nature-literature-pipeline

Name: nature-literature-pipeline
Author: Yuan1z0825

1.4kinstalls1.8kforks

How to install nature-literature-pipeline?

yuan1z0825/nature-skills/nature-literature-pipeline

$npx -y skills add Yuan1z0825/nature-skills --skill nature-literature-pipeline

Installs into the current project.

Summary

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.

Files · 1

View on GitHub

SKILL.md

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

People who liked this also viewed

6 picks

Type

nature-literature-pipeline

1.4kinstalls1.8kforks

View on GitHub

How to install nature-literature-pipeline?

yuan1z0825/nature-skills/nature-literature-pipeline

$npx -y skills add Yuan1z0825/nature-skills --skill nature-literature-pipeline

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

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

People who liked this also viewed

6 picks

Type