凡自治之物 · LGD 治理学 · 创造术家族 | 评测协议:skill-quality-gate
English
When to use
- When a user asks about AI-system compliance, governance-level assessment, or whether an agent needs safety guardrails.
- When the "registered · evidenced · gated" framework must be landed, turning the LGD three laws into a self-scoring standard rubric.
- When the user provides a system description and wants an LGD-based compliance-audit scorecard with concrete improvement suggestions.
Usage
- Script: run
python lgd_audit.py(or the related CLI) in the runtime to start the audit logic. - Input:
<system_description>is the core required argument — describe the AI system's architecture, business logic or governance state; natural-language input is auto-parsed. - The skill reads the local script
lgd_audit.pyand the standard library; output is a JSON scorecard plus a text report, embeddable in CI/CD.
Workflow
- Intent detection: the system sees triggers like "LGD three laws" or "AI compliance self-check" and enters audit mode.
- Element extraction: pull identity (registered), evidence (evidenced) and gate-process (gated) info from the description.
- Scoring: run
lgd_audit.py; the internal engine computes the "four registrations" and "four gates" compliance scores from the LGD definitions. - Report: emit a structured scorecard with defect points, a missing-evidence list and governance-gap analysis.
- Improvement: guide the user to complete identity/lineage, archive key artifacts or add review-gate nodes.
- Closed loop: suggest the user revise the description per the report and re-run, verifying the three laws now hold locally.
Evidence & safety statement
- Evidence: TBD (no evaluation / badge link yet; update here once it is produced)
- Version: 1.0.1
- Security: no independent security scan has been performed (TBD); the conclusion is pending and no endorsement is given until it is completed.
中文
何时用
- 当用户咨询 AI 系统合规性、治理水平评估或是否需要为 Agent 部署安全护栏时。
- 当需要落地『有籍·有证·有门禁』治理框架,将 LGD 三律转化为可自评分标准 rubric 时。
- 当用户提供系统描述,希望获得基于 LGD 标准的合规审计评分及具体的改进项建议时。
用法
- 脚本命令:在运行环境调用
python lgd_audit.py或相关 CLI 接口直接启动审计逻辑。 - 输入参数:<system_description> 为核心必填参数,描述待评估的 AI 系统架构、业务逻辑或治理现状;支持自然语言输入自动解析。
- 文档交互:技能核心读取本地脚本
lgd_audit.py及标准库,输出为 JSON 评分卡与文本报告,可嵌入到 CI/CD 流程中。
流程
- 意图识别:系统检测到「LGD 三律」「AI 合规自评」等触发词,确认进入审计模式。
- 要素提取:从输入描述中提取身份(有籍)、证据(有证)及门禁流程(门禁)相关信息。
- 标准评分:运行
lgd_audit.py,内部引擎依据 LGD 定义计算「四登记」与「四道门」的合规分。 - 报告生成:输出包含缺陷点、缺失证据清单及治理缺口分析的结构化评分卡。
- 改进执行:指导用户在系统中补全身份血缘、归档关键工件或增加评审门禁节点。
- 闭环确认:建议用户根据报告修正描述并再次调用,验证 LGD 三律已在本地落地生效。
证据与安全声明
- 证据:TBD(暂无评测/徽章链接;产生后在此更新实际链接)
- 版本:1.0.1
- 安全:未做独立安全扫描(TBD),结论待补;补全前不作推荐背书。
