技能发现

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。

概述

工作流程

搜索 GitHub 页面web_search。更喜欢提及的查询SKILL.md、请求的主题,以及site:github.com。

选择一个明确指向 GitHub 技能目录或SKILL.md页。

致电skill_install_github与该 GitHub URL。

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
@trpc-group · 未声明许可证
上下文用量评级
低消耗
接入复杂程度
需简单配置
是否需要外部接口密钥
不需要
兼容的系统
未声明(默认跨平台)
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
  • 命令执行
网络行为
仅限本地
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

Overview

Use this skill when the user wants a new public Agent Skill that is not
already installed.

Workflow

1. Search GitHub pages with `web_search`.
   Prefer queries that mention `SKILL.md`, the requested topic, and
   `site:github.com`.

2. Pick a result that clearly points to a GitHub skill directory or a
   `SKILL.md` page.

3. Call `skill_install_github` with that GitHub URL.

4. Read the tool result carefully.
   It returns the exact `skill_name` that was installed and may also
   include `installed_files`.

5. Immediately call `skill_load` with the returned `skill_name`.

6. Only if local execution is explicitly enabled for this demo and the
   user asked for a runnable demo, follow the installed skill docs and
   use `skill_run`.

7. If the docs are brief, use `installed_files` to avoid guessing.
   Prefer obvious entrypoint files such as `run.sh` or scripts under
   `scripts/`.

Rules

- Prefer small public skills with a clear `SKILL.md`.
- Prefer GitHub results that point directly to a skill, not a repo home
  page.
- Tell the user which skill you installed and where it came from.
- Never run downloaded code automatically.
- If installation fails, explain the failure briefly and try another
  candidate.

讨论

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