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
1---
2name: nature-literature-pipeline
3description: |
4 Complete automated literature discovery pipeline: multi-source search → six-dimension scoring → fine reading → formatted delivery → archival.
5 Combines a configurable engine with daily cron-driven application layer. Works with Feishu, Telegram, or any messaging platform.
6license: MIT
7metadata:
8 source: https://skillmd.com/skills/lovits/nature-literature-pipeline
9 author: Jiahao8595
10 hermes:
11 tags: [research, literature, pipeline, cron, automation, discovery]
12 related_skills: [nature-academic-search, nature-citation, arxiv, zotero]
13---
14
15# Nature Literature Pipeline
16
17A 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.
18
19## What It Does
20
21```
22Cron (daily trigger, e.g. 08:30)
23 │
24 ├─ ① SEARCH (30 candidates)
25 │ arXiv / OpenAlex / Crossref / Semantic Scholar (auto-degradation)
26 │
27 ├─ ② COARSE FILTER (30 → 5)
28 │ Six-dimension scoring: topic match × 35 + methodology × 20
29 │ + journal quality × 15 + network relevance × 10
30 │ + applied value × 10 + archival value × 10
31 │
32 ├─ ③ FINE READ (top 5)
33 │ Abstract-level or full-text. Source level tagged:
34 │ Full-text / Abstract only / Metadata only
35 │
36 ├─ ④ DELIVER
37 │ Formatted digest to Feishu/Telegram/etc.
38 │ 🏅 rank | title | journal | ⭐ score | 💡 one-liner
39 │ 🔬 methods | 📊 key results | 🧭 commentary
40 │
41 └─ ⑤ ARCHIVE
42 DOI/arXiv de-dup → classify → write notes → update index
43```
44
45## Quick Start
46
47After installing, tell your agent:
48
49```
50My research area is [X], keywords: [Y], deliver to [feishu group name], archive to [path]
51```
52
53The agent will configure keywords, delivery target, and archive path automatically.
54
55Then set up a daily cron job:
56
57```
58Set up a daily literature push at 08:30 Beijing time, 30 candidates, top 5 delivered
59```
60
61## Architecture
62
63The skill is organized in two layers:
64
65| Layer | Purpose | Files |
66|-------|---------|-------|
67| **Engine** | Scoring, classification, note templates, gap analysis | `references/scoring-system.md`, `references/gap-analysis.md`, `references/note-template.md` |
68| **Application** | Daily cron pipeline, delivery formatting, archival workflow | `references/push-format.md`, `references/cron-setup.md`, `references/review-compilation-workflow.md` |
69
70## Configuration
71
72All domain-specific content is configurable:
73
74- **Keywords** — your research keywords (English + Chinese)
75- **Scoring weights** — adjust the six dimensions for your field
76- **Classification rules** — define your own tier system (A-E or custom)
77- **Delivery target** — Feishu group, Telegram channel, email, etc.
78- **Archive path** — local vault/wiki directory
79
80A config template is provided in `templates/literature-push-template.md`.
81
82## Built-in Safeguards
83
84- **Score validation**: Each dimension capped, total recalculated — no 11/10 allowed
85- **Triple de-duplication**: DOI / arXiv ID / OpenAlex ID
86- **Graceful degradation**: Semantic Scholar down → auto-switch to OpenAlex + Crossref + arXiv
87- **Read-only archive**: Daily pipeline writes to `raw/` literature directory only; never modifies wiki/knowledge base without user approval
88
89## Related Skills
90
91- `nature-academic-search` — ad-hoc literature search (complementary; this skill adds structured daily automation)
92- `nature-citation` — CNS citation export (for importing pipeline discoveries into manuscripts)
93- `zotero` — library management (for long-term organization of pipeline outputs)
94- `arxiv` — arXiv API (used as a search source)
95
96## References
97
98| Reference | Purpose |
99|-----------|---------|
100| `references/scoring-system.md` | Six-dimension scoring rubric with weights, caps, and evaluation logic |
101| `references/gap-analysis.md` | Methodology for identifying research gaps through systematic literature survey |
102| `references/note-template.md` | Standardized literature note format with YAML frontmatter |
103| `references/push-format.md` | Daily digest message template with field guidelines and example |
104| `references/cron-setup.md` | Cron job creation, verification, and manual fallback procedures |
105| `references/review-compilation-workflow.md` | End-to-end workflow for concentrated literature review writing |
106
107## Pitfalls
108
1091. **Keyword drift**: Review keywords monthly — research directions evolve
1102. **Score inflation**: Subagents may inflate scores; always validate arithmetic
1113. **Duplicate creep**: Classic papers will reappear; maintain a dedup index
1124. **Wiki safety**: Pipeline writes to `raw/` only; wiki integration is manual
1135. **Cron locality**: Hermes cron is local, not cloud — machine must be running