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 aia-generationgit 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/aia-generation)<a href="https://agentmods.dev/skills/zhou210712/claude-for-legal-zh/aia-generation"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/aia-generation/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/aia-generation"><img src="https://agentmods.dev/badge/skills/zhou210712/claude-for-legal-zh/aia-generation.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 | $0.00087 | $0.03180 |
| Opus 5.5 | $0.00035 | $0.01272 |
| Sonnet 5.5 | $0.00017 | $0.00636 |
| Haiku 4.5 | $0.00009 | $0.00318 |
Grade A, and why
aia-generation 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 1mo 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aia-generation
- 读取
~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md→ 监管注册表（适用法规、阈值、义务）、AI系统清单、科技伦理审查配置。 - 运行以下工作流。
- 判定走快速轨还是全面轨。提取系统描述 → 确定监管角色和风险等级 → 生成评估。
- 输出：定级 + 评估文件，包含具体行动项、负责人和截止日期。
/ai-governance-legal:aia-generation "客户信用评分模型 v2"
AI系统评估生成
事务上下文
事务上下文。 检查实践级 CLAUDE.md 中的 ## 事务工作区。如果 已启用 为 ✗（法务内部用户的默认值），跳过本段其余部分——技能使用实践级上下文，事务机制不可见。如果已启用且无活跃事务，询问："此事务属于哪个事务？运行 /ai-governance-legal:matter-workspace switch <slug> 或回答 实践级。" 加载活跃事务的 matter.md 获取事务特定上下文和覆盖项。将输出写入事务文件夹 ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/matters/<matter-slug>/。除非 跨事务上下文 为 开，否则绝不读取其他事务的文件。
目的
有些AI法规要求进行正式评估——在部署高风险系统之前、在商业模式变更之前、在训练数据或决策逻辑发生实质性变更时。此技能生成评估，并按法规要求保留记录。
适用法规
中国的AI治理框架由多个法规和规范性文件构成，根据系统类型和风险等级适用不同的评估要求：
- 《生成式人工智能服务管理办法》：面向公众提供生成式AI服务的，需进行安全评估和算法备案（第17条
[法条原文]） - 《科技伦理审查办法（试行）》：涉及生命健康、个人信息、社会公共利益等的科技活动需进行伦理审查
[法条原文] - 《互联网信息服务算法推荐管理规定》：使用算法推荐技术的，需进行算法备案（第24条
[法条原文]）和安全评估（第27条[法条原文]） - 《互联网信息服务深度合成管理规定》：提供深度合成服务的，需进行安全评估（第15条
[法条原文]） - 《个人信息保护法》：涉及个人信息处理的AI系统，需进行个人信息保护影响评估（第55-56条
[法条原文]）
加载当前状态
读取 ~/.claude/plugins/config/claude-for-legal/ai-governance-legal/CLAUDE.md：
## AI系统清单— 系统中每个AI系统的角色和等级## 监管注册表— 适用的法规及阈值## 科技伦理审查配置— 伦理审查委员会设置和审查触发条件
工作流
第1步：轨道判定
| 特征 | 快速轨 | 全面轨 |
|---|---|---|
| 系统类型 | 低风险内部工具（非面向公众） | 高风险系统或面向公众的系统 |
| 数据处理 | 不涉及个人信息或仅涉及内部员工数据 | 涉及用户个人信息、敏感个人信息或大规模数据处理 |
| 算法备案 | 无需备案 | 需要或可能需要进行算法备案 |
| 深度合成/生成式 | 不涉及 | 涉及生成合成内容或深度合成 |
| 评估历史 | 已有近期全面评估记录，仅作小幅更新 | 首次评估或实质性变更 |
如果系统明确匹配左列所有特征 → 快速轨。否则 → 全面轨。
第2步：监管角色判定
根据系统性质确定监管角色：
| 角色 | 定义 | 典型场景 |
|---|---|---|
| AI服务提供者 | 自主研发并向公众提供AI服务的主体 | 自研模型/SaaS AI产品 |
| AI服务使用者 | 使用第三方AI服务进行内部业务活动的主体 | 采购第三方AI能力嵌入自有业务流程 |
| 双重角色 | 同时具备提供者和使用者属性 | 基于第三方模型微调后对外提供服务 |
角色判定影响后续义务范围：
- 提供者：需进行算法备案、安全评估、内容标识，承担更重的合规义务（《生成式人工智能服务管理办法》第7-17条
[法条原文]） - 使用者：需确保合规使用、进行供应商尽职调查，但备案义务较轻
第3步：风险等级判定
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.
- 1mo ago First seen · 234 lines · 87 tokens per session scan A db1cac6e7072
aia-generation is a skill published in the GitHub repository zhou210712/claude-for-legal-ZH (238 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 87 tokens to every session and 3,180 once invoked, about $0.0003 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
prowler-compliance
Creates, syncs, audits and manages Prowler compliance frameworks end-to-end. Covers the two supported JSON schemas (universal multi-provider and legacy per-provider), the SDK model tree (legacy attribute classes, universal ComplianceFramework, ConfigRequirements guardrails), output formatters (legacy per-framework +…
policy
Define and enforce decision policies, compliance rules, and exceptions over Semantica graphs. Uses ContextGraph.checkdecisionrules/enforcedecisionpolicy and context.PolicyEngine.
ai-ethics-review
Conduct a structured ethical review of an AI or ML feature, model, or product. Use when preparing to deploy an AI system, assessing algorithmic risk, auditing a model for bias, or producing a responsible AI impact assessment. Produces a structured ethics review covering fairness, transparency, privacy, safety…
open-weights
Use when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping. Owns the license-class map (OSI-open versus custom-community versus non-commercial), the always-verify-the-model-card rule, size-to-VRAM…
801-regulations-eu-ai-act
Use when reviewing, designing, or modifying Java enterprise systems that use AI, LLMs, AI agents, RAG, tool calling, workflow automation, or model-based decision support and need EU AI Act regulatory awareness. This should trigger for requests such as Review a Java AI system for EU AI Act controls; Design governance…
813-regulations-iso-42001
Use when reviewing, designing, or modifying Java enterprise systems that use GenAI, LLMs, AI-assisted coding, RAG, AI agents, generated code, generated dependencies, prompt workflows, external model providers, or AI-enabled business logic and need ISO/IEC 42001 AI management system-aware engineering guidance. Part of…