@wentorai/research-plugins 1.3.2 → 1.4.2

package/skills/tools/diagram/mermaid-architect-guide/SKILL.md

@@ -56,7 +56,7 @@ C4Context
 
     System(platform, "Wentor Platform", "AI-powered research assistant ecosystem")
 
-    System_Ext(scholar, "Semantic Scholar", "Academic paper database")
+    System_Ext(scholar, "OpenAlex", "Academic paper database")
     System_Ext(crossref, "CrossRef", "DOI resolution and metadata")
     System_Ext(github, "GitHub", "Code and skill repositories")
 

package/skills/tools/diagram/plantuml-guide/SKILL.md

@@ -225,7 +225,7 @@ package "Data Layer" {
 }
 
 package "External APIs" {
-  [Semantic Scholar] as S2
+  [Unpaywall] as UP
   [CrossRef] as CR
   [OpenAlex] as OA
 }

package/skills/tools/document/grobid-pdf-parsing/SKILL.md

@@ -16,7 +16,7 @@ metadata:
 
 Academic PDFs are the primary format for distributing research, yet extracting structured data from them remains challenging. PDFs encode visual layout, not semantic structure -- headings, paragraphs, equations, tables, and citations are all just positioned text and graphics. GROBID (GeneRation Of BIbliographic Data) is the leading open-source tool for parsing academic PDFs into structured XML/TEI format, extracting metadata, body text, references, and figures with high accuracy.
 
-GROBID is used by major academic platforms including Semantic Scholar, CORE, and ResearchGate for large-scale document processing. It combines machine learning models (CRF and deep learning) with heuristic rules to handle the diverse formatting of academic papers across publishers and disciplines.
+GROBID is used by major academic platforms including CORE, ResearchGate, and others for large-scale document processing. It combines machine learning models (CRF and deep learning) with heuristic rules to handle the diverse formatting of academic papers across publishers and disciplines.
 
 This guide covers installing and running GROBID, using its REST API for batch processing, extracting specific elements (metadata, references, body sections), and integrating GROBID output into downstream workflows such as knowledge bases, systematic reviews, and literature analysis pipelines.
 

package/skills/tools/document/paper-parse-guide/SKILL.md

@@ -32,7 +32,7 @@ Both modes begin by parsing the paper's structure from its PDF or HTML source, e
 | DOI | Resolve via CrossRef/Unpaywall | Auto-fetches open access version |
 | arXiv ID | `https://arxiv.org/pdf/{id}` | Always available |
 | URL | Direct download | May require institutional access |
-| Semantic Scholar ID | S2 API + PDF link | Includes metadata |
+| OpenAlex ID | OpenAlex API + OA link | Includes metadata |
 
 ### PDF Parsing Pipeline
 
@@ -238,6 +238,6 @@ comparison = create_comparison_table(summaries,
 
 - GROBID: https://github.com/kermitt2/grobid
 - PyMuPDF: https://pymupdf.readthedocs.io
-- Semantic Scholar API: https://api.semanticscholar.org
+- OpenAlex API: https://api.openalex.org
 - Unpaywall API: https://unpaywall.org/products/api
 - S. Keshav, "How to Read a Paper" (2007): http://ccr.sigcomm.org/online/files/p83-keshavA.pdf

package/skills/tools/knowledge-graph/SKILL.md

@@ -1,9 +1,9 @@
 ---
 name: knowledge-graph-skills
-description: "10 knowledge graphs skills. Trigger: building knowledge graphs, connecting concepts, ontology design. Design: graph construction, traversal, and visualization for research knowledge."
+description: "9 knowledge graphs skills. Trigger: building knowledge graphs, connecting concepts, ontology design. Design: graph construction, traversal, and visualization for research knowledge."
 ---
 
-# Knowledge Graphs — 10 Skills
+# Knowledge Graphs — 9 Skills
 
 Select the skill matching the user's need, then `read` its SKILL.md.
 
@@ -16,6 +16,5 @@ Select the skill matching the user's need, then `read` its SKILL.md.
 | [notero-zotero-notion-guide](./notero-zotero-notion-guide/SKILL.md) | Sync Zotero references and annotations to Notion databases |
 | [ontology-design-guide](./ontology-design-guide/SKILL.md) | Design ontologies and knowledge graphs for research data modeling |
 | [openspg-guide](./openspg-guide/SKILL.md) | Ant Group knowledge graph engine with SPG and KAG framework |
-| [paperpile-notion-guide](./paperpile-notion-guide/SKILL.md) | Sync Paperpile references and annotations to Notion |
 | [rag-methodology-guide](./rag-methodology-guide/SKILL.md) | RAG architecture for academic knowledge retrieval and synthesis |
 | [zotero-markdb-connect-guide](./zotero-markdb-connect-guide/SKILL.md) | Sync Zotero references to Obsidian and Logseq markdown |

package/skills/tools/knowledge-graph/citation-network-builder/SKILL.md

@@ -44,12 +44,12 @@ OpenAlex (free):
   - Limits: Reference linking less complete than WoS
   - Best for: Large-scale analysis, reproducible research
 
-Semantic Scholar (free):
+CrossRef (free):
   - Format: JSON via REST API
-  - Coverage: ~200M papers, strong in CS/Biomed
-  - Strengths: Free, citation context, citation intents
-  - Limits: Weaker coverage in humanities and social sciences
-  - Best for: CS/AI-focused networks, citation intent analysis
+  - Coverage: ~150M DOIs across all publishers
+  - Strengths: Free, authoritative DOI metadata, reference linking
+  - Limits: No abstract text, citation counts may lag
+  - Best for: Cross-publisher networks, DOI resolution
 ```
 
 ### Data Cleaning for Network Construction

package/skills/tools/knowledge-graph/knowledge-graph-construction/SKILL.md

@@ -293,7 +293,7 @@ Provide a detailed answer citing specific papers, methods, and findings from the
 - **Start with a clear schema.** Define your entity types and relations before extracting data. A schema change later requires re-processing.
 - **Use persistent identifiers.** DOIs for papers, ORCIDs for authors, and canonical names for methods prevent duplicate nodes.
 - **Validate extracted triples.** LLM extraction is imperfect. Sample and manually verify 5-10% of extractions.
-- **Enrich with external data.** Link your KG to OpenAlex, Semantic Scholar, or Wikidata for additional metadata.
+- **Enrich with external data.** Link your KG to OpenAlex, CrossRef, or Wikidata for additional metadata.
 - **Version your graph.** Export snapshots regularly and track changes over time.
 - **Design queries before building.** Know what questions you want to answer before deciding on the schema.
 

package/skills/tools/ocr-translate/zotero-pdf2zh-guide/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "tools"
     subcategory: "ocr-translate"
+    emoji: "🌐"
     keywords:
       - pdf-translation
       - zotero-plugin

package/skills/tools/scraping/academic-web-scraping/SKILL.md

@@ -28,7 +28,6 @@ APIs are always preferable to scraping when available. They provide structured d
 
 | API | Data | Rate Limit | Auth |
 |-----|------|-----------|------|
-| Semantic Scholar | Papers, authors, citations | 100 req/sec (with key) | API key (free) |
 | OpenAlex | Papers, authors, venues, concepts | 100K req/day | Email in header |
 | Crossref | DOI metadata | 50 req/sec (polite pool) | Email in header |
 | PubMed (Entrez) | Biomedical literature | 10 req/sec (with key) | API key (free) |
@@ -319,7 +318,7 @@ class DataCollector:
 ## References
 
 - [OpenAlex API Documentation](https://docs.openalex.org/) -- Open bibliographic data API
-- [Semantic Scholar API](https://api.semanticscholar.org/) -- Paper and author data
+- [CrossRef API](https://api.crossref.org/) -- DOI resolution and metadata
 - [BeautifulSoup Documentation](https://www.crummy.com/software/BeautifulSoup/bs4/doc/) -- HTML parsing
 - [Scrapy Documentation](https://docs.scrapy.org/) -- Web scraping framework
 - [Playwright Documentation](https://playwright.dev/python/) -- Browser automation

package/skills/tools/scraping/google-scholar-scraper/SKILL.md

@@ -41,7 +41,7 @@ Ethical guidelines:
     OpenAlex could answer it instead
 
 Official and semi-official alternatives:
-  - Semantic Scholar API: free, 100 requests/sec, excellent coverage
+  - OpenAlex API: free, no key required, excellent coverage
   - OpenAlex API: free, comprehensive, well-documented
   - Crossref API: free, DOI-based metadata and citation counts
   - CORE API: free, full-text open access content
@@ -232,12 +232,12 @@ OpenAlex (openalex.org):
   - Data: titles, abstracts, citations, authors, institutions
   - Best for: large-scale bibliometric analysis
 
-Semantic Scholar (semanticscholar.org):
-  - Coverage: 200M+ papers
-  - API: REST, free key available
-  - Rate limit: 100 requests/sec with API key
-  - Data: titles, abstracts, citations, citation contexts, TLDR
-  - Best for: citation analysis, NLP on papers
+OpenAlex (openalex.org):
+  - Coverage: 250M+ works, all disciplines
+  - API: REST, no key required
+  - Rate limit: ~10 requests/sec polite
+  - Data: titles, abstracts, citations, concepts, author profiles
+  - Best for: cross-disciplinary analysis, open data research
 
 Crossref (crossref.org):
   - Coverage: 130M+ DOIs

package/skills/writing/citation/SKILL.md

@@ -11,7 +11,7 @@ Select the skill matching the user's need, then `read` its SKILL.md.
 |-------|-------------|
 | [academic-citation-manager](./academic-citation-manager/SKILL.md) | Manage academic citations across BibTeX, APA, MLA, and Chicago formats |
 | [bibtex-management-guide](./bibtex-management-guide/SKILL.md) | Clean, format, deduplicate, and manage BibTeX bibliography files for LaTeX |
-| [citation-assistant-skill](./citation-assistant-skill/SKILL.md) | Claude Code skill for citation workflow via Semantic Scholar |
+| [citation-assistant-skill](./citation-assistant-skill/SKILL.md) | Claude Code skill for citation workflow via OpenAlex and CrossRef |
 | [citation-style-guide](./citation-style-guide/SKILL.md) | APA, MLA, Chicago citation format guide with CSL configuration |
 | [jabref-reference-guide](./jabref-reference-guide/SKILL.md) | Guide to JabRef open-source BibTeX and BibLaTeX reference manager |
 | [jasminum-zotero-guide](./jasminum-zotero-guide/SKILL.md) | Guide to Jasminum for retrieving CNKI Chinese academic metadata in Zotero |

package/skills/writing/citation/academic-citation-manager/SKILL.md

@@ -18,7 +18,7 @@ Manage academic citations across multiple formats (BibTeX, APA 7th, MLA 9th, Chi
 
 Citation management is a persistent friction point in academic writing. Researchers collect references from multiple sources (databases, PDFs, colleagues, web pages), store them in different formats, and must output them in the specific style required by each target journal. Errors in citations -- misspelled author names, incorrect years, broken DOIs, inconsistent formatting -- are among the most common reasons for desk rejection and reviewer criticism.
 
-This skill provides a comprehensive citation management workflow that goes beyond what GUI reference managers offer. It can retrieve complete metadata from a DOI in seconds, convert between any citation format, detect and merge duplicate entries, validate entries against CrossRef and Semantic Scholar databases, and generate properly formatted bibliographies for any major citation style.
+This skill provides a comprehensive citation management workflow that goes beyond what GUI reference managers offer. It can retrieve complete metadata from a DOI in seconds, convert between any citation format, detect and merge duplicate entries, validate entries against CrossRef and OpenAlex databases, and generate properly formatted bibliographies for any major citation style.
 
 The approach is text-based and scriptable, making it ideal for integration with LaTeX workflows, Markdown writing pipelines, and automated document generation. All citation data is stored in standard BibTeX format as the canonical source, with on-demand conversion to other formats for specific manuscript requirements.
 
@@ -52,33 +52,36 @@ print(bibtex)
 # }
 ```
 
-### From Semantic Scholar
+### From OpenAlex
 
 ```python
-def get_citation_from_s2(paper_id):
-    """Retrieve citation data from Semantic Scholar API."""
-    url = f"https://api.semanticscholar.org/graph/v1/paper/{paper_id}"
-    params = {"fields": "title,authors,year,venue,doi,citationCount,externalIds"}
-    response = requests.get(url, params=params)
+def get_citation_from_openalex(work_id):
+    """Retrieve citation data from OpenAlex API."""
+    url = f"https://api.openalex.org/works/{work_id}"
+    headers = {"User-Agent": "ResearchPlugins/1.0 (https://wentor.ai)"}
+    response = requests.get(url, headers=headers)
     if response.status_code == 200:
         data = response.json()
         return format_as_bibtex(data)
     return None
 
-def format_as_bibtex(s2_data):
-    """Convert Semantic Scholar data to BibTeX."""
-    authors = s2_data.get("authors", [])
-    author_str = " and ".join(a["name"] for a in authors)
-    first_author = authors[0]["name"].split()[-1] if authors else "Unknown"
-    year = s2_data.get("year", "")
+def format_as_bibtex(oa_data):
+    """Convert OpenAlex data to BibTeX."""
+    authorships = oa_data.get("authorships", [])
+    author_str = " and ".join(a["author"]["display_name"] for a in authorships)
+    first_author = authorships[0]["author"]["display_name"].split()[-1] if authorships else "Unknown"
+    year = str(oa_data.get("publication_year", ""))
     key = f"{first_author}_{year}"
 
+    venue = oa_data.get("primary_location", {}) or {}
+    journal = (venue.get("source") or {}).get("display_name", "")
+
     return f"""@article{{{key},
-  title={{{s2_data.get('title', '')}}},
+  title={{{oa_data.get('title', '')}}},
   author={{{author_str}}},
   year={{{year}}},
-  journal={{{s2_data.get('venue', '')}}},
-  doi={{{s2_data.get('doi', '')}}}
+  journal={{{journal}}},
+  doi={{{oa_data.get('doi', '')}}}
 }}"""
 ```
 
@@ -308,7 +311,7 @@ pandoc paper.md --citeproc --bibliography=references.bib \
 ## References
 
 - CrossRef API: https://api.crossref.org
-- Semantic Scholar API: https://api.semanticscholar.org
+- OpenAlex API: https://api.openalex.org
 - APA 7th Edition Manual: https://apastyle.apa.org/products/publication-manual-7th-edition
 - BibTeX documentation: http://www.bibtex.org
 - CSL styles repository: https://github.com/citation-style-language/styles

package/skills/writing/citation/citation-assistant-skill/SKILL.md

@@ -1,12 +1,12 @@
 ---
 name: citation-assistant-skill
-description: "Claude Code skill for citation workflow via Semantic Scholar"
+description: "Claude Code skill for citation workflow via OpenAlex and CrossRef"
 metadata:
   openclaw:
     emoji: "📎"
     category: "writing"
     subcategory: "citation"
-    keywords: ["citation assistant", "Semantic Scholar", "Claude Code skill", "reference lookup", "academic citation"]
+    keywords: ["citation assistant", "OpenAlex", "Claude Code skill", "reference lookup", "academic citation"]
     source: "https://github.com/ZhangNy301/citation-assistant"
 ---
 
@@ -14,7 +14,7 @@ metadata:
 
 ## Overview
 
-Citation Assistant is a Claude Code skill that integrates Semantic Scholar API into the coding workflow for instant paper lookup, citation formatting, and reference management. Search for papers by title or keyword, get formatted BibTeX entries, find related works, and insert citations — all without leaving the terminal. Designed for researchers writing papers in LaTeX or Markdown.
+Citation Assistant is a Claude Code skill that integrates OpenAlex and CrossRef APIs into the coding workflow for instant paper lookup, citation formatting, and reference management. Search for papers by title or keyword, get formatted BibTeX entries, find related works, and insert citations — all without leaving the terminal. Designed for researchers writing papers in LaTeX or Markdown.
 
 ## Installation
 
@@ -32,106 +32,118 @@ openclaw skills install citation-assistant
 ```python
 import requests
 
-S2_API = "https://api.semanticscholar.org/graph/v1"
+OA_API = "https://api.openalex.org"
 
 def search_papers(query, limit=5):
-    """Search Semantic Scholar for papers."""
+    """Search OpenAlex for papers."""
     resp = requests.get(
-        f"{S2_API}/paper/search",
+        f"{OA_API}/works",
         params={
-            "query": query,
-            "limit": limit,
-            "fields": "title,authors,year,citationCount,"
-                      "externalIds,abstract,venue",
+            "search": query,
+            "per_page": limit,
         },
+        headers={"User-Agent": "ResearchPlugins/1.0 (https://wentor.ai)"},
     )
-    return resp.json().get("data", [])
+    return resp.json().get("results", [])
 
 papers = search_papers("attention mechanism transformer")
 for p in papers:
-    authors = ", ".join(a["name"] for a in p["authors"][:3])
-    print(f"[{p['year']}] {p['title']}")
-    print(f"  {authors} — Citations: {p['citationCount']}")
-    print(f"  DOI: {p.get('externalIds', {}).get('DOI', 'N/A')}")
+    authors = [a["author"]["display_name"] for a in p.get("authorships", [])[:3]]
+    print(f"[{p.get('publication_year')}] {p.get('title')}")
+    print(f"  {', '.join(authors)} — Citations: {p.get('cited_by_count')}")
+    print(f"  DOI: {p.get('doi', 'N/A')}")
 ```
 
 ### BibTeX Generation
 
 ```python
-def get_bibtex(paper_id):
-    """Get BibTeX for a Semantic Scholar paper."""
+def get_bibtex(doi):
+    """Get BibTeX for a paper via CrossRef DOI resolution."""
     resp = requests.get(
-        f"{S2_API}/paper/{paper_id}",
-        params={
-            "fields": "title,authors,year,venue,externalIds,"
-                      "journal,publicationTypes",
-        },
+        f"https://api.crossref.org/works/{doi}",
+        headers={"User-Agent": "ResearchPlugins/1.0 (https://wentor.ai; mailto:dev@wentor.ai)"},
     )
-    paper = resp.json()
+    msg = resp.json().get("message", {})
 
     # Generate citation key
-    first_author = paper["authors"][0]["name"].split()[-1].lower()
-    key = f"{first_author}{paper['year']}"
+    authors = msg.get("author", [])
+    first_author = authors[0].get("family", "unknown").lower() if authors else "unknown"
+    year = str(msg.get("published", {}).get("date-parts", [[""]])[0][0])
+    key = f"{first_author}{year}"
 
     # Build BibTeX
-    authors_str = " and ".join(a["name"] for a in paper["authors"])
-    doi = paper.get("externalIds", {}).get("DOI", "")
+    authors_str = " and ".join(f"{a.get('given', '')} {a.get('family', '')}".strip() for a in authors)
+    doi_str = msg.get("DOI", "")
+
+    title = msg.get("title", [""])[0] if isinstance(msg.get("title"), list) else msg.get("title", "")
+    journal = msg.get("container-title", [""])[0] if msg.get("container-title") else ""
 
     bibtex = f"""@article{{{key},
-  title = {{{paper['title']}}},
+  title = {{{title}}},
   author = {{{authors_str}}},
-  year = {{{paper['year']}}},
-  journal = {{{paper.get('venue', '')}}},
-  doi = {{{doi}}},
+  year = {{{year}}},
+  journal = {{{journal}}},
+  doi = {{{doi_str}}},
 }}"""
     return bibtex
 
 # Example
-bibtex = get_bibtex("204e3073870fae3d05bcbc2f6a8e263d9b72e776")
+bibtex = get_bibtex("10.18653/v1/N19-1423")
 print(bibtex)
 ```
 
 ### Citation Context
 
 ```python
-def get_citation_context(paper_id, limit=10):
-    """Get papers that cite this work with context."""
+def get_citing_works(openalex_id, limit=10):
+    """Get papers that cite this work via OpenAlex."""
     resp = requests.get(
-        f"{S2_API}/paper/{paper_id}/citations",
+        f"{OA_API}/works",
         params={
-            "fields": "title,year,contexts,intents",
-            "limit": limit,
+            "filter": f"cites:{openalex_id}",
+            "per_page": limit,
+            "sort": "cited_by_count:desc",
         },
+        headers={"User-Agent": "ResearchPlugins/1.0 (https://wentor.ai)"},
     )
-    citations = resp.json().get("data", [])
+    results = resp.json().get("results", [])
 
-    for cit in citations:
-        paper = cit["citingPaper"]
-        print(f"\n{paper['title']} ({paper.get('year', '?')})")
-        for ctx in cit.get("contexts", [])[:2]:
-            print(f"  Context: ...{ctx[:100]}...")
-        print(f"  Intent: {cit.get('intents', ['unknown'])}")
+    for paper in results:
+        authors = [a["author"]["display_name"] for a in paper.get("authorships", [])[:3]]
+        print(f"\n{paper.get('title')} ({paper.get('publication_year', '?')})")
+        print(f"  Authors: {', '.join(authors)}")
+        print(f"  Citations: {paper.get('cited_by_count', 0)}")
 
-get_citation_context("204e3073870fae3d05bcbc2f6a8e263d9b72e776")
+get_citing_works("W2741809807")
 ```
 
 ### Related Paper Discovery
 
 ```python
-def find_related(paper_id, limit=10):
-    """Find papers related to a given paper."""
+def find_related(openalex_id, limit=10):
+    """Find papers related to a given paper via OpenAlex."""
+    # Get the paper's concepts, then search for similar works
     resp = requests.get(
-        f"{S2_API}/paper/{paper_id}/recommendations",
+        f"{OA_API}/works/{openalex_id}",
+        headers={"User-Agent": "ResearchPlugins/1.0 (https://wentor.ai)"},
+    )
+    paper = resp.json()
+    concepts = [c["display_name"] for c in paper.get("concepts", [])[:3]]
+
+    related_resp = requests.get(
+        f"{OA_API}/works",
         params={
-            "fields": "title,authors,year,citationCount",
-            "limit": limit,
+            "search": " ".join(concepts),
+            "per_page": limit,
+            "sort": "cited_by_count:desc",
         },
+        headers={"User-Agent": "ResearchPlugins/1.0 (https://wentor.ai)"},
     )
-    return resp.json().get("recommendedPapers", [])
+    return related_resp.json().get("results", [])
 
-related = find_related("204e3073870fae3d05bcbc2f6a8e263d9b72e776")
+related = find_related("W2741809807")
 for p in related:
-    print(f"[{p['year']}] {p['title']} ({p['citationCount']} cites)")
+    print(f"[{p.get('publication_year')}] {p.get('title')} ({p.get('cited_by_count')} cites)")
 ```
 
 ## Workflow Integration
@@ -161,10 +173,11 @@ def build_bibliography(queries, output_file="refs.bib"):
     for query in queries:
         papers = search_papers(query, limit=3)
         for paper in papers:
-            pid = paper.get("paperId")
-            if pid and pid not in seen_ids:
-                seen_ids.add(pid)
-                bibtex = get_bibtex(pid)
+            doi = paper.get("doi")
+            if doi and doi not in seen_ids:
+                seen_ids.add(doi)
+                bibtex = get_bibtex(doi.replace("https://doi.org/", ""))
+
                 all_bibtex.append(bibtex)
 
     with open(output_file, "w") as f:
@@ -189,4 +202,5 @@ build_bibliography([
 ## References
 
 - [Citation Assistant GitHub](https://github.com/ZhangNy301/citation-assistant)
-- [Semantic Scholar API](https://api.semanticscholar.org/)
+- [OpenAlex API](https://api.openalex.org/)
+- [CrossRef API](https://api.crossref.org/)

package/skills/writing/citation/obsidian-citation-guide/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "writing"
     subcategory: "citation"
+    emoji: "📚"
     keywords:
       - obsidian
       - citations

package/skills/writing/citation/obsidian-zotero-guide/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "writing"
     subcategory: "citation"
+    emoji: "🔗"
     keywords:
       - obsidian
       - zotero

package/skills/writing/citation/onecite-reference-guide/SKILL.md

@@ -14,7 +14,7 @@ metadata:
 
 ## Overview
 
-OneCite is an AI-powered toolkit for parsing, completing, and formatting academic references. Given incomplete or messy citation strings, it extracts structured metadata, fills in missing fields via API lookups (CrossRef, Semantic Scholar), and outputs clean formatted references in any style (APA, MLA, BibTeX, Chicago). Available as a Python library and MCP server for agent integration.
+OneCite is an AI-powered toolkit for parsing, completing, and formatting academic references. Given incomplete or messy citation strings, it extracts structured metadata, fills in missing fields via API lookups (CrossRef, OpenAlex), and outputs clean formatted references in any style (APA, MLA, BibTeX, Chicago). Available as a Python library and MCP server for agent integration.
 
 ## Installation
 

package/skills/writing/citation/papersgpt-zotero-guide/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "writing"
     subcategory: "citation"
+    emoji: "📑"
     keywords:
       - zotero
       - ai-assistant

package/skills/writing/citation/zotero-mdnotes-guide/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "writing"
     subcategory: "citation"
+    emoji: "📝"
     keywords:
       - zotero
       - markdown

package/skills/writing/citation/zotero-reference-guide/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "writing"
     subcategory: "citation"
+    emoji: "📖"
     keywords:
       - zotero
       - references
@@ -37,7 +38,7 @@ The plugin is particularly powerful for literature reviews, where you need to sy
 - Identifies DOIs, arXiv IDs, and other persistent identifiers within references
 
 **Database Matching**
-- Matches parsed references against Crossref, Semantic Scholar, and other academic databases
+- Matches parsed references against Crossref, OpenAlex, and other academic databases
 - Retrieves complete metadata for matched references (abstract, keywords, citation count)
 - Displays match confidence to help users verify correct identification
 - Supports manual correction when automatic matching fails

package/skills/writing/citation/zotero-scholar-guide/SKILL.md

@@ -16,7 +16,7 @@ metadata:
 
 Zotero is the most widely used open-source reference manager in academia, offering a powerful combination of local storage, cloud sync, browser integration, and a comprehensive API. While most researchers use Zotero through its desktop application and browser connector, the Zotero API enables programmatic access that is essential for automated research workflows—saving papers from scripts, batch-importing search results, organizing libraries algorithmically, and integrating reference management into custom research pipelines.
 
-This skill covers using the Zotero Web API to create, read, update, and organize library items programmatically. It is designed for researchers who want to automate parts of their reference management workflow: importing papers from arXiv or Semantic Scholar searches directly into Zotero, auto-tagging papers based on content analysis, organizing collections programmatically, and exporting citations in various formats.
+This skill covers using the Zotero Web API to create, read, update, and organize library items programmatically. It is designed for researchers who want to automate parts of their reference management workflow: importing papers from arXiv or OpenAlex searches directly into Zotero, auto-tagging papers based on content analysis, organizing collections programmatically, and exporting citations in various formats.
 
 The skill complements the existing `zotero-api` skill by focusing specifically on practical scholar workflows—the common patterns a researcher uses when integrating Zotero into their daily literature management.
 

package/skills/writing/composition/scientific-writing-resources/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "writing"
     subcategory: "composition"
+    emoji: "✍️"
     keywords:
       - scientific-writing
       - writing-tools

package/skills/writing/latex/latex-drawing-collection/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "writing"
     subcategory: "latex"
+    emoji: "🎨"
     keywords:
       - latex-drawing
       - tikz

package/skills/writing/latex/latex-templates-collection/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "writing"
     subcategory: "latex"
+    emoji: "📋"
     keywords:
       - latex-templates
       - paper-templates

package/skills/writing/templates/novathesis-guide/SKILL.md

@@ -8,6 +8,7 @@ metadata:
   openclaw:
     category: "writing"
     subcategory: "templates"
+    emoji: "🎓"
     keywords:
       - thesis-template
       - latex-thesis