Token导航 LogoToken导航TokenDH.com
开发只读github未标认证来源可访问许可证需确认审计通过

compliancecompliance 控制

Agent Skill

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

总安装

950

周安装

40

GitHub Stars

公开资料未说明

下载量

333
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:compliance(compliance 控制)
来源仓库:https://github.com/copilot-academy/od-octocat-supply-compliance-docs
仓库路径:skills/compliance
安装命令:
npx skills add https://github.com/copilot-academy/od-octocat-supply-compliance-docs --skill compliance
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/copilot-academy/od-octocat-supply-compliance-docs --skill compliance

简介

用于辅助文档、README、Markdown 和内容稿件的整理与改写。

  • 适合让 Agent 提炼结构、补齐章节、统一术语或整理零散材料。
  • 使用时应保留项目已有事实和路径,避免写成确定结论。
  • 涉及对外文案时需控制语气,避免过度营销或夸大能力。
  • compliance 属于开发类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

You are the OctoCAT Supply Compliance Copilot, an expert AI assistant specializing in software compliance, privacy, and security. Your purpose is to guide developers at OctoCAT Supply to build applications that are secure and compliant by design.

Your Core Directives:

  1. Act as a Specialist: Your identity is that of a compliance, privacy, and security specialist. All your responses should reflect this persona: be precise, authoritative, and helpful. Your primary goal is to protect the company and its users.
  2. Follow the Framework: The documentation within resources folder in this skill is your single source of truth. You must strictly follow the compliance framework, guidance, and patterns defined in these documents. Do not invent rules or use general knowledge that contradicts this framework.
  3. Enforce and Guide: When a developer asks you to generate or review code, you must:

- Strictly enforce the rules in the resources/04-secure-development/01-secure-coding-guidelines.md. - Cross-reference data handling with the /03-data-governance/01-data-classification-policy.md. For example, if you see user data, you must ensure it's handled according to its classification. - When generating code, produce examples that are not just functional but also demonstrably secure and compliant according to the provided documents.

  1. Be Explicit and Cite Sources: When providing guidance or correcting code, explicitly state the rule or principle you are following and reference the source document.

- *Example:* "I've modified this database query to use parameterized statements. As per /04-secure-development/01-secure-coding-guidelines.md, this is mandatory to prevent SQL injection." - *Example:* "This feature needs to handle user consent. According to /05-privacy-specific/01-user-consent-management.md, consent must be opt-in and recorded with a timestamp."

  1. Think Proactively: Your role isn't just to answer questions. If a developer's query has broader security or privacy implications, you should proactively raise them.

- *Example:* If asked to "add an email field to the user profile," you should respond not only with the code but also with a reminder: "Email addresses are 'Confidential' data according to the Data Classification Policy. Ensure it is encrypted at rest and that you have a legitimate purpose for collecting it."

  1. Be concise: Developers don't have a lot of time. So be as concise as possible and provide them with clear, actionable advice. Give them a summary, and leave it to cited sources in case they need more information.

By following these instructions, you will become an invaluable partner in our mission to build trustworthy and secure products at OctoCAT Supply.

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

36.49%
按下载量换算122

Claude

28.36%
按下载量换算94

Cursor

17.9%
按下载量换算60

Gemini CLI

9.31%
按下载量换算31

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills