skill-compliance
Skill0 starsChanged 3 months agoMITView on GitHub
Skill上架合规检查器（国内平台 + 发布披露）。检查金融敏感词、免责声明、安全红线，并按 DISCLOSURE v0.2 检查发布披露完整性（D1/D3/D4 必填）与声明-代码一致性（云端/离线/端点 mismatch）、DSH 宿主依赖遮蔽风险；输出 disclosure 摘要（开放数据层字段）。
1 other project uses a version of this.
Adopted by
Most recently taken up by
- cordanaLLM/praetortheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- cordanaLLM/praetor★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- bundle-lintSkill
- csv-toolsSkill
- dependency-scanSkill
- excel2insights-proSkill
- excel2insightsSkill
- expert2skillSkill
- finance-toolsSkill
- fitness-dailySkill
- malware-scanSkill
- runtime-probeSkill
- study-abroad-assistantSkill
- sum2slides-proSkill
The file
Files
⚠️ 免责声明：本工具为辅助性参考工具，不构成投资建议，不构成法律建议。市场有风险，投资需谨慎；据此操作，风险自担。正式合规意见请咨询具备资质的律师。最终决策与责任由使用者自行承担。 仅供参考，不构成任何操作依据；市场有风险，投资需谨慎，据此操作风险自担。 本工具不持有证券投资咨询牌照，所有分析仅供学习研究参考，不构成买卖建议。
Skill Compliance Check
功能
上传 skill 到 SkillHub 前，用本工具做一次快速合规预检：
| 检查项 | 内容 | |
| FINANCE | 违规金融用语（荐股类、收益保证类、需资质类） | |
| DISCLAIMER | 是否在显眼位置有免责声明（投资/法律类） | |
| EXAGGERATION | 绝对化用语（广告法禁止的夸大表述）、夸大描述 | |
| 检查项 | 内容 | 依据类型 |
| -------- | ------ | ---------- |
| FINANCE | 违规金融用语（荐股类、收益保证类、需资质类） | 法律 |
| DISCLAIMER | 投资/法律免责声明是否在显眼位置 | 法律/法规 |
| EXAGGERATION | 绝对化用语（广告法禁止的夸大表述）、夸大描述 | 法律 |
| SECURITY | subprocess/exec/eval 红线、JSON合法性、版本号格式 | 平台规范 |
| SUPPLY_CHAIN | 外部脚本获取、代码混淆、未固定版本依赖 | 平台规范 |
| MCP | MCP权限最小化、工具权限声明、通配符检测 | 平台规范 |
| OUTPUT | 未验证输出注入、跨上下文输出、文件写入安全 | 平台规范 |
| ADVISORY | 描述-行为不一致检测（如声明network:none但代码含网络请求） | 建议性 |
| PRIVACY | 数据隐私合规（个人信息收集声明、用户同意机制、数据出境合规） | 法律 |
| REGULATORY | 专项监管合规（ICP备案、AIGC标识、算法备案、数据安全法、关基保护等） | 法律/法规 |
| RECOMMENDATIONS | 基于检测结果给出改进建议 | 最佳实践 |
💡 关于两类评分: 本工具采用双轨评分机制
- 法律合规评分（0-100）：基于法律/法规/标准的评分，影响 PASS/NEEDS_FIX/REJECT 判定
- 平台告警（不计分）：基于平台规范/最佳实践的建议性问题，不影响合规结论，但建议关注
评分规则
| 扣分 | 等级 |
| -30 / 项 | Critical（安全红线、医疗红线） |
| -15 / 项 | High（隐私合规、金融敏感词、缺免责声明） |
| -5 / 项 | Medium（极限词、JSON问题） |
| -2 / 项 | Low（建议性） |
| ≥70分 | PASS — 可上架（无 redline 触发） |
| 40–69分 | NEEDS_FIX — 建议修复后再上传 |
| <40分 | REJECT — 强烈不建议上传 |
法律免责声明
本工具仅为辅助检查参考，不构成任何形式的合规保证。最终合规责任由 skill 开发者自行承担。
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.