gov-disclosure-check

零依赖 Python 命令行工具，对政务公开文本或系统数据校验决策依据、责任部门、时限、救济渠道、数据来源等强制披露字段，对照 LGD 三律给出通过/失败结论、违规明细与整改建议，标准输出为 JSON 并附带退出码。

zhaoxinghua09-cell

热度 62.13

最近更新 2026-10-17 07:32:39

分类：安全依赖：代码执行 / 读写文件应用场景：法律文档 / 报告撰写 / 数据处理

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add gov-disclosure-check

Metadata

name: gov-disclosure-check
description: gov-disclosure-check — LGD 三律在政务 / 信息公开披露域的纵深合规工具（零依赖）：强制披露字段校验（决策依据/责任部门/时限/救济渠道/数据来源），对 AI 系统/数据做可执行合规校验。适用场景：当需要政务公开披露校验能力时使用本技能；触发词：gov-disclosure-check。
slug: gov-disclosure-check
version: 1.0.1
display_name: 政务公开披露校验
display_name_en: Gov Disclosure Check
agent_created: true
author: 诺声(Logos)@SynomosAI
license: MIT
license_scope: 代码（.py 文件）MIT；本 SKILL.md 与其中理论文本不在 MIT 覆盖范围内（见文末「License & attribution」）
allowed-tools: Read, Glob, Grep, Bash, Write, WebFetch
category: AI 治理
platforms: ["windows","macos","linux"]
copyright: SynomosAI
description_zh: gov-disclosure-check — LGD 三律在政务 / 信息公开披露域的纵深合规工具（零依赖）：强制披露字段校验（决策依据/责任部门/时限/救济渠道/数据来源），对 AI 系统/数据做可执行合规校验。
description_en: LGD three-laws compliance for government information disclosure (zero-dependency): mandatory fields such as decision basis, responsible department, deadline, remedy channel and data source.
classification: {"skillhub":["security-compliance"],"iso_25010":["Security"]}
risk_tier: medium
risk_rationale: 门禁批量补丁默认 medium（按默认策略设计为中等风险）：调用 API/读写文件/本地执行，最小权限，密钥走 Secret；若实际涉对外代执行(push/发布/发送/上架)须人工复评，改 high 并走人工批准。
tags: ["gov-disclosure-check","AI 治理","政务公开","强制披露"]
read_when: ["AI 生成政务公文/政策解读/决策报告前要核强制披露字段","处理信息公开申请时实时校验数据来源与发布时限","政务交互历史数据合规审计要扫缺失披露信息并出整改清单","跨平台数据迁移或 API 文档集成前要完整性检查保证可溯源"]
ai_protocol: true
spec: usk/1.0
interface: {"type":"cli","entry_point":"scripts/gov_disclosure_check.py","runtime":"python3","call_pattern":"args"}
input_schema: {"args":{"type":"string","description":"命令行参数透传给主脚本，具体取值见各包 --help","required":false}}
output_schema: {"stdout":{"type":"string","description":"标准输出为 JSON 结果，含逐项检查与总体结论"},"exit_code":{"type":"integer","description":"0=PASS/完成；1=FAIL/有警告或待补强；2=用法或参数错误"}}
capabilities: ["cli_tool"]
permissions: {"network":false,"filesystem":false,"subprocess":false}
requirements: {"python_packages":[],"min_python":"3.8"}
changelog: 1.0.1: Bilingual rewrite (full EN+ZH, English first), added read_when; 1.0.0: initial upload (USK v3)

凡自治之物 · LGD 治理学 · 创造术家族｜评测协议：见平台质量门禁规范

English

When to use

Before AI-generated government documents, policy interpretations or decision reports, when the output must contain mandatory fields such as "decision basis", "responsible department" and "remedy channel".
When the system handles information-disclosure requests, for real-time checks that data sources and publication deadlines meet legal requirements.
When auditing historical government-interaction data for compliance, auto-scanning missing key disclosures and generating a remediation list.
Before cross-platform data migration or API-document integration, running one completeness check so deliverables stay traceable.

Usage

Call the core script gov_disclosure_check.py for local build verification; dependencies are expected under __pycache__. The CLI -i flag points at the text to check (JSON or Markdown), and -l enables logging. In document mode, read the input file directly and run gov_disclosure_check.py --validate in the console — no extra dependency installation needed. Pass the target data object through the agent interface to trigger the internal check engine.

Workflow

Confirm the completeness of the raw input — government text or system data.
Run the gov_disclosure_check.py loader to extract the mandatory disclosure fields (decision basis, responsible department, etc.).
Compare against the LGD three-laws standard on both field-missing-ness and format compliance.
Generate a structured report with pass/fail status and details of each violation.
If the check fails, auto-flag the anomalous entries and output actionable fix suggestions.
Confirm the final compliance status — either allow publication, or enter the fix loop and re-run the script.

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

AI 生成政务公文、政策解读或决策报告前，需确保输出内容包含“决策依据”、“责任部门”及“救济渠道”等强制字段。
当系统处理信息公开申请时，用于实时校验数据来源与发布时限是否符合法律三律要求。
在对政务交互历史数据进行合规审计时，自动扫描缺失的关键披露信息并生成整改清单。
在进行跨平台数据迁移或 API 文档集成前，执行一次完整性检查以保证交付物可溯源。

用法

调用核心脚本 gov_disclosure_check.py 进行本地编译环境验证，确保依赖环境在 __pycache__ 目录下已就绪。命令行参数 -i 指定待校验的文本内容（如 JSON、Markdown 格式），参数 -l 开启日志记录模式。若技能处于文档型模式，需直接读取输入文件并在控制台执行 gov_disclosure_check.py --validate，无需手动安装额外依赖库。通过 Agent 接口传入目标数据对象即可触发脚本内部校验引擎。

流程

确认待处理政务文本或系统数据的原始输入完整性。
执行 gov_disclosure_check.py 加载器，提取强制披露字段（决策依据、责任部门等）。
对照 LGD 三律标准进行字段缺失度与格式合规性双重比对。
生成包含通过/失败状态及具体违规项详情的结构化报告。
若校验失败，自动标记异常条目并输出可执行修改建议。
确认最终合规状态，允许发布或进入修正流程后重新调用脚本。

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。