特工学院观星者

人工智能 社区

技能解读

当前原文的自动摘译,尚未人工审校。

🏁 先决条件

运行之前,请验证gh CLI 是否已安装并经过身份验证:运行gh --version 以确认其已安装。如果没有,请安装它(例如,macOS 上的brew install gh,或适合用户操作系统的包管理器)。运行gh auth status以确认其已通过身份验证。如果没有,请运行gh auth login并引导用户完成交互式身份验证流程。在两项检查都通过之前,不要继续进行其余的技能。

🛠️技能流程

验证gh CLI 是否已安装并经过身份验证(请参阅上面的先决条件)。使用带有 --paginate 标志的 gh api 获取 microsoft/agent-academy 存储库的观星者完整列表,以自动检索所有页面(API 每页最多返回 100 个结果,因此对于超过 100 个观星者的存储库需要分页)。使用 --jq 仅选择每个观星仪对象中的 login、type 和 url 字段。

📜 规则

始终使用 gh api --paginate 获取 microsoft/agent-academy 的观星仪,确保检索到所有页面(使用 per_page=100 提高效率)。始终使用 --jq '[.[] | {login, type, url}]' 将响应限制为仅对 login、type 和 url 字段。不要存储任何其他字段。始终将结果保存到相对于存储库根目录的temp/stargazers.json,如果不存在则创建temp目录。

流狐档案 运行与权限由流狐静态检查推断,不代表作者声明或实际测试结果。
领域
人工智能
作者声明的智能体
未找到明确声明;不据此推断已兼容或已测试
静态检查
88 / 100 · 启发式扫描,不代表运行安全
运行环境证据
未执行;当前没有隔离运行测试证据
作者 / 版本 / 许可证
@microsoft · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
即装即用
是否需要外部接口密钥
不需要
兼容的系统
macOS
运行环境要求
未检出明确要求
检测到的文件与系统行为
  • 只读
  • 允许写入 / 修改
网络行为
允许外网请求
安装命令数
无(仅作为资料)

需要注意: 未声明工具权限范围;实际权限由运行环境决定。

作者说明文件(原文) SKILL.md

# Agent Academy Stargazers

This skill fetches the list of users who have starred the `microsoft/agent-academy` repository on GitHub. If the user provides a GitHub username, it also checks whether that specific user has starred the repo.

## 🏁 Prerequisites

Before running, verify the `gh` CLI is installed and authenticated:

1. Run `gh --version` to confirm it is installed. If not, install it (e.g., `brew install gh` on macOS, or the appropriate package manager for the user's OS).
2. Run `gh auth status` to confirm it is authenticated. If not, run `gh auth login` and guide the user through the interactive authentication flow.

Do not proceed with the rest of the skill until both checks pass.

## 🛠️ Skill Flow

1. Verify the `gh` CLI is installed and authenticated (see Prerequisites above).
2. Fetch the full list of stargazers for the `microsoft/agent-academy` repository using `gh api` with the `--paginate` flag to automatically retrieve all pages (the API returns at most 100 results per page, so pagination is required for repos with more than 100 stargazers). Use `--jq` to select only the `login`, `type`, and `url` fields from each stargazer object.
3. Save the filtered list to `temp/stargazers.json` in the repository root.
4. Tell the user how many stargazers were found and that the list was saved to `temp/stargazers.json`.
5. If the user provided a GitHub username, check whether that username appears in the stargazer list and tell the user the result (e.g., "✅ @username has starred the repo" or "❌ @username has not starred the repo").

## 📜 Rules

- Always use `gh api --paginate` to fetch stargazers for `microsoft/agent-academy`, ensuring all pages are retrieved (use `per_page=100` for efficiency).
- Always use `--jq '[.[] | {login, type, url}]'` to limit the response to only the `login`, `type`, and `url` fields. Do not store any other fields.
- Always save the result to `temp/stargazers.json` relative to the repository root, creating the `temp` directory if it does not exist.
- Always fetch fresh data from GitHub — never rely on previously fetched results or conversation history.
- If the `gh` CLI is not installed, install it using the appropriate package manager for the user's OS (e.g., `brew install gh` on macOS) before proceeding.
- If the `gh` CLI is not authenticated, run `gh auth login` and guide the user through authentication before proceeding.
- If the API request fails (e.g., network error, repo not found), report the error clearly to the user and do not write a partial or empty file.

讨论

基于 GitHub Discussions。登录 GitHub 即可参与讨论、点赞、订阅更新。