research-paper-kb

Persistent cross-session knowledge base for research papers. Ingest arXiv/DOI → extract method, gap, threat level → append to PAPERS.md. Never lose paper context again across sessions.

Jump to install

Repository: ECNU-ICALK/Ecology-Harness
Last source activity: April 25, 2026 at 05:34
Detected SKILL.md language: English
Stars: 3
Forks: 0

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

Back to search Back to installation

name	research-paper-kb
slug	research-paper-kb
triggers	/research-paper-kb
author	IlkhamFY
license	MIT
hub_pack	clawhub-research
trust_level	community
upstream_url	https://clawhub.ai/skills/research-paper-kb
audit_status	reviewed
description	Persistent cross-session knowledge base for research papers. Ingest arXiv/DOI → extract method, gap, threat level → append to PAPERS.md. Never lose paper context again across sessions.
homepage	https://github.com/IlkhamFY/stch-botorch
metadata	{"author":"IlkhamFY","category":"Academic & Research","tags":["research","papers","arxiv","bibtex","knowledge-base","literature","academic","persistent-memory"]}

research-paper-kb

Persistent research paper knowledge base for AI agents.

Ingest any paper (arXiv URL, DOI, or title) and extract structured intelligence into a permanent PAPERS.md knowledge base that survives across sessions. Never lose context on a paper again.

Trigger Conditions

Use this skill when the user:

Pastes an arXiv URL (e.g. https://arxiv.org/abs/2310.12345)
Pastes a DOI (e.g. 10.1038/s41586-024-07156-8)
Says "add this paper to my KB" / "track this paper" / "save this paper"
Says "what do we know about [paper title]"
Says "update my paper KB" / "scan my PAPERS.md"
Says "show me the papers I'm tracking" / "what papers have I saved"

What This Skill Does

Fetches the paper abstract, metadata, and key sections
Extracts structured intelligence (method, gap, threat level, overlap)
Generates a clean BibTeX entry
Appends a structured entry to PAPERS.md in the workspace
Updates MEMORY.md with a pointer so future sessions know the KB exists
Works across sessions — the knowledge base is a file, not context

Step-by-Step Instructions

Step 1: Identify the Paper

Accept any of:

arXiv URL: https://arxiv.org/abs/XXXX.XXXXX
arXiv ID: 2310.12345 or 2310.12345v2
DOI: 10.XXXX/...
Title string: look up via Semantic Scholar API

Normalize to arXiv ID or DOI before proceeding.

Step 2: Fetch Paper Metadata

For arXiv papers — fetch the abstract page:

https://arxiv.org/abs/<arxiv_id>

Extract: title, authors, date, abstract, subject categories.

Also fetch the Semantic Scholar API for structured metadata:

https://api.semanticscholar.org/graph/v1/paper/arXiv:<arxiv_id>?fields=title,authors,year,abstract,tldr,citationCount,influentialCitationCount,fieldsOfStudy

For DOI papers — use Semantic Scholar:

https://api.semanticscholar.org/graph/v1/paper/<DOI>?fields=title,authors,year,abstract,tldr,citationCount,influentialCitationCount,externalIds

https://api.semanticscholar.org/graph/v1/paper/search?query=<url_encoded_title>&fields=title,authors,year,abstract,externalIds&limit=1

Field	What to Extract
Method	Core technical approach or contribution (1-2 sentences)
Gap they claim	What problem/limitation they say they're solving
Key results	Main quantitative or qualitative outcome
Overlap with user's work	Ask the user if context is unclear; or infer from prior PAPERS.md entries and MEMORY.md
Threat level	1-5 scale: how much does this threaten the user's research? (1=unrelated, 5=directly competing)
Citation count	From Semantic Scholar
Related papers	Up to 3 highly-cited related papers from the same fetch

@article{<AuthorYEARkeyword>,
  title     = {<Full Title>},
  author    = {<Author1> and <Author2> and ...},
  journal   = {arXiv preprint arXiv:<id>},
  year      = {<year>},
  url       = {https://arxiv.org/abs/<id>},
  note      = {arXiv:<id>}
}

@article{<AuthorYEARkeyword>,
  title     = {<Full Title>},
  author    = {<Author1> and <Author2> and ...},
  journal   = {<venue>},
  year      = {<year>},
  doi       = {<doi>},
  url       = {https://doi.org/<doi>}
}

# PAPERS.md — Research Paper Knowledge Base
> Auto-maintained by the `research-paper-kb` skill. Add papers with: "add this paper to my KB"
> Last updated: <date>

---

## [<Short Title>](<arxiv_or_doi_url>)
**Added:** <YYYY-MM-DD>  
**Authors:** <Author1>, <Author2>, ...  
**Venue:** <arXiv / Conference / Journal>  
**Citations:** <N> (Semantic Scholar)  
**Threat Level:** <1-5> — <one-line reason>

### Method
<1-2 sentence description of the core technical contribution>

### Gap They Claim
<What problem/limitation they say they're solving>

### Key Results
<Main outcomes, benchmarks, or claims>

### Overlap With My Work
<How this relates to the user's research — ask if unclear>

### Notes
<Any additional context the user provides, or leave blank>

### BibTeX
```bibtex
<bibtex entry>


### Step 6: Update MEMORY.md

After writing to PAPERS.md, append or update the PAPERS.md pointer in `MEMORY.md`:

Find or create a section `## Research Paper KB`:
```markdown
## Research Paper KB
- PAPERS.md exists in workspace root — <N> papers tracked as of <date>
- Latest addition: <Short title> (<threat level>/5)
- Run `research-paper-kb` to add more papers

✅ Added to PAPERS.md

**[Paper Title]** (<year>)
- Authors: ...
- Threat level: X/5 — <reason>
- BibTeX key: `AuthorYearWord`

PAPERS.md now has N papers. Run `show me my papers` to review.

Situation	Handling
arXiv paper not found	Try Semantic Scholar title search; if still not found, ask user to confirm title
DOI behind paywall	Fetch abstract from DOI.org metadata (`https://doi.org/<doi>` with Accept: application/json); note "full text unavailable"
Paper already in PAPERS.md	Detect by title/arXiv ID match; offer to update notes or threat level instead
User doesn't know their research area	Ask: "What's your research focus? I'll use this to assess overlap." Store in MEMORY.md
Semantic Scholar rate limit	Fall back to arXiv API: `http://export.arxiv.org/api/query?id_list=<id>`

name: research-paper-kb
version: 1.0.0
author: <your-github-handle>
category: Academic & Research
tags: [research, papers, arxiv, bibtex, knowledge-base, literature, academic, persistent-memory]
summary: Persistent cross-session knowledge base for research papers. Ingest arXiv/DOI → extract method/gap/threat level → append to PAPERS.md. Never lose paper context again.
requires: []