curation

作者: google-gemini

選擇與排名規則——如何將原始抓取的內容池轉化為讀者真正想要的少數項目,並以品味檔案作為引導……

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.

來自 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。當你需要透過命令列與 Gemini API 互動、管理代理或生成媒體(圖片、……)時使用。
behavioral-evals
google-gemini
建立、執行、修正及推廣行為評估的指引。用於驗證代理決策邏輯、除錯失敗、除錯提示…
gemini-live-api-dev
google-gemini
通過WebSocket與Gemini進行即時雙向串流,支援音訊、視訊和文字對話。支援音訊輸入/輸出(16 kHz PCM)、視訊幀、文字,以及具備語音活動偵測的自動轉錄功能,可處理中斷情況。包含原生音訊功能:情感對話、主動音訊和思考模式;支援同步和非同步工具使用的函式呼叫;以及Google Search基礎驗證。提供具備上下文壓縮、恢復功能的會話管理,以及...
gemini-omni-flash-api
google-gemini
使用此技能進行生成式影片編輯、文字轉影片、圖片參考影片生成,以及基於…的首幀轉場動畫。
gemini-api-dev
google-gemini
We need to translate the given text from English to Traditional Chinese. The text describes building applications with Google's Gemini models, mentioning multimodal content, function calling, structured outputs, supported languages, model versions, features, and SDKs. We must preserve the name "gemini-api-dev" but it's not in the text, so ignore. Also preserve technical terms like "Gemini", "Pro", "Flash", "Pro Image", "1M token context", "Gemini 2.x", "1.5", "JSON", "SDKs", "google-genai", etc. No extra commentary. Output only the translation. Translation: 使用 Google 的 Gemini 模型建置應用程式,支援多模態內容、函式呼叫與結構化輸出,涵蓋 Python、JavaScript、Go 及 Java。可存取最新的 Gemini 3 模型(Pro、Flash、Pro Image),具備 100 萬 Token 上下文;舊版 Gemini 2.x 與 1.5 模型已棄用。支援文字生成、圖片/音訊
gemini-interactions-api
google-gemini
Gemini模型與代理的統一介面,具備伺服器端狀態、串流與工具編排功能。支援多種當前模型(gemini-3-flash-preview、gemini-3-pro-preview、gemini-2.5-flash/pro)及Deep Research代理;自動將已棄用的模型ID替換為當前替代方案。透過previous_interaction_id將對話歷史卸載至伺服器,實現有狀態的多輪互動,無需手動管理歷史記錄。內建工具編排功能,包括...
deliver
google-gemini
將簡報的精簡版本發布到 Google Chat 或 Slack 的 incoming webhook,讓每日執行自動送達——若未設定 webhook 則靜默跳過…