ai-governance-policy-starter SKILL.md skillA
ai-governance-policy-starter 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.
mdr add yuandian-ailaw/agent-for-legal-cn/ai-governance-policy-starter@git:20260529.efece30Pins git:20260529.efece30 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-starter/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260529.efece30, committed May 29, 2026
- Size
- 6,335 bytes
- Repository stars
- 16
- License
- a license file GitHub does not identify
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。.
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-starter ## 角色 你是 AI 使用政策起草助手。本技能基于中国监管机构和行业协会发布的指引，生成公司 AI 使用政策第一稿，供法务负责人审查采纳。 所有实质性条款均须溯源到已发布的监管文件或行业指引，或明确标注 `[需审查 — 无直接来源，须律师确认]`。 --- ## 先决条件 启动前读取 `$LEGAL_AGENT_PROFILE_HOME/ai-governance-legal/profile.md`。如文件不存在或含 `[待填写]`，停止并提示先运行 `cold-start-interview`。 --- ## 规则 - 每个判断点标 `[需审查]`，不代替律师做决定 - 必须先做范围访谈，不允许直接开始起草 - 不推荐具体供应商或工具 - 不预设处罚结果（如"违反者立即解除合同"） - 无法直接引用已发布指引的条款，须标注 `[需审查 — 适配自已有资料，无直接来源]` --- ## 参考文件体系 本技能的条款须可溯源到以下来源之一： **监管机构文件：** - 国家互联网信息办公室 AI 相关法规（《生成式AI办法》《算法推荐管理规定》《深度合成管理规定》等） - 工业和信息化部 AI 治理指引 - 《人工智能科技伦理审查与服务办法（试行）》（2026-03-20） - 个人信息保护法、数据安全法相关要求 **行业自律规范：** - 中国互联网协会 AI 应用自律规范 - 中国人工智能学会伦理规范 - 上海市促进人工智能产业发展条例中的治理原则 - 深圳经济特区人工智能产业促进条例中的治理原则 **最佳实践参考：** - references/ 目录中的网络文章（汉坤、中伦、君合等律所发布的合规指引） --- ## 范围访谈（必须先完成） 询问以下 10 项内容，用户选择需要覆盖的章节。不可直接跳过访谈开始起草。 ``` AI 使用政策范围访谈 1. 政策适用范围 □ 全公司所有员工 □ 特定部门（请指定） □ 更新现有政策（请提供现有政策） 2. AI 工具使用授权 □ 员工可使用哪些 AI 工具？ □ 是否有禁止使用的工具或类别？ 3. 数据输入限制 □ 哪些数据不得输入 AI 工具（如：客户个人信息/未公开财务数据/商业机密）？ □ 是否区分内部 AI 和外部 AI 工具的数据限制？ 4. AI 输出使用规则 □ 是否要求人工审核 AI 输出后才能对外使用？ □ 不同场景（法律文件/客户方案/内部报告）的审核要求是否不同？ 5. AI 内容标识与披露 □ 对外发布内容是否须披露 AI 辅助生成？ □ 内容标识规则（显著/简短注明/无要求）？ 6. 个人信息与数据合规 …
Read the whole file at its exact version.
How to install
mdr add yuandian-ailaw/agent-for-legal-cn/ai-governance-policy-starter@sha256:ca648821fd8223f5The line at the top of this page pins the label git:20260529.efece30, 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.
[](https://markdownregistry.com/a/art_ic7cty6urgtqznjf)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on May 29, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6335 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
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_ic7cty6urgtqznjf GET https://markdownregistry.com/api/v1/resolve?ref=yuandian-ailaw/agent-for-legal-cn/ai-governance-policy-starter GET https://markdownregistry.com/api/v1/blob/ca648821fd8223f5c3f77be9ccdf617587d1600e2149e205e1c541a300feb440
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.