curation

Selection and ranking rules — how to turn the raw fetched pool into the handful of items the reader actually wants, guided by the taste profile in…

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.

Plus de skills de google-gemini

greeter
google-gemini
Une compétence d'accueil amicale
official
code-reviewer
google-gemini
Révision automatisée du code pour les modifications locales et les pull requests distantes avec une analyse structurée couvrant la correction, la maintenabilité et la sécurité. Prend en charge les modifications du système de fichiers local (staged et unstaged) et les PR distantes (par numéro ou URL) avec extraction automatique via GitHub CLI. Analyse le code selon sept dimensions : correction, maintenabilité, lisibilité, efficacité, sécurité, gestion des cas limites et couverture de test. Exécute des suites de vérification préalable optionnelles (ex. : npm run preflight) pour détecter...
official
review-duplication
google-gemini
Utilisez cette compétence lors des revues de code pour examiner de manière proactive la base de code à la recherche de fonctionnalités dupliquées, de réinventions de la roue ou d’absence de réutilisation de l’existant…
official
reconciliation
google-gemini
Concilier les dépenses chargées avec la base de données de factures pré-analysées, en signalant les écarts tels que les différences de montant, les factures manquantes et les discordances de commerçant…
official
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…
official
async-pr-review
google-gemini
Déclenchez cette compétence lorsque l'utilisateur souhaite lancer une revue de PR asynchrone, exécuter des vérifications en arrière-plan sur une PR, ou vérifier le statut d'une revue de PR asynchrone déjà lancée…
official
ci
google-gemini
Une compétence spécialisée pour Gemini CLI qui offre des performances élevées et un échec rapide
official
critique
google-gemini
Expertise en audit et correction des scripts de dépôt et des workflows GitHub Actions pour garantir la robustesse technique et la sécurité.
official