curation

Aturan seleksi dan peringkat — cara mengubah kumpulan hasil mentah yang diambil menjadi segelintir item yang benar-benar diinginkan pembaca, dipandu oleh profil selera di…

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.

Lebih banyak skill dari google-gemini

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
Panduan untuk menggunakan alat CLI Gemini API. Gunakan saat Anda perlu berinteraksi dengan Gemini API melalui baris perintah, mengelola agen, atau menghasilkan media (gambar, …)
behavioral-evals
google-gemini
Panduan untuk membuat, menjalankan, memperbaiki, dan mempromosikan evaluasi perilaku. Gunakan saat memverifikasi logika keputusan agen, men-debug kegagalan, men-debug prompt…
gemini-live-api-dev
google-gemini
Streaming dua arah secara real-time dengan Gemini melalui WebSocket untuk percakapan audio, video, dan teks. Mendukung input/output audio (PCM 16 kHz), bingkai video, teks, dan transkripsi otomatis dengan deteksi aktivitas suara untuk penanganan interupsi. Menyertakan fitur audio asli: dialog afektif, audio proaktif, dan mode berpikir; pemanggilan fungsi untuk penggunaan alat sinkron dan asinkron; serta penjangkaran Google Search. Menawarkan manajemen sesi dengan kompresi konteks, kelanjutan, dan...
gemini-omni-flash-api
google-gemini
Gunakan keterampilan ini untuk penyuntingan video generatif, teks-ke-video, pembuatan video dengan referensi gambar, dan animasi transisi bingkai pertama-ke-video menggunakan…
gemini-api-dev
google-gemini
Bangun aplikasi dengan model Gemini dari Google, mendukung konten multimodal, pemanggilan fungsi, dan keluaran terstruktur di Python, JavaScript, Go, dan Java. Akses model Gemini 3 terkini (Pro, Flash, Pro Image) dengan konteks 1M token; model lawas Gemini 2.x dan 1.5 sudah tidak digunakan lagi. Mendukung pembuatan teks, pemahaman gambar/audio/video, pemanggilan fungsi, keluaran JSON terstruktur, eksekusi kode, caching konteks, dan embeddings. SDK resmi tersedia: google-genai (Python),...
gemini-interactions-api
google-gemini
Antarmuka terpadu untuk model dan agen Gemini dengan status sisi server, streaming, dan orkestrasi alat. Mendukung beberapa model terkini (gemini-3-flash-preview, gemini-3-pro-preview, gemini-2.5-flash/pro) dan agen Deep Research; secara otomatis mengganti ID model yang tidak digunakan lagi dengan alternatif terkini. Offload riwayat percakapan ke server melalui previous_interaction_id untuk interaksi multi-putaran yang memiliki status tanpa pengelolaan riwayat manual. Orkestrasi alat bawaan termasuk...
deliver
google-gemini
Memposting versi ringkas dari briefing ke incoming webhook Google Chat atau Slack, sehingga laporan harian terkirim dengan sendirinya — melewati secara diam-diam ketika tidak ada webhook yang…