AI Agent Hub
Back to skills
Nexus Reader Daily WeRead Rising List Recommendations icon

Nexus Reader Daily WeRead Rising List Recommendations

Content Creation Updated 2026.08.30

Paste the following prompt into your AI chat to install this skill:

Please follow https://skillhub.cn/install/skillhub.md to install @user_217d8d33/nexus-reader.

About this skill

Problem

Manual daily selection from WeRead's rising list, recommendation copy, and card layout is repetitive and hard to keep visually consistent. nexus-reader separates data fetching, LLM-assisted copywriting, and card rendering into a reusable workflow.

How it works

  • Fetch the top 20 WeRead rising-list books and save them to data/weread_rising_YYYY-MM-DD.json, including title, author, and recommendation score.
  • Use an LLM to create book_desc, a headline, recommendation copy, and lunar_date, then write data/nexus-reader-YYYYMMDD.json.
  • Render an HTML card from the card JSON and optionally export a PNG. Cover, rating, and reading count fields are taken from the fetched data to avoid inventing metadata.

Boundaries

This skill is best for consistent daily reading cards, not in-depth book reviews or cross-platform publishing. Cover images depend on a CDN and may fail in weak network conditions; PNG export requires an optional dependency. Same-day cache can be reused, and the workflow falls back to older cache if fetching fails.

Use Cases

  • A reading-account operator fetches 20 WeRead rising-list books daily and renders a consistent HTML daily card.
  • A content editor converts the WeRead rising list into a shareable image by rendering HTML and exporting a PNG card.
  • An automation engineer schedules a daily 08:00 job to fetch data, generate card JSON, and push an HTML preview link.
  • A personal reading-stream maintainer keeps real title, rating, and reading count fields while asking an LLM to add copy and lunar date.

Best For

  • content operators maintaining daily reading cards with a fixed visual template and list data source
  • content editors turning WeRead rankings into social sharing images
  • LLM workflow engineers building daily scheduled reading-recommendation automation
  • reading-assistant maintainers who need real ratings and reader counts while using models only for copy