@wentorai/research-plugins 1.0.0 → 1.2.0

package/skills/literature/search/baidu-scholar-guide/SKILL.md

@@ -0,0 +1,110 @@
+---
+name: baidu-scholar-guide
+description: "Using Baidu Scholar for Chinese and English academic literature search"
+metadata:
+  openclaw:
+    emoji: "🔍"
+    category: "literature"
+    subcategory: "search"
+    keywords: ["baidu scholar", "chinese literature", "academic search", "CNKI", "bilingual research", "chinese journals"]
+    source: "https://xueshu.baidu.com"
+---
+
+# Baidu Scholar Guide
+
+## Overview
+
+Baidu Scholar (百度学术, xueshu.baidu.com) is one of the largest academic search engines with particular strength in indexing Chinese-language scholarly publications. For researchers working with Chinese academic literature—or conducting bilingual research that spans both English and Chinese sources—Baidu Scholar provides access to content that is often underrepresented in Western databases like Google Scholar, Scopus, or Web of Science.
+
+Baidu Scholar indexes content from major Chinese academic databases including CNKI (China National Knowledge Infrastructure), Wanfang Data, VIP/CQVIP, as well as international sources like IEEE, Springer, Elsevier, and arXiv. This makes it a valuable complement to English-centric search tools, particularly for fields where Chinese research output is substantial: materials science, traditional medicine, agricultural science, renewable energy, and AI/ML.
+
+This skill covers effective search strategies on Baidu Scholar, navigating its interface, accessing full-text content, and integrating Chinese-language papers into your broader research workflow.
+
+## Search Strategies and Syntax
+
+### Basic Search
+
+Navigate to `https://xueshu.baidu.com` and enter your search terms. Baidu Scholar supports both Chinese and English queries. For bilingual research, run parallel searches:
+
+- English query: `"deep learning" medical imaging`
+- Chinese equivalent: `"深度学习" 医学影像`
+
+### Advanced Filtering
+
+After performing a search, use the left sidebar filters to narrow results:
+
+- **Time range** (时间): Filter by publication year or custom date range
+- **Author** (作者): Filter by specific author names
+- **Journal/Conference** (来源): Filter by publication venue
+- **Keywords** (关键词): Refine by subject keywords
+- **Type** (类型): Journal article, conference paper, thesis, patent
+
+### Effective Query Techniques
+
+1. **Use quotes for exact phrases**: `"convolutional neural network"` or `"卷积神经网络"`
+2. **Combine Chinese and English terms**: Many Chinese papers include English keywords—searching for the English term often finds Chinese papers too.
+3. **Search by author in both scripts**: A Chinese researcher may publish as both "张三" and "San Zhang"—search both forms.
+4. **Use subject-specific Chinese terminology**: Consult your field's Chinese glossary (术语表) for standard translations of technical terms.
+5. **Check "related searches" (相关搜索)**: Baidu Scholar suggests related queries that can reveal alternative terminology.
+
+## Navigating Chinese Academic Databases
+
+Baidu Scholar results often link to papers hosted on major Chinese databases. Understanding how to access these is essential:
+
+### CNKI (中国知网, cnki.net)
+- The largest Chinese academic database with over 200 million records
+- Requires institutional subscription for full-text access
+- Many Chinese universities provide VPN-based remote access
+- Supports export to EndNote, BibTeX, and other reference managers
+
+### Wanfang Data (万方数据, wanfangdata.com.cn)
+- Strong coverage of Chinese dissertations and conference proceedings
+- Offers a free preview of the first page of many papers
+- Institutional access widely available at Chinese universities
+
+### VIP/CQVIP (维普, cqvip.com)
+- Focuses on Chinese periodical literature
+- Good coverage of Chinese-language journals not indexed elsewhere
+
+### Access Tips
+
+- If you lack institutional access, check whether the paper is also available on the author's personal page, ResearchGate, or a university repository.
+- Many Chinese authors post preprints on arXiv or ChinaXiv (chinaxiv.org).
+- Baidu Scholar's "free download" (免费下载) links sometimes point to open-access copies.
+- Use the DOI when available to find the paper on the publisher's site.
+
+## Citation Features and Export
+
+Baidu Scholar provides several useful citation tools:
+
+- **Citation count**: Displayed below each result; click to see citing papers.
+- **Citation export**: Click "引用" (Cite) below any result to get formatted citations in GB/T 7714, MLA, APA, or BibTeX format.
+- **Related papers**: The "相关文章" link shows semantically similar papers.
+- **Author profiles**: Click an author name to see their indexed publications and citation metrics.
+
+### Exporting to Reference Managers
+
+To integrate Baidu Scholar results into your reference management workflow:
+
+1. Click the "引用" button on a search result
+2. Select "BibTeX" format
+3. Copy the BibTeX entry and import into Zotero, Mendeley, or your preferred manager
+4. Verify the metadata—Chinese-to-BibTeX conversion sometimes introduces encoding issues
+5. Manually add the English translation of the title in a `note` field for bilingual libraries
+
+## Best Practices for Bilingual Research
+
+When conducting research that spans Chinese and English literature:
+
+- **Maintain parallel search logs**: Document both your English and Chinese search strategies so your methodology is reproducible.
+- **Use consistent translation**: Establish a glossary mapping key technical terms between languages and use it consistently in your review.
+- **Cite Chinese sources properly**: Use the GB/T 7714 standard for Chinese references when publishing in Chinese venues, or transliterate titles when publishing in English journals.
+- **Cross-validate findings**: When a claim appears in Chinese literature but not in English sources (or vice versa), investigate whether it represents a genuine knowledge gap or a language barrier issue.
+- **Note database coverage differences**: Be transparent in your methodology about which databases you searched and in which languages.
+
+## References
+
+- Baidu Scholar: https://xueshu.baidu.com
+- CNKI: https://www.cnki.net
+- ChinaXiv: https://chinaxiv.org
+- GB/T 7714-2015 citation standard: https://std.samr.gov.cn

package/skills/literature/search/base-academic-search/SKILL.md

@@ -0,0 +1,196 @@
+---
+name: base-academic-search
+description: "Search 400M+ open access documents via the BASE search engine API"
+metadata:
+  openclaw:
+    emoji: "🔍"
+    category: "literature"
+    subcategory: "search"
+    keywords: ["BASE", "academic search", "open access", "Bielefeld", "OAI-PMH", "repository aggregator"]
+    source: "https://www.base-search.net/"
+---
+
+# BASE (Bielefeld Academic Search Engine) API
+
+## Overview
+
+BASE is one of the world's largest search engines for academic open access web resources. Operated by Bielefeld University Library, it indexes 400M+ documents from 11,000+ content providers including institutional repositories, preprint servers, and digital libraries. Unlike Google Scholar, BASE provides structured metadata, license information, and full-text links. The API is free with registration.
+
+## API Endpoints
+
+### Base URL
+
+```
+https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi
+```
+
+### Search
+
+```bash
+# Basic keyword search (JSON response)
+curl "https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi?\
+func=PerformSearch&query=climate+change+adaptation&format=json&hits=20"
+
+# Search with field filters
+curl "https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi?\
+func=PerformSearch&query=dctitle:transformer+AND+dcsubject:NLP&format=json"
+
+# Filter by document type and year
+curl "https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi?\
+func=PerformSearch&query=deep+learning&dctypenorm=121&dcyear:2024&format=json"
+
+# Open access only
+curl "https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi?\
+func=PerformSearch&query=CRISPR&dcrights:open&format=json"
+```
+
+### Search Fields
+
+| Field | Description | Example |
+|-------|-------------|---------|
+| `dctitle` | Title | `dctitle:attention+mechanism` |
+| `dccreator` | Author | `dccreator:vaswani` |
+| `dcsubject` | Subject/keywords | `dcsubject:machine+learning` |
+| `dcdescription` | Abstract | `dcdescription:neural+network` |
+| `dcyear` | Publication year | `dcyear:2024` |
+| `dctype` | Document type text | `dctype:article` |
+| `dctypenorm` | Normalized type code | `121` (journal article) |
+| `dcrights` | Access rights | `dcrights:open` |
+| `dclang` | Language | `dclang:eng` |
+| `dclink` | Source URL | `dclink:arxiv.org` |
+| `dcoa` | Open access status | `dcoa:1` (OA), `dcoa:2` (restricted) |
+| `dcprovider` | Content provider | `dcprovider:arxiv.org` |
+
+### Document Type Codes
+
+| Code | Type |
+|------|------|
+| `121` | Journal article |
+| `122` | Book / monograph |
+| `14` | Conference paper |
+| `15` | Thesis / dissertation |
+| `17` | Report |
+| `18` | Preprint |
+
+### Query Parameters
+
+| Parameter | Description | Default |
+|-----------|-------------|---------|
+| `func` | Must be `PerformSearch` | Required |
+| `query` | Search query with optional field prefixes | Required |
+| `format` | Response format: `json` or `xml` | `xml` |
+| `hits` | Results per page (max 125) | 10 |
+| `offset` | Pagination offset | 0 |
+| `sortby` | Sort: `dcyear desc`, `score desc` | relevance |
+
+## Response Structure
+
+```json
+{
+  "response": {
+    "numFound": 45200,
+    "start": 0,
+    "docs": [
+      {
+        "dctitle": "Attention Is All You Need",
+        "dccreator": ["Ashish Vaswani", "Noam Shazeer"],
+        "dcyear": "2017",
+        "dcsubject": ["machine learning", "attention mechanism"],
+        "dcdescription": "The dominant sequence transduction models...",
+        "dcidentifier": "https://arxiv.org/abs/1706.03762",
+        "dcsource": "arXiv.org",
+        "dcprovider": "arxiv.org",
+        "dcdocid": "abc123xyz",
+        "dcoa": 1,
+        "dctypenorm": ["18"],
+        "dclang": ["eng"]
+      }
+    ]
+  }
+}
+```
+
+## Python Usage
+
+```python
+import requests
+
+BASE_URL = "https://api.base-search.net/cgi-bin/BaseHttpSearchInterface.fcgi"
+
+
+def search_base(query: str, hits: int = 20,
+                doc_type: int = None, oa_only: bool = False) -> list:
+    """Search BASE for academic open access documents."""
+    q = query
+    if doc_type:
+        q += f" AND dctypenorm:{doc_type}"
+    if oa_only:
+        q += " AND dcoa:1"
+
+    params = {
+        "func": "PerformSearch",
+        "query": q,
+        "format": "json",
+        "hits": hits,
+        "sortby": "dcyear desc",
+    }
+
+    resp = requests.get(BASE_URL, params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for doc in data.get("response", {}).get("docs", []):
+        results.append({
+            "title": doc.get("dctitle"),
+            "authors": doc.get("dccreator", []),
+            "year": doc.get("dcyear"),
+            "source": doc.get("dcsource"),
+            "url": doc.get("dcidentifier"),
+            "abstract": (doc.get("dcdescription") or "")[:300],
+            "open_access": doc.get("dcoa") == 1,
+            "type": doc.get("dctypenorm", []),
+        })
+    return results
+
+
+def search_dissertations(topic: str, lang: str = "eng") -> list:
+    """Find dissertations and theses on a topic."""
+    query = f"{topic} AND dctypenorm:15 AND dclang:{lang}"
+    return search_base(query, hits=50)
+
+
+def search_by_provider(query: str, provider: str) -> list:
+    """Search within a specific content provider."""
+    full_query = f"{query} AND dcprovider:{provider}"
+    return search_base(full_query)
+
+
+# Example: find recent open access ML papers
+papers = search_base("transformer self-attention", hits=10, oa_only=True)
+for p in papers:
+    oa = "OA" if p["open_access"] else "restricted"
+    print(f"[{p['year']}] {p['title']} ({oa}) — {p['source']}")
+
+# Example: find dissertations on climate modeling
+theses = search_dissertations("climate modeling ocean")
+for t in theses:
+    print(f"[{t['year']}] {t['title']} — {', '.join(t['authors'][:2])}")
+```
+
+## BASE vs Other Search Engines
+
+| Feature | BASE | Google Scholar | OpenAlex |
+|---------|------|---------------|----------|
+| Records | 400M+ | Unknown | 250M+ |
+| Open access focus | Yes | No | Yes |
+| Structured API | Yes | No official API | Yes |
+| License metadata | Yes | No | Partial |
+| Dissertation coverage | Excellent | Good | Limited |
+| Repository-level filtering | Yes | No | No |
+
+## References
+
+- [BASE Search Engine](https://www.base-search.net/)
+- [BASE API Documentation](https://www.base-search.net/about/en/about_develop.php)
+- [BASE Content Providers](https://www.base-search.net/about/en/about_sources.php)

package/skills/literature/search/chatpaper-guide/SKILL.md

@@ -0,0 +1,122 @@
+---
+name: chatpaper-guide
+description: "Use ChatPaper to summarize and search arXiv papers with LLM assistance"
+metadata:
+  openclaw:
+    emoji: "📑"
+    category: "literature"
+    subcategory: "search"
+    keywords: ["arxiv", "paper-summarization", "literature-search", "chatgpt", "research-acceleration"]
+    source: "https://github.com/kaixindelele/ChatPaper"
+---
+
+# ChatPaper Guide
+
+## Overview
+
+ChatPaper is an open-source tool that leverages large language models to automatically summarize, search, and analyze academic papers from arXiv. It addresses a fundamental challenge in modern research: the overwhelming volume of new publications makes it nearly impossible for researchers to keep up with developments in their fields through manual reading alone.
+
+The tool connects to the arXiv API to retrieve papers based on keyword queries, then uses LLM capabilities to generate structured summaries covering research motivation, methodology, key findings, and limitations. This enables researchers to rapidly triage large batches of papers and identify the most relevant ones for detailed study.
+
+With over 19,000 GitHub stars, ChatPaper has become a widely adopted tool in the research community. It supports multiple LLM backends and offers both command-line and web-based interfaces, making it accessible to researchers with varying levels of technical expertise.
+
+## Installation and Setup
+
+Clone the repository and install dependencies:
+
+```bash
+git clone https://github.com/kaixindelele/ChatPaper.git
+cd ChatPaper
+pip install -r requirements.txt
+```
+
+Configure your LLM API access by setting environment variables:
+
+```bash
+# For OpenAI API
+export OPENAI_API_KEY=$OPENAI_API_KEY
+
+# Optional: use a custom API endpoint
+export OPENAI_BASE_URL=$OPENAI_BASE_URL
+```
+
+Alternatively, edit the configuration directly in the settings file to specify your preferred model and API parameters. The tool supports OpenAI models as well as compatible alternatives.
+
+Verify the installation by running a test query:
+
+```bash
+python chat_paper.py --query "transformer attention mechanism" --max_results 3
+```
+
+## Core Features
+
+**Automated Paper Search and Summarization**: ChatPaper queries arXiv based on your research interests and generates concise, structured summaries for each paper:
+
+```bash
+# Search for recent papers on a topic
+python chat_paper.py \
+  --query "graph neural networks drug discovery" \
+  --max_results 10 \
+  --sort "Relevance" \
+  --language "en"
+```
+
+Each summary is structured to highlight the core research question, proposed method, experimental results, and conclusions, saving significant reading time during literature reviews.
+
+**Batch Processing**: Process multiple search queries or a list of arXiv paper IDs in a single run:
+
+```bash
+# Summarize specific papers by arXiv ID
+python chat_paper.py \
+  --pdf_path "2301.00234,2302.01567,2303.04589" \
+  --language "en"
+```
+
+**Multi-Language Output**: Generate summaries in your preferred language regardless of the source paper language. This is particularly useful for researchers who think and write in a language different from the papers they read:
+
+```bash
+python chat_paper.py \
+  --query "quantum computing optimization" \
+  --language "zh" \
+  --max_results 5
+```
+
+**Research Report Generation**: Beyond individual summaries, ChatPaper can compile comparative analysis reports across multiple papers on the same topic, identifying common themes, methodological differences, and research gaps.
+
+## Academic Workflow Integration
+
+ChatPaper integrates into research workflows at several critical stages:
+
+**Daily Literature Monitoring**: Set up automated scripts to check for new papers in your research area each morning. Create a cron job or scheduled task that runs ChatPaper queries and delivers summaries to your inbox or a designated folder:
+
+```bash
+# Example daily monitoring script
+python chat_paper.py \
+  --query "large language model reasoning" \
+  --max_results 20 \
+  --sort "LastUpdatedDate" \
+  --days 1 \
+  --save_path ./daily_summaries/
+```
+
+**Systematic Review Support**: When conducting systematic literature reviews, use ChatPaper to generate initial screening summaries for a large pool of candidate papers. This accelerates the title-and-abstract screening phase by providing structured, consistent summaries that highlight methodological details often buried in abstracts.
+
+**Research Group Discussions**: Generate summary documents for journal club or lab meeting preparation. Share the structured summaries with your group so everyone arrives with baseline understanding of the papers under discussion.
+
+**Identifying Research Gaps**: By summarizing many papers in a subfield simultaneously, patterns emerge in what has been studied and what remains unexplored. ChatPaper summaries can be analyzed collectively to map the landscape of a research area.
+
+## Advanced Usage and Tips
+
+**Custom Prompts**: Modify the summarization prompts to focus on aspects most relevant to your research. For example, you might emphasize dataset details for data-centric work or focus on theoretical contributions for more mathematical fields.
+
+**Combining with Reference Managers**: Export ChatPaper summaries alongside BibTeX entries for direct import into Zotero, Mendeley, or other reference management tools. This creates an annotated bibliography with minimal manual effort.
+
+**Rate Limiting Considerations**: When processing large batches, be mindful of both arXiv API rate limits and your LLM provider quotas. Space requests appropriately and consider using local or self-hosted models for high-volume processing.
+
+**Quality Verification**: LLM-generated summaries may occasionally contain inaccuracies. Always verify critical claims by checking the original paper, particularly for numerical results, statistical significance values, and methodological details that require precise interpretation.
+
+## References
+
+- ChatPaper repository: https://github.com/kaixindelele/ChatPaper
+- arXiv API documentation: https://info.arxiv.org/help/api/
+- Related tool ChatReviewer for automated paper review generation

package/skills/literature/search/citeseerx-api/SKILL.md

@@ -0,0 +1,183 @@
+---
+name: citeseerx-api
+description: "Search computer science literature via the CiteSeerX digital library"
+metadata:
+  openclaw:
+    emoji: "📄"
+    category: "literature"
+    subcategory: "search"
+    keywords: ["CiteSeerX", "computer science", "citation index", "academic search", "CS literature", "autonomous citation"]
+    source: "https://citeseerx.ist.psu.edu/"
+---
+
+# CiteSeerX API
+
+## Overview
+
+CiteSeerX is a scientific literature digital library focusing on computer and information science, with 10M+ documents and 100M+ citations. It provides autonomous citation indexing — extracting and linking citations without manual curation. The API supports document search, citation lookup, and metadata retrieval. Free, no authentication required.
+
+## API Endpoints
+
+### Base URL
+
+```
+https://citeseerx.ist.psu.edu/api
+```
+
+### Document Search
+
+```bash
+# Keyword search
+curl "https://citeseerx.ist.psu.edu/api/search?q=graph+neural+networks&start=0&rows=20"
+
+# Search by title
+curl "https://citeseerx.ist.psu.edu/api/search?q=title:attention+is+all+you+need"
+
+# Search by author
+curl "https://citeseerx.ist.psu.edu/api/search?q=author:hinton&rows=25"
+
+# Filter by year
+curl "https://citeseerx.ist.psu.edu/api/search?q=federated+learning&year=2024"
+
+# Sort by citation count
+curl "https://citeseerx.ist.psu.edu/api/search?q=reinforcement+learning&sort=citationCount+desc"
+```
+
+### Get Document by ID
+
+```bash
+# Get document metadata
+curl "https://citeseerx.ist.psu.edu/api/document?doi=10.1.1.123.456"
+
+# Get citations for a document
+curl "https://citeseerx.ist.psu.edu/api/citations?doi=10.1.1.123.456"
+
+# Get citing documents
+curl "https://citeseerx.ist.psu.edu/api/citedby?doi=10.1.1.123.456"
+```
+
+### Query Parameters
+
+| Parameter | Description | Example |
+|-----------|-------------|---------|
+| `q` | Search query | `q=deep+learning` |
+| `start` | Pagination offset | `start=20` |
+| `rows` | Results per page | `rows=50` |
+| `sort` | Sort field | `citationCount desc` |
+| `year` | Filter by year | `year=2024` |
+| `doi` | CiteSeerX document ID | `doi=10.1.1.123.456` |
+
+## Response Structure
+
+```json
+{
+  "response": {
+    "numFound": 5200,
+    "docs": [
+      {
+        "id": "10.1.1.123.456",
+        "title": "Graph Neural Networks: A Review",
+        "authors": ["Zhou, Jie", "Cui, Ganqu"],
+        "year": 2020,
+        "abstract": "Graph neural networks have been widely applied...",
+        "venue": "AI Open",
+        "citationCount": 3500,
+        "url": "https://citeseerx.ist.psu.edu/doc/10.1.1.123.456"
+      }
+    ]
+  }
+}
+```
+
+## Python Usage
+
+```python
+import requests
+
+BASE_URL = "https://citeseerx.ist.psu.edu/api"
+
+
+def search_citeseerx(query: str, rows: int = 20,
+                     sort_by_citations: bool = False) -> list:
+    """Search CiteSeerX computer science literature."""
+    params = {
+        "q": query,
+        "rows": rows,
+        "start": 0,
+    }
+    if sort_by_citations:
+        params["sort"] = "citationCount desc"
+
+    resp = requests.get(f"{BASE_URL}/search", params=params, timeout=30)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for doc in data.get("response", {}).get("docs", []):
+        results.append({
+            "id": doc.get("id"),
+            "title": doc.get("title"),
+            "authors": doc.get("authors", []),
+            "year": doc.get("year"),
+            "venue": doc.get("venue"),
+            "citations": doc.get("citationCount", 0),
+            "abstract": doc.get("abstract", "")[:300],
+            "url": doc.get("url"),
+        })
+    return results
+
+
+def get_citations(doc_id: str) -> list:
+    """Get papers cited by a document."""
+    resp = requests.get(
+        f"{BASE_URL}/citations",
+        params={"doi": doc_id},
+        timeout=30,
+    )
+    resp.raise_for_status()
+    return resp.json().get("citations", [])
+
+
+def get_cited_by(doc_id: str) -> list:
+    """Get papers that cite a document."""
+    resp = requests.get(
+        f"{BASE_URL}/citedby",
+        params={"doi": doc_id},
+        timeout=30,
+    )
+    resp.raise_for_status()
+    return resp.json().get("citedby", [])
+
+
+# Example: find most-cited CS papers on a topic
+papers = search_citeseerx("knowledge distillation",
+                          rows=10, sort_by_citations=True)
+for p in papers:
+    print(f"[{p['year']}] {p['title']} (cited: {p['citations']})")
+
+# Example: citation chain analysis
+if papers:
+    refs = get_citations(papers[0]["id"])
+    print(f"\nReferences of top paper ({len(refs)} citations):")
+    for r in refs[:5]:
+        print(f"  -> {r.get('title', 'Unknown')}")
+```
+
+## Unique Features
+
+- **Autonomous citation indexing**: Automatically extracts and links citations from PDF
+- **CS focus**: Deep coverage of computer science subdisciplines
+- **Citation graph**: Full bidirectional citation linking
+- **Free PDF access**: Links to crawled open-access PDFs
+
+## Limitations
+
+- Primarily CS/information science (limited other fields)
+- Some metadata may be noisy (auto-extracted from PDF)
+- Coverage strongest for older papers (2000-2020)
+
+## References
+
+- [CiteSeerX](https://citeseerx.ist.psu.edu/)
+- [CiteSeerX Documentation](https://citeseerx.ist.psu.edu/about)
+- Giles, C.L., Bollacker, K.D., Lawrence, S. (1998). "CiteSeer: An Automatic Citation Indexing System." *ACM DL*.