agentleFS
uvwtuvwt/agentdock-skills/skills/ntfy/SKILL.md

ntfy

Skill6 starsChanged 3 months agoApache-2.0View on GitHub

Use this skill when sending notifications via ntfy.sh or self-hosted ntfy servers.

  • Reads credentials

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

ntfy Notifications Skill

把 ntfy.sh 开源 HTTP 通知服务封装为 AgentDock 原生 Skill,用于 Dock 通知推送。

能力

  • send:向 ntfy topic 发送推送通知。支持标题、优先级、标签、点击 URL、图标和 Markdown 正文。
  • event:发送格式化的 Dock 运行事件通知,自动拼接 severity / device / service / time 等上下文。
  • health:验证 ntfy server URL 与 topic 配置;live: true 会真实发送一条健康检查通知。
  • subscribe:轮询拉取 topic 最近的消息(JSON 格式),支持 since 和 limit 参数。

配置

默认连接 https://ntfy.sh。可设置 NTFY_SERVER_URL 环境变量或在调用中传 server_url 指向自建 ntfy server。

Topic 名称从 NTFY_TOPIC 环境变量或调用参数 topic 获取。

认证(可选)

  • Token 认证:设置 NTFY_TOKEN 环境变量,使用 Authorization: Bearer <token> 头。
  • Basic Auth:设置 NTFY_USERNAME 和 NTFY_PASSWORD 环境变量。
  • 无认证时使用公开 ntfy.sh 服务(topic 公开可见)。

可通过 NTFY_ENV_FILE 或调用参数 env_file 指定 .env 文件。

安全约束

  • server_url 仅允许 http / https,禁止 URL 内嵌用户名和密码。
  • 认证凭据只从环境变量 / .env 读取,不接受 action input 传入。
  • Token 和密码在输出中自动脱敏。
  • 不依赖第三方 Python 包。

辅助脚本执行

Skill 本体是本说明文档。确需调用包内辅助脚本时,在 Skill 包根目录使用相对路径执行;运行宿主负责切换到包根目录并把所需变量注入当前子进程。

printf '%s' '{"skill_action":"<动作>"}' | python3 run.py

输入必须是 JSON 对象。写操作仍按本文档中的确认规则执行。

动作用途
sendSend a push notification to an ntfy topic. Supports title, priority, tags, click URL, icon, and Markdown-formatted body.
eventSend a formatted Dock event notification through ntfy.
healthVerify ntfy configuration and optionally perform a live connectivity check.
subscribePoll an ntfy topic for recent messages (JSON format). Returns the latest messages without establishing a long-lived connection.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.