ai-governance-policy-monitor SKILL.md skillA

ai-governance-policy-monitor from yuandian-ailaw/agent-for-legal-cn is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add yuandian-ailaw/agent-for-legal-cn/ai-governance-policy-monitor@git:20260910.aea2351

Pins git:20260910.aea2351 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
yuandian-ailaw/agent-for-legal-cn
Path
legal-skillpack-ai-governance-legal/skills/ai-governance-policy-monitor/SKILL.md
Versions recorded
2
Latest version
git:20260910.aea2351, committed Sep 10, 2026
First version recorded
May 29, 2026
Size
5,242 bytes
Repository stars
16
License
a license file GitHub does not identify

扫描已保存的评估和审查结果,发现 AI 政策与实际做法之间的漂移,或直接检查拟议做法。 本 skill 仅覆盖中国大陆 AI 治理法规——其他法域 AI 治理请走当地服务或律所。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# /policy-monitor

## 角色

你是 AI 治理政策一致性监察员。本技能追踪公司内部 AI 政策(记录在 `$LEGAL_AGENT_PROFILE_HOME/ai-governance-legal/profile.md`)与实际 AI 做法(记录在 `$LEGAL_AGENT_LOCAL_DATA_HOME/ai-governance-legal/ai-systems.yaml` 和历史评估文件)之间的漂移,及时发现政策滞后或实践越界。

---

## 先决条件

启动前读取 `$LEGAL_AGENT_PROFILE_HOME/ai-governance-legal/profile.md` 和 `$LEGAL_AGENT_LOCAL_DATA_HOME/ai-governance-legal/ai-systems.yaml`。如 `$LEGAL_AGENT_PROFILE_HOME/ai-governance-legal/profile.md` 不存在或含 `[待填写]`,停止并提示先运行 `cold-start-interview`。

---

## 两种运行模式

### 模式 A:直接查询(默认)

用户描述一个拟议做法,直接对照 `$LEGAL_AGENT_PROFILE_HOME/ai-governance-legal/profile.md` 中的政策承诺进行 diff:

**流程:**
1. 理解拟议做法(如有模糊,最多问 2 个澄清问题)
2. 在 `$LEGAL_AGENT_PROFILE_HOME/ai-governance-legal/profile.md` 中找出所有相关政策条款
3. 逐条 diff:做法 vs 政策要求
4. 输出一致性结论 + 建议

---

### 模式 B:扫描模式(`--sweep`)

扫描所有已保存的治理文件,提取新批准的做法,检查是否产生政策漂移。

**扫描范围:**
- `$LEGAL_AGENT_LOCAL_DATA_HOME/ai-governance-legal/ai-systems.yaml`:当前所有 AI 系统的状态和合规备注
- `$LEGAL_AGENT_PROFILE_HOME/ai-governance-legal/profile.md` 用例注册表:已分类的用例及其条件
- 上次扫描后新增的系统或变更记录

**扫描维度:**

**1. 政策覆盖缺口扫描**
检查是否有系统已在使用但未被 AI 政策覆盖:
- 新增系统的业务类型是否在政策中有对应条款?
- 有条件审批的用例的条件清单是否已落实?

**2. 供应商立场漂移扫描**
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add yuandian-ailaw/agent-for-legal-cn/ai-governance-policy-monitor@sha256:739b66672d6b3ae1

The line at the top of this page pins the label git:20260910.aea2351, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_chyxhe5qyktzuqob.svg)](https://markdownregistry.com/a/art_chyxhe5qyktzuqob)

3 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between May 29, 2026 and Sep 10, 2026, about one every 104 days.

versioncommittedcommitsizeaudit
git:20260910.aea2351 latest2026-09-10 aea2351 5,242 BA view · diff
git:20260529.efece302026-05-29 efece30 5,249 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (5242 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

yuandian-ailaw/agent-for-legal-cn · 16 stars · license a license file GitHub does not identify · pushed 2026-09-10 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_chyxhe5qyktzuqob
GET https://markdownregistry.com/api/v1/resolve?ref=yuandian-ailaw/agent-for-legal-cn/ai-governance-policy-monitor
GET https://markdownregistry.com/api/v1/blob/739b66672d6b3ae1ace274502434347c3a2ee2a4054652f82ddd270ccf4e908f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from yuandian-ailaw/agent-for-legal-cn

ai-governance-aia-generation SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-ai-governance-legal/skills/ai-governance-aia-generation/SKILL.md · 生成 AI 系统合规评估文档,含监管分类、风险分析和建议。 本 skill 仅覆盖中国大陆 AI 治理法规——其他法域 AI 治理请走当地服务或律所。
git:20260910.aea2351 · audit A · 16 stars
ai-governance-cold-start-interview SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-ai-governance-legal/skills/ai-governance-cold-start-interview/SKILL.md · 初始化访谈,将业务规范写入 $LEGAL_AGENT_PROFILE_HOME/ai-governance-legal/profile.md。所有其他技能的先决条件。 本 skill 仅覆盖中国大陆 AI 治理法规——其他法域 AI…
git:20260910.aea2351 · audit A · 16 stars
ai-governance-customize SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-ai-governance-legal/skills/ai-governance-customize/SKILL.md · 对 AI 治理合规 profile 做单点调整——不需要重跑整个 cold-start 访谈。可调公司基础信息、AI 活动角色(Provider/Deployer)、监管足迹、红线清单、用例注册表、供应商立场、政策承诺、备案状态、集成状态…
git:20260910.e804a64 · audit A · 16 stars
ai-governance-inventory SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-ai-governance-legal/skills/ai-governance-inventory/SKILL.md · 管理 AI 系统合规清单,按中国法规框架对每个系统进行类型和风险层级分类。 本 skill 仅覆盖中国大陆 AI 治理法规——其他法域 AI 治理请走当地服务或律所。
git:20260910.aea2351 · audit A · 16 stars
ai-governance-policy-starter SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-ai-governance-legal/skills/ai-governance-policy-starter/SKILL.md · 参照已发布的监管指引和行业规范,生成 AI 使用政策草稿供律师审查。 本 skill 仅覆盖中国大陆 AI 治理法规——其他法域 AI 治理请走当地服务或律所。
git:20260529.efece30 · audit A · 16 stars
ai-governance-reg-gap-analysis SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-ai-governance-legal/skills/ai-governance-reg-gap-analysis/SKILL.md · 将新 AI 法规或监管要求与现有治理状态进行差距分析,输出修复计划。 本 skill 仅覆盖中国大陆 AI 治理法规——其他法域 AI 治理请走当地服务或律所。
git:20260910.aea2351 · audit A · 16 stars
ai-governance-use-case-triage SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-ai-governance-legal/skills/ai-governance-use-case-triage/SKILL.md · 对拟议 AI 用例进行合规分类:审批通过 / 有条件审批 / 不审批。 本 skill 仅覆盖中国大陆 AI 治理法规——其他法域 AI 治理请走当地服务或律所。
git:20260910.aea2351 · audit A · 16 stars
ai-governance-vendor-ai-review SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-ai-governance-legal/skills/ai-governance-vendor-ai-review/SKILL.md · 审查供应商 AI 协议条款,重点检查数据出境、训练数据使用、境内存储等中国法合规要点。 本 skill 仅覆盖中国大陆 AI 治理法规——其他法域 AI 治理请走当地服务或律所。
git:20260529.efece30 · audit A · 16 stars
commercial-amendment-history SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-commercial-legal/skills/commercial-amendment-history/SKILL.md · 追溯合同从基础协议到所有修订的变更轨迹——可以是所有变更的时间线摘要, 也可以是特定条款的追踪。当用户说"这个合同历次改了什么""显示修订历史" "最新的[条款]在哪里""[条款]如何演变的"或上传多个版本的协议时使用。
git:20260529.efece30 · audit A · 16 stars
commercial-cold-start-interview SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-commercial-legal/skills/commercial-cold-start-interview/SKILL.md · 运行冷启动访谈以了解你的商事合同实务并写入团队业务领域配置。在首次使用插件时、 配置文件缺失或仍为模板占位符时、或当用户说"设置插件""配置商事合同" "引导我""我们开始吧"时使用。这是全新安装时应运行的唯一技能。
git:20260529.efece30 · audit A · 16 stars
commercial-customize SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-commercial-legal/skills/commercial-customize/SKILL.md · 商事合同业务领域配置的引导式定制——修改一项配置而无需重新运行完整的冷启动访谈。 调整风险姿态、上报联系人、审查指引立场、保密协议分类偏好、行文风格、 审查偏好或事项工作区路径。当用户说"改一下我的[某配置]""更新我的配置"…
git:20260529.efece30 · audit A · 16 stars
commercial-escalation-flagger SKILL.md skill
yuandian-ailaw/agent-for-legal-cn · legal-skillpack-commercial-legal/skills/commercial-escalation-flagger/SKILL.md · 根据审查指引中的上报矩阵将合同问题路由至合适的审批人,并起草上报说明。 当用户说"谁需要批准这个""上报这个""这个需要法务负责人签字吗" "路由这个去审批"或当其他技能发现超出审查者权限的问题时使用。
git:20260529.efece30 · audit A · 16 stars

Every file in yuandian-ailaw/agent-for-legal-cn

Browse by kind, by grade A, or by owner.