@wentorai/research-plugins 1.0.0 → 1.2.0

package/skills/literature/search/ieee-xplore-api/SKILL.md

@@ -0,0 +1,177 @@
+---
+name: ieee-xplore-api
+description: "Search IEEE's 6M+ engineering and CS publications via the Xplore API"
+metadata:
+  openclaw:
+    emoji: "🔌"
+    category: "literature"
+    subcategory: "search"
+    keywords: ["ieee", "engineering literature", "computer science", "technical standards", "conference papers", "xplore"]
+    source: "https://developer.ieee.org/"
+---
+
+# IEEE Xplore API
+
+## Overview
+
+IEEE Xplore provides access to over 6 million technical documents — journal articles, conference proceedings, technical standards, and books — covering electrical engineering, computer science, and related fields. The API enables metadata search, full-text access (with subscription), and DOI-based batch lookup. Requires an API key (free registration) and institutional subscription for full features.
+
+## API Endpoints
+
+### Base URL
+
+```
+https://ieeexploreapi.ieee.org/api/v1/search/articles
+```
+
+### Metadata Search
+
+```bash
+# Basic keyword search
+curl "https://ieeexploreapi.ieee.org/api/v1/search/articles?\
+apikey=YOUR_API_KEY&\
+querytext=transformer+attention+mechanism&\
+max_records=25"
+
+# Search with filters
+curl "https://ieeexploreapi.ieee.org/api/v1/search/articles?\
+apikey=YOUR_API_KEY&\
+querytext=federated+learning&\
+start_year=2022&\
+end_year=2026&\
+content_type=Conferences&\
+max_records=50"
+```
+
+### Query Parameters
+
+| Parameter | Description | Example |
+|-----------|-------------|---------|
+| `apikey` | API key (required) | `apikey=YOUR_KEY` |
+| `querytext` | Free-text search | `querytext=neural+network` |
+| `article_title` | Title search | `article_title=BERT` |
+| `author` | Author name | `author=Vaswani` |
+| `abstract` | Abstract search | `abstract=reinforcement+learning` |
+| `index_terms` | IEEE keyword terms | `index_terms=machine+learning` |
+| `d-au` | Exact author | `d-au=Yann+LeCun` |
+| `start_year` | From year | `start_year=2020` |
+| `end_year` | To year | `end_year=2026` |
+| `content_type` | Document type | `Journals`, `Conferences`, `Standards`, `Books` |
+| `publication_title` | Venue name | `publication_title=CVPR` |
+| `max_records` | Results (max 200) | `max_records=50` |
+| `start_record` | Pagination offset | `start_record=51` |
+| `sort_field` | Sort by | `article_date`, `article_title` |
+| `sort_order` | Sort direction | `asc` or `desc` |
+
+### Boolean Search
+
+```bash
+# Boolean operators: AND, OR, NOT
+querytext=(machine AND learning) NOT survey
+
+# Phrase search
+querytext="graph neural network"
+
+# Field-specific boolean
+article_title="attention" AND author="Vaswani"
+```
+
+### DOI Batch Lookup
+
+```bash
+# Look up up to 25 DOIs at once
+curl "https://ieeexploreapi.ieee.org/api/v1/search/articles?\
+apikey=YOUR_API_KEY&\
+doi=10.1109/CVPR.2024.12345&\
+doi=10.1109/TPAMI.2023.67890"
+```
+
+## Response Structure
+
+```json
+{
+  "total_records": 1250,
+  "articles": [
+    {
+      "title": "Article Title",
+      "authors": {
+        "authors": [
+          {"full_name": "Author Name", "affiliation": "University"}
+        ]
+      },
+      "abstract": "The abstract text...",
+      "publication_title": "IEEE CVPR 2024",
+      "content_type": "Conferences",
+      "doi": "10.1109/CVPR.2024.12345",
+      "publication_date": "2024-06-01",
+      "start_page": "100",
+      "end_page": "110",
+      "citing_paper_count": 15,
+      "pdf_url": "https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=12345",
+      "html_url": "https://ieeexplore.ieee.org/document/12345"
+    }
+  ]
+}
+```
+
+## Python Usage
+
+```python
+import os
+import requests
+
+API_KEY = os.environ["IEEE_API_KEY"]
+BASE_URL = "https://ieeexploreapi.ieee.org/api/v1/search/articles"
+
+def search_ieee(query: str, max_results: int = 25,
+                content_type: str = None, start_year: int = None) -> list:
+    """Search IEEE Xplore for technical publications."""
+    params = {
+        "apikey": API_KEY,
+        "querytext": query,
+        "max_records": max_results,
+        "sort_field": "article_date",
+        "sort_order": "desc"
+    }
+    if content_type:
+        params["content_type"] = content_type
+    if start_year:
+        params["start_year"] = start_year
+
+    resp = requests.get(BASE_URL, params=params)
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for article in data.get("articles", []):
+        authors = [a["full_name"] for a in article.get("authors", {}).get("authors", [])]
+        results.append({
+            "title": article.get("title"),
+            "authors": authors,
+            "venue": article.get("publication_title"),
+            "year": article.get("publication_date", "")[:4],
+            "doi": article.get("doi"),
+            "citations": article.get("citing_paper_count", 0),
+            "url": article.get("html_url")
+        })
+    return results
+
+# Example
+papers = search_ieee("edge computing IoT", content_type="Journals", start_year=2023)
+for p in papers:
+    print(f"[{p['year']}] {p['title']} — {p['venue']} (cited: {p['citations']})")
+```
+
+## Access Tiers
+
+| Tier | Access Level | Requirements |
+|------|-------------|-------------|
+| **Free** | Metadata + abstracts | API key registration |
+| **Open Access** | Full text of OA articles | API key |
+| **Institutional** | Full text of all articles | API key + subscription |
+
+## References
+
+- [IEEE Xplore API Portal](https://developer.ieee.org/)
+- [API Documentation](https://developer.ieee.org/docs)
+- [IEEE Xplore Digital Library](https://ieeexplore.ieee.org/)

package/skills/literature/search/lens-scholarly-api/SKILL.md

@@ -0,0 +1,211 @@
+---
+name: lens-scholarly-api
+description: "Search 300M+ scholarly and patent records via the Lens.org API"
+metadata:
+  openclaw:
+    emoji: "🔎"
+    category: "literature"
+    subcategory: "search"
+    keywords: ["Lens.org", "patent search", "scholarly search", "citation linking", "innovation", "prior art"]
+    source: "https://www.lens.org/"
+---
+
+# Lens.org Scholarly and Patent API
+
+## Overview
+
+Lens.org provides unified access to 300M+ scholarly articles and 150M+ patent records with cross-linkage between them. Uniquely, Lens connects academic research to patent citations, enabling innovation tracking and prior art discovery. The API offers full-text search, citation analysis, and patent-paper linkage. Free for non-commercial use with registration (up to 1,000 requests/day).
+
+## Authentication
+
+```bash
+# Register at https://www.lens.org/lens/user/subscriptions
+# API token provided in your account settings
+# Include in header: Authorization: Bearer YOUR_TOKEN
+```
+
+## API Endpoints
+
+### Scholarly Search
+
+```bash
+# POST-based search
+curl -X POST "https://api.lens.org/scholarly/search" \
+  -H "Authorization: Bearer $LENS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "query": {
+      "match": {"field_of_study": "machine learning"}
+    },
+    "size": 20,
+    "from": 0,
+    "sort": [{"year_published": "desc"}]
+  }'
+
+# Boolean query
+curl -X POST "https://api.lens.org/scholarly/search" \
+  -H "Authorization: Bearer $LENS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "query": {
+      "bool": {
+        "must": [
+          {"match": {"title": "transformer"}},
+          {"range": {"year_published": {"gte": 2023}}}
+        ],
+        "should": [
+          {"match": {"abstract": "attention mechanism"}}
+        ]
+      }
+    },
+    "size": 25
+  }'
+```
+
+### Patent Search
+
+```bash
+curl -X POST "https://api.lens.org/patent/search" \
+  -H "Authorization: Bearer $LENS_TOKEN" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "query": {
+      "bool": {
+        "must": [
+          {"match": {"title": "neural network"}},
+          {"term": {"jurisdiction": "US"}}
+        ]
+      }
+    },
+    "size": 20
+  }'
+```
+
+### Scholarly Fields
+
+| Field | Description | Type |
+|-------|-------------|------|
+| `title` | Article title | text |
+| `abstract` | Abstract text | text |
+| `author.display_name` | Author name | text |
+| `year_published` | Publication year | integer |
+| `source.title` | Journal/venue name | text |
+| `field_of_study` | Research field | text |
+| `doi` | DOI identifier | keyword |
+| `pmid` | PubMed ID | keyword |
+| `citing_patent_count` | Patents citing this work | integer |
+| `scholarly_citations_count` | Citation count | integer |
+| `open_access.is_oa` | Open access status | boolean |
+
+## Python Usage
+
+```python
+import os
+import requests
+
+TOKEN = os.environ["LENS_API_TOKEN"]
+BASE_URL = "https://api.lens.org"
+HEADERS = {
+    "Authorization": f"Bearer {TOKEN}",
+    "Content-Type": "application/json",
+}
+
+
+def search_scholarly(query: str, size: int = 20,
+                     min_year: int = None,
+                     fields: list = None) -> list:
+    """Search Lens scholarly records."""
+    must_clauses = [{"match": {"title": query}}]
+    if min_year:
+        must_clauses.append(
+            {"range": {"year_published": {"gte": min_year}}}
+        )
+
+    body = {
+        "query": {"bool": {"must": must_clauses}},
+        "size": size,
+        "sort": [{"scholarly_citations_count": "desc"}],
+    }
+    if fields:
+        body["include"] = fields
+
+    resp = requests.post(
+        f"{BASE_URL}/scholarly/search",
+        headers=HEADERS,
+        json=body,
+    )
+    resp.raise_for_status()
+    data = resp.json()
+
+    results = []
+    for doc in data.get("data", []):
+        results.append({
+            "title": doc.get("title"),
+            "authors": [a.get("display_name", "")
+                        for a in doc.get("authors", [])[:5]],
+            "year": doc.get("year_published"),
+            "source": doc.get("source", {}).get("title"),
+            "doi": doc.get("doi"),
+            "citations": doc.get("scholarly_citations_count", 0),
+            "patent_citations": doc.get("citing_patent_count", 0),
+            "open_access": doc.get("open_access", {}).get("is_oa"),
+        })
+    return results
+
+
+def find_patent_cited_papers(topic: str, min_patents: int = 5) -> list:
+    """Find papers cited by patents (innovation indicators)."""
+    body = {
+        "query": {
+            "bool": {
+                "must": [
+                    {"match": {"title": topic}},
+                    {"range": {"citing_patent_count": {"gte": min_patents}}},
+                ]
+            }
+        },
+        "size": 50,
+        "sort": [{"citing_patent_count": "desc"}],
+    }
+
+    resp = requests.post(
+        f"{BASE_URL}/scholarly/search",
+        headers=HEADERS,
+        json=body,
+    )
+    resp.raise_for_status()
+    return resp.json().get("data", [])
+
+
+# Example: find high-impact ML papers cited by patents
+papers = search_scholarly("deep learning", size=10, min_year=2020)
+for p in papers:
+    print(f"[{p['year']}] {p['title']}")
+    print(f"  Citations: {p['citations']} scholarly, "
+          f"{p['patent_citations']} patent")
+
+# Example: find industry-impactful research
+patent_cited = find_patent_cited_papers("battery technology")
+for doc in patent_cited[:5]:
+    print(f"{doc['title']} — {doc.get('citing_patent_count')} patents")
+```
+
+## Unique Features
+
+- **Patent-paper linkage**: Discover which research is cited in patents
+- **Unified search**: Scholarly + patent in one platform
+- **Innovation metrics**: Track technology transfer from academia to industry
+- **Prior art search**: Find relevant literature for patent applications
+
+## Rate Limits
+
+| Tier | Daily requests | Results per query |
+|------|---------------|-------------------|
+| Free (non-commercial) | 1,000 | 1,000 |
+| Institutional | 10,000+ | 10,000 |
+
+## References
+
+- [Lens.org](https://www.lens.org/)
+- [Lens API Documentation](https://docs.api.lens.org/)
+- [Lens Scholarly Search](https://www.lens.org/lens/search/scholar/list)

package/skills/literature/search/multi-database-literature-search/SKILL.md

@@ -0,0 +1,198 @@
+---
+name: multi-database-literature-search
+description: "Conduct comprehensive literature searches across multiple academic databases"
+metadata:
+  openclaw:
+    emoji: "🔍"
+    category: "literature"
+    subcategory: "search"
+    keywords: ["multi-database search", "systematic review", "literature search", "academic databases", "cross-database", "search strategy"]
+    source: "https://clawhub.ai/jpjy/literature-search"
+---
+
+# Multi-Database Literature Search
+
+## Overview
+
+No single database covers all academic literature. A comprehensive search requires querying multiple databases, each with its own coverage, search syntax, and strengths. This guide provides a structured approach to searching across Google Scholar, PubMed, Semantic Scholar, arXiv, IEEE Xplore, ACM Digital Library, and Scopus/Web of Science, with strategies for deduplication and result management.
+
+## Database Coverage Map
+
+| Database | Coverage | Strengths | Free? |
+|----------|----------|-----------|-------|
+| **Google Scholar** | All disciplines, broadest | Grey literature, books, citations | Yes |
+| **Semantic Scholar** | 220M+ papers, all fields | AI-powered relevance, citation context, TLDR | Yes |
+| **PubMed** | Biomedical, life sciences | MeSH terms, clinical trials, 36M+ records | Yes |
+| **arXiv** | Physics, CS, math, econ, stats | Preprints, latest research, open access | Yes |
+| **OpenAlex** | 250M+ works, all fields | Open metadata, citation network, concepts | Yes |
+| **Scopus** | All disciplines | Citation metrics, author profiles | Subscription |
+| **Web of Science** | All disciplines | Impact factors, citation reports | Subscription |
+| **IEEE Xplore** | Engineering, CS | IEEE/IET publications, standards | Partial |
+| **ACM DL** | Computer science | ACM proceedings, computing reviews | Partial |
+| **SSRN** | Social sciences, economics | Working papers, preprints | Yes |
+| **JSTOR** | Humanities, social sciences | Historical archives, journals | Partial |
+
+## Search Strategy Design
+
+### Step 1: Decompose Your Question
+
+```
+Research question:
+  "How does remote work affect employee productivity in knowledge-intensive firms?"
+
+Concept blocks:
+  Block A: remote work | telework | work from home | telecommuting | hybrid work
+  Block B: productivity | performance | output | efficiency | effectiveness
+  Block C: knowledge work | knowledge-intensive | white collar | professional
+```
+
+### Step 2: Build Database-Specific Queries
+
+Each database has different syntax. Translate your concept blocks:
+
+**Google Scholar**:
+```
+("remote work" OR telework OR "work from home") AND
+(productivity OR performance OR output) AND
+("knowledge work" OR "knowledge-intensive" OR professional)
+```
+
+**PubMed**:
+```
+("remote work"[Title/Abstract] OR "telework"[Title/Abstract] OR
+ "work from home"[Title/Abstract]) AND
+("productivity"[Title/Abstract] OR "performance"[Title/Abstract]) AND
+("knowledge workers"[Title/Abstract] OR "professional"[Title/Abstract])
+```
+
+**Semantic Scholar API**:
+```bash
+curl "https://api.semanticscholar.org/graph/v1/paper/search?\
+query=remote+work+productivity+knowledge+workers&\
+year=2019-2026&\
+fieldsOfStudy=Economics,Business&\
+limit=100&\
+fields=title,authors,year,abstract,citationCount,url"
+```
+
+**arXiv**:
+```
+all:"remote work" AND all:productivity AND cat:econ.*
+```
+
+### Step 3: Execute Searches Systematically
+
+```markdown
+## Search Log Template (PRISMA-compliant)
+
+| # | Database | Date | Query String | Filters | Results | Relevant | Notes |
+|---|----------|------|-------------|---------|---------|----------|-------|
+| 1 | Google Scholar | 2026-03-10 | [full query] | 2019-2026 | 1,240 | ~80 | Top 200 screened |
+| 2 | Semantic Scholar | 2026-03-10 | [full query] | Year ≥ 2019 | 487 | ~45 | API, sorted by relevance |
+| 3 | PubMed | 2026-03-10 | [full query] | 5 years | 156 | ~30 | MeSH term: Teleworking |
+| 4 | SSRN | 2026-03-10 | [full query] | — | 89 | ~20 | Working papers |
+| 5 | Scopus | 2026-03-10 | [full query] | 2019-2026 | 312 | ~55 | Most overlap with GS |
+```
+
+## Deduplication
+
+After collecting results from multiple databases, remove duplicates:
+
+```python
+import pandas as pd
+from fuzzywuzzy import fuzz
+
+def deduplicate_papers(df: pd.DataFrame, title_col: str = "title",
+                        threshold: int = 90) -> pd.DataFrame:
+    """Remove duplicate papers based on fuzzy title matching."""
+    df = df.sort_values("citation_count", ascending=False)
+    keep = []
+    seen_titles = []
+
+    for _, row in df.iterrows():
+        title = row[title_col].lower().strip()
+        is_dup = False
+        for seen in seen_titles:
+            if fuzz.ratio(title, seen) >= threshold:
+                is_dup = True
+                break
+        if not is_dup:
+            keep.append(row)
+            seen_titles.append(title)
+
+    result = pd.DataFrame(keep)
+    print(f"Deduplicated: {len(df)} → {len(result)} ({len(df)-len(result)} duplicates removed)")
+    return result
+
+# Usage
+all_results = pd.concat([gs_results, s2_results, pubmed_results, scopus_results])
+unique = deduplicate_papers(all_results)
+```
+
+### DOI-Based Deduplication (More Reliable)
+
+```python
+def deduplicate_by_doi(df: pd.DataFrame) -> pd.DataFrame:
+    """Primary: DOI match. Fallback: fuzzy title match for missing DOIs."""
+    with_doi = df[df["doi"].notna()].drop_duplicates(subset="doi", keep="first")
+    without_doi = df[df["doi"].isna()]
+    without_doi_deduped = deduplicate_papers(without_doi, threshold=85)
+    return pd.concat([with_doi, without_doi_deduped]).reset_index(drop=True)
+```
+
+## Screening Workflow
+
+### Title/Abstract Screening
+
+```markdown
+After deduplication, screen titles and abstracts:
+
+Include if:
+  □ Directly addresses research question
+  □ Empirical study with data OR systematic review
+  □ Published in peer-reviewed venue OR reputable preprint server
+  □ Written in English or Chinese
+
+Exclude if:
+  □ Irrelevant population (e.g., manual labor when studying knowledge work)
+  □ No empirical component (pure opinion)
+  □ Duplicate or superseded version
+  □ Cannot access full text (after OA and institutional access attempts)
+```
+
+### Citation Chaining
+
+After initial screening, expand coverage:
+
+```
+Forward citation (who cited this paper?):
+  - Semantic Scholar: "Citations" tab
+  - Google Scholar: "Cited by" link
+  - Web of Science: "Citing Articles"
+
+Backward citation (what does this paper cite?):
+  - Read the reference list of each key paper
+  - Identify seminal works and foundational papers
+
+Typically adds 15-30% more relevant papers beyond database searches
+```
+
+## Recommended Search Order
+
+For maximum coverage with minimum effort:
+
+```
+1. Semantic Scholar (broad coverage, AI-powered ranking, free API)
+2. Google Scholar (broadest coverage, catches grey literature)
+3. Domain-specific DB (PubMed for biomedical, arXiv for CS/physics, SSRN for social science)
+4. Scopus or Web of Science (if institutional access available — adds citation metrics)
+5. Citation chaining from top 10 most relevant papers found so far
+6. Grey literature: Google, institutional repositories, conference websites
+```
+
+## References
+
+- Moher, D., et al. (2009). "PRISMA Statement." *BMJ*, 339, b2535.
+- Bramer, W. M., et al. (2017). "De-duplication of database search results." *BMC Medical Research Methodology*, 17(1), 1-9.
+- [Semantic Scholar API](https://api.semanticscholar.org/)
+- [PubMed Search Guide](https://pubmed.ncbi.nlm.nih.gov/help/)