Skip to content
Get packs

Nature Literature Pipeline

Automatically finds, scores, summarizes and archives daily research papers for your field

Source Download skill
Repository
Yuan1z0825/nature-skills
Stars
51,827
Licence
Apache-2.0
Files
12 files

What it does

Once installed, the agent can run a daily literature routine: it searches academic sources (arXiv, OpenAlex, Crossref, Semantic Scholar) for about 30 candidate papers, scores them on six weighted criteria such as topic match, methodology, and journal quality, and keeps the top 5. It then writes short summaries for those papers, sends a formatted digest to a messaging app such as Feishu or Telegram, and saves notes into a local archive folder, skipping duplicates.

Great for

  • Researchers or graduate students who want a daily digest of new papers in their field
  • Lab groups that want a shared, automatically maintained literature feed
  • Users comfortable setting up scheduled jobs and a local notes folder

Skip it if

  • Users who only need a one-off search; the README positions the separate nature-academic-search skill for that
  • Anyone who expects the machine to run unattended while it is off: the skill notes that Hermes cron is local, not cloud, so the computer must be running
  • Work requiring verified accuracy without review: scores come from an agent following a rubric and the skill itself warns subagents may inflate scores

Try asking

  • “My research area is protein language models, keywords: ESM, structure prediction, deliver to my lab Feishu group, archive to ~/vault/literature”
  • “Set up a daily literature push at 08:30 Beijing time, 30 candidates, top 5 delivered”
  • “Score these candidate papers on the six-dimension rubric and write notes for the top five”
Step-by-step guide: how to use Nature Literature PipelineInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 12 original files, the Apache-2.0 licence and an attribution note.

    nature-literature-pipeline.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip nature-literature-pipeline.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip nature-literature-pipeline.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Review your keywords monthly, since research directions drift and the skill itself recommends this
  • Spot-check scores on the first few digests before trusting the ranking
  • Keep the archive pointed at a dedicated raw/ folder; the skill says wiki changes need manual approval

What's inside

  • agents/openai.yaml
  • manifest.yaml
  • README_EN.md
  • README.md
  • references/cron-setup.md
  • references/gap-analysis.md
  • references/note-template.md
  • references/push-format.md
  • references/review-compilation-workflow.md
  • references/scoring-system.md
  • SKILL.md
  • templates/literature-push-template.md

Redistributed unmodified from Yuan1z0825/nature-skills under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.