发,分类即终止,结果为不核准。常见红线类别:
- 社会信用评估:涉及对自然人进行社会信用评分(《生成式人工智能服务管理办法》第4条
[法条原文]) - 算法歧视:基于种族、民族、宗教信仰、性别、年龄等因素对用户实行不合理差别待遇(《互联网信息服务算法推荐管理规定》第10条
[法条原文]) - 侵害个人信息权益:未取得个人同意或超出必要范围使用个人信息进行AI训练(《个人信息保护法》第13-17条
[法条原文]) - 安全与公共利益风险:涉及国家安全、公共安全、社会公共利益造成实质性威胁的用例
- 科技伦理禁止领域:严重违反科技伦理原则的研发活动(《科技伦理审查办法(试行)》
[法条原文]) - 以操纵舆论为目的:利用算法实施舆论操纵、虚假信息传播或扰乱社会秩序
如果触发红线 → 分类结果:不核准。附书面理由、引用的法规条文及红线来源。
第3步:残余风险分级
对未触发红线的用例,从以下维度评估残余风险:
| 维度 | 低风险指征 | 高风险指征 |
|---|---|---|
| 受影响人群 | 仅内部员工,非敏感角色 | 公众用户、未成年人、弱势群体 |
| 决策影响 | 非实质性(界面排序、内容推荐) | 对权利或利益有法律或实质性影响(信贷、就业、教育) |
| 自动化程度 | 人工在环,AI为辅助 | 全自动化,无人工审核 |
| 数据敏感性 | 非个人信息或已脱敏数据 | 敏感个人信息、生物识别、行踪轨迹 |
| 透明度 | 易于向用户解释,可公开说明 | 黑箱模型,难以解释决策逻辑 |
| 模型来源 | 自主研发或可控 | 第三方接口,训练和更新流程不透明 |
| 算法备案状态 | 无需备案或已完成备案 | 需要备案但未备案(《互联网信息服务算法推荐管理规定》第24条 [法条原文]) |
模式检测:如果用例匹配以下高风险模式之一,自动建议附条件分类(即使其他维度风险较低):
- 生成合成:生成合成文本、图像、音视频并向公众开放 → 需满足《生成式人工智能服务管理办法》第7条(训练数据合法性)、第15条(内容标识)
[法条原文] - 算法推荐:应用算法推荐技术提供互联网信息服务 → 需完成算法备案(《互联网信息服务算法推荐管理规定》第24条
[法条原文]) - 自动化决策:在交易价格等交易条件上实行不合理的差别待遇 → 需确保公平性和透明度(《互联网信息服务算法推荐管理规定》第21条
[法条原文]) - 向公众开放:面向不特定公众提供服务 → 需进行安全评估和科技伦理审查(《科技伦理审查办法(试行)》
[法条原文]) - 深度合成:提供深度合成服务 → 需进行内容标识(《互联网信息服务深度合成管理规定》第16-17条
[法条原文])
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 · 163 lines · 91 tokens per session scan A cf1be4634f9d
use-case-triage is a skill published in the GitHub repository zhou210712/claude-for-legal-ZH (212 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 2,389 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…