nature-literature-pipeline
yuan1z0825/nature-skills
Automated daily literature discovery pipeline with multi-source search, six-dimension scoring, and formatted delivery to Feishu or Telegram.
What is nature-literature-pipeline?
A production-tested literature pipeline that searches multiple academic sources (arXiv, OpenAlex, Crossref, Semantic Scholar), scores candidates across six dimensions, performs fine reading, and delivers formatted digests daily via cron. Use this to stay current with research in your field without manual searching.
- Multi-source search across arXiv, OpenAlex, Crossref, and Semantic Scholar with automatic fallback if sources are unavailable
- Six-dimension scoring system (topic match, methodology, journal quality, network relevance, applied value, archival value) to filter 30 candidates down to top 5
- Fine reading of abstracts or full text with source-level tagging (full-text, abstract-only, or metadata-only)
- Formatted daily digest delivery to Feishu, Telegram, or other messaging platforms with rank, score, methods, key results, and commentary
- Automated archival with DOI/arXiv deduplication, classification, note generation, and index updates
How to install nature-literature-pipeline
npx skills add https://github.com/yuan1z0825/nature-skills --skill nature-literature-pipeline- Node.js and npm installed to add the skill
- A Feishu group or Telegram channel for delivery (or alternative messaging platform)
- A local directory for archival (vault, wiki, or knowledge base)
- Research keywords in English and Chinese (provided by user during configuration)
How to use nature-literature-pipeline
- 1.Install the skill using: npx skills add https://github.com/yuan1z0825/nature-skills --skill nature-literature-pipeline
- 2.Tell your agent your research area and keywords (e.g., 'My research is on machine learning for biology, keywords: protein folding, neural networks')
- 3.Specify your delivery target (Feishu group name or Telegram channel) and archive path
- 4.Configure scoring weights if needed (optional; defaults provided for general research)
- 5.Set up a daily cron job with your agent (e.g., 'Set up a daily literature push at 08:30 Beijing time, 30 candidates, top 5 delivered')
- 6.Review the formatted digest each morning; the pipeline automatically archives papers and updates your index
Use cases
- Receive a curated top-5 literature digest every morning at a set time (e.g., 08:30 Beijing time) in your team chat
- Automatically filter 30 daily arXiv submissions in your research area down to the most relevant papers for your field
- Maintain a deduplicated, indexed archive of discovered papers with standardized notes and metadata
- Identify research gaps by systematically surveying literature across multiple sources and scoring by applied value and novelty
- Integrate pipeline discoveries into manuscript writing via exported citations
- Researchers and PhD students tracking literature in a specific field
- Research teams using Feishu or Telegram for daily communication
- Anyone maintaining a personal research vault or wiki who wants automated paper discovery
- Lab managers curating literature for team review
nature-literature-pipeline FAQ
The pipeline uses graceful degradation: if Semantic Scholar is unavailable, it automatically switches to OpenAlex + Crossref + arXiv to maintain the 30-candidate pool.
Yes. The six-dimension scoring system (topic match, methodology, journal quality, network relevance, applied value, archival value) is fully configurable via the config template. Adjust weights to match your research priorities.
No. The pipeline writes only to a `raw/` literature directory. Integration with your wiki or knowledge base is manual, giving you full control over what gets added.
It uses triple deduplication: DOI, arXiv ID, and OpenAlex ID. A maintained dedup index prevents classic papers from reappearing in digests.
You can trigger the pipeline manually at any time; the cron job is optional. The agent can also provide a fallback procedure if the local cron fails.
Full instructions (SKILL.md)
Source of truth, from yuan1z0825/nature-skills.
name: nature-literature-pipeline description: | Complete automated literature discovery pipeline: multi-source search → six-dimension scoring → fine reading → formatted delivery → archival. Combines a configurable engine with daily cron-driven application layer. Works with Feishu, Telegram, or any messaging platform. license: MIT metadata: author: Jiahao8595 hermes: tags: [research, literature, pipeline, cron, automation, discovery] related_skills: [nature-academic-search, nature-citation, arxiv, zotero]
Nature Literature Pipeline
A complete, production-tested automated literature pipeline. Not just "search for papers" — it's a structured engine that scores, classifies, reads, delivers, and archives research papers daily.
What It Does
Cron (daily trigger, e.g. 08:30)
│
├─ ① SEARCH (30 candidates)
│ arXiv / OpenAlex / Crossref / Semantic Scholar (auto-degradation)
│
├─ ② COARSE FILTER (30 → 5)
│ Six-dimension scoring: topic match × 35 + methodology × 20
│ + journal quality × 15 + network relevance × 10
│ + applied value × 10 + archival value × 10
│
├─ ③ FINE READ (top 5)
│ Abstract-level or full-text. Source level tagged:
│ Full-text / Abstract only / Metadata only
│
├─ ④ DELIVER
│ Formatted digest to Feishu/Telegram/etc.
│ 🏅 rank | title | journal | ⭐ score | 💡 one-liner
│ 🔬 methods | 📊 key results | 🧭 commentary
│
└─ ⑤ ARCHIVE
DOI/arXiv de-dup → classify → write notes → update index
Quick Start
After installing, tell your agent:
My research area is [X], keywords: [Y], deliver to [feishu group name], archive to [path]
The agent will configure keywords, delivery target, and archive path automatically.
Then set up a daily cron job:
Set up a daily literature push at 08:30 Beijing time, 30 candidates, top 5 delivered
Architecture
The skill is organized in two layers:
| Layer | Purpose | Files |
|---|---|---|
| Engine | Scoring, classification, note templates, gap analysis | references/scoring-system.md, references/gap-analysis.md, references/note-template.md |
| Application | Daily cron pipeline, delivery formatting, archival workflow | references/push-format.md, references/cron-setup.md, references/review-compilation-workflow.md |
Configuration
All domain-specific content is configurable:
- Keywords — your research keywords (English + Chinese)
- Scoring weights — adjust the six dimensions for your field
- Classification rules — define your own tier system (A-E or custom)
- Delivery target — Feishu group, Telegram channel, email, etc.
- Archive path — local vault/wiki directory
A config template is provided in templates/literature-push-template.md.
Built-in Safeguards
- Score validation: Each dimension capped, total recalculated — no 11/10 allowed
- Triple de-duplication: DOI / arXiv ID / OpenAlex ID
- Graceful degradation: Semantic Scholar down → auto-switch to OpenAlex + Crossref + arXiv
- Read-only archive: Daily pipeline writes to
raw/literature directory only; never modifies wiki/knowledge base without user approval
Related Skills
nature-academic-search— ad-hoc literature search (complementary; this skill adds structured daily automation)nature-citation— CNS citation export (for importing pipeline discoveries into manuscripts)zotero— library management (for long-term organization of pipeline outputs)arxiv— arXiv API (used as a search source)
References
| Reference | Purpose |
|---|---|
references/scoring-system.md | Six-dimension scoring rubric with weights, caps, and evaluation logic |
references/gap-analysis.md | Methodology for identifying research gaps through systematic literature survey |
references/note-template.md | Standardized literature note format with YAML frontmatter |
references/push-format.md | Daily digest message template with field guidelines and example |
references/cron-setup.md | Cron job creation, verification, and manual fallback procedures |
references/review-compilation-workflow.md | End-to-end workflow for concentrated literature review writing |
Pitfalls
- Keyword drift: Review keywords monthly — research directions evolve
- Score inflation: Subagents may inflate scores; always validate arithmetic
- Duplicate creep: Classic papers will reappear; maintain a dedup index
- Wiki safety: Pipeline writes to
raw/only; wiki integration is manual - Cron locality: Hermes cron is local, not cloud — machine must be running
Related skills
More from yuan1z0825/nature-skills and the wider catalog.
nature-paper-card
Build structured deep-reading analysis cards for scientific papers, breaking down methods, evidence chains, and research gaps.
nature-paper-to-patent
Transform research papers into evidence-grounded Chinese invention patent drafts and technical disclosures.
nature-paper2ppt
Transform scientific papers into polished Chinese academic presentations with figures and speaker notes.
nature-polishing
Polish, translate, and tighten academic prose while preserving facts and evidence boundaries.
nature-reader
Create bilingual Chinese-English paper readers with aligned text, figures, tables, and equations from PDFs or HTML.
nature-ref-verifier
Multi-source cross-verification of academic references with field-level comparison and structured error reporting.