按中国法规（网安法 / PIPL / 等保2.0 / 数据出境 / AI生成内容标识）审计一个 AI 项目的代码仓库，产出每条都带 文件:行 取证、经独立复核、经脚本校验的合规报告。当用户问「这个项目上线合不合规」「调用了 OpenAI/Claude 算不算数据出境」「要不要做 AI 标识」「帮我做合规自查/等保/PIPL 检查」时使用。Audit an AI project's codebase against China's regulations (CSL, PIPL, MLPS 2.0, cross-border data transfer, AI content labeling) with file:line evidence, independent verification and a deterministic validator.
安装
npx skills add jnMetaCode/shellward --skill china-ai-compliance-auditnpx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a claude-code -gnpx skills add jnMetaCode/shellward --skill china-ai-compliance-audit -a codex -ggemini skills install https://github.com/jnMetaCode/shellward.git --path skills/china-ai-compliance-auditgh skill install jnMetaCode/shellward china-ai-compliance-auditgit clone --depth 1 https://github.com/jnMetaCode/shellward /tmp/jnMetaCode__shellward
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/jnMetaCode__shellward/skills/china-ai-compliance-audit ~/.claude/skills/china-ai-compliance-audit # Claude Code
cp -R /tmp/jnMetaCode__shellward/skills/china-ai-compliance-audit ~/.agents/skills/china-ai-compliance-audit # Codex, Cursor, Gemini CLI, Copilot, OpenCode