deliver

作者: google-gemini

将简报的浓缩版发布到 Google Chat 或 Slack 的传入 webhook,使每日运行自行投递——当没有 webhook 时静默跳过……

npx skills add https://github.com/google-gemini/gemini-managed-agents-templates --skill deliver

Deliver Skill

Use this skill as the final step of a sweep, after the briefing file is written. It closes the last mile: instead of the briefing waiting in the workspace until someone polls for it, the run pushes a condensed version to a chat space.

Usage

python3 skills/deliver/scripts/deliver.py .agents/workspace/briefings/<file>.md

The script:

  1. Looks for a webhook URL in /credentials/webhook.env (written into the environment by client/triggers.py create when CHAT_WEBHOOK_URL or SLACK_WEBHOOK_URL is set at creation time).
  2. If none is configured, prints a skip notice and exits 0 — delivery is optional and its absence is never an error.
  3. Condenses the briefing markdown for chat (headings bolded, links kept, capped below the ~4,096-character Chat message limit, with a note that the full briefing lives in the workspace).
  4. POSTs {"text": ...} to the webhook — the same wire format works for both Google Chat and Slack incoming webhooks.

Instructions for the Agent

  • Run this exactly once per sweep, after the briefing file exists, passing the briefing's path.
  • A "skipping delivery" message is normal operation — do not mention it as a problem in your output.
  • If the POST fails (non-2xx), report the status and response body verbatim in your final output — the briefing itself is already safely written, so a delivery failure never warrants rewriting it or retrying more than once.

来自 google-gemini 的更多技能

agent-tui
google-gemini
Main Agents: Do NOT use this skill directly. If you need to test the TUI, invoke the `tui_tester` subagent. Drive terminal UI (TUI) applications…
gemini-api-cli
google-gemini
使用Gemini API CLI工具的指南。当你需要通过命令行与Gemini API交互、管理代理或生成媒体(图像、……)时使用。
behavioral-evals
google-gemini
创建、运行、修复和推广行为评估的指南。用于验证代理决策逻辑、调试故障、调试提示…
gemini-live-api-dev
google-gemini
通过WebSocket与Gemini进行实时双向流式传输,支持音频、视频和文本对话。具备音频输入/输出(16 kHz PCM)、视频帧、文本以及带语音活动检测的自动转录功能,可实现中断处理。包含原生音频特性:情感对话、主动音频和思考模式;支持同步和异步工具调用的函数调用;以及Google搜索接地功能。提供会话管理,包括上下文压缩、恢复等。
gemini-omni-flash-api
google-gemini
使用此技能进行生成式视频编辑、文本转视频、图像参考视频生成以及首帧到视频的过渡动画,基于…
gemini-api-dev
google-gemini
使用Google的Gemini模型构建应用程序,支持多模态内容、函数调用和结构化输出,覆盖Python、JavaScript、Go和Java语言。可访问当前Gemini 3模型(Pro、Flash、Pro Image),具备100万token上下文;旧版Gemini 2.x和1.5模型已弃用。支持文本生成、图像/音频/视频理解、函数调用、结构化JSON输出、代码执行、上下文缓存和嵌入功能。提供官方SDK:google-genai(Python)...
gemini-interactions-api
google-gemini
Gemini模型与代理的统一接口,支持服务端状态、流式传输和工具编排。兼容当前多款模型(gemini-3-flash-preview、gemini-3-pro-preview、gemini-2.5-flash/pro)及Deep Research代理;自动将已弃用的模型ID替换为当前替代方案。通过previous_interaction_id将对话历史卸载至服务端,实现有状态的多轮交互,无需手动管理历史记录。内置工具编排功能包括...
fetch-news
google-gemini
获取读者感兴趣的所有主题和类别的Google News和Hacker News最新条目,并针对之前运行中显示过的所有条目进行去重。