curation

作者: google-gemini

选择与排名规则——如何将原始抓取的内容池转化为读者真正想要的少量条目,并遵循品味档案的引导……

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

Curation Skill

Curation is editing, not summarizing. From the candidate pool in new_items.json, choose the items this specific reader should see today.

Selection Rules

  1. The taste profile decides. Re-read interests.json before selecting. preferences.more entries boost an item; preferences.less entries drop it unless it is genuinely major; preferences.notes carry dated, specific guidance from past feedback — treat recent notes as the strongest signal.
  2. Cap the briefing at 10 news items total across all topics, and up to 4 community-buzz items. Fewer is fine; padding is not. If a topic produced nothing worth including, say so in one line rather than including filler.
  3. Prefer, in order: primary sources and official announcements → original reporting → high-engagement community discussion → aggregation/commentary. Drop listicles and rumor pieces by default (they are on the default less list).
  4. Collapse duplicates of one story. When several outlets carry the same development, pick the strongest single link and mention coverage breadth in the why-it-matters line ("also covered by Reuters and The Verge") — breadth itself is a signal the story matters.
  5. Genre feeds are the serendipity channel. Pick at most 2-3 genre items the reader did not explicitly ask about but would plausibly care about, given their profile. Label them as discoveries.
  6. Community items are for signal, not noise. Select a Hacker News item only when it adds something the news coverage lacks: practitioner experience, technical pushback, or early buzz on something not yet covered.
  7. Longform earns its slot with depth. Select at most 2 Medium pieces per briefing, and only for genuine substance — tutorials, architecture write-ups, first-hand experience reports. Medium has no engagement signal in the feed, so judge entirely on title substance and taste-profile fit; skip anything that reads as engagement-bait or paywalled teaser fluff.

Ranking Within the Briefing

Lead with the item that best combines: relevance to an explicit topic, recency, source quality, and taste-profile fit. Genre discoveries and community buzz always come after the reader's explicit topics.

What Never Gets Selected

  • Items you cannot link.
  • Items whose headline alone is too thin to say why it matters — do not pad with invented detail.
  • Pure engagement-bait framed as news, regardless of topic match.

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...
deliver
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……