@wentorai/research-plugins 1.0.0 → 1.2.0

package/skills/writing/citation/mendeley-api/SKILL.md

@@ -0,0 +1,231 @@
+---
+name: mendeley-api
+description: "Manage references and search Mendeley's catalog via REST API"
+metadata:
+  openclaw:
+    emoji: "📚"
+    category: "writing"
+    subcategory: "citation"
+    keywords: ["mendeley", "reference manager", "bibliography", "catalog search", "research library", "citations"]
+    source: "https://dev.elsevier.com/mendeley.html"
+---
+
+# Mendeley REST API
+
+## Overview
+
+Mendeley provides a reference management platform with a REST API for programmatic access to personal libraries, group collections, and the Mendeley Catalog — a crowdsourced database of 200M+ academic documents. The API supports OAuth 2.0 authentication, CRUD operations on documents/folders/annotations, and catalog search with rich metadata. Free tier available with registration.
+
+## Authentication
+
+Mendeley uses OAuth 2.0 with client credentials or authorization code flow.
+
+```bash
+# 1. Register app at https://dev.elsevier.com/
+# 2. Get access token via client credentials (for catalog search)
+curl -X POST "https://api.mendeley.com/oauth/token" \
+  -d "grant_type=client_credentials" \
+  -d "scope=all" \
+  -d "client_id=$MENDELEY_CLIENT_ID" \
+  -d "client_secret=$MENDELEY_CLIENT_SECRET"
+
+# Response: { "access_token": "...", "expires_in": 3600, "token_type": "bearer" }
+```
+
+## API Endpoints
+
+### Base URL
+
+```
+https://api.mendeley.com
+```
+
+### Catalog Search
+
+Search across Mendeley's 200M+ document database:
+
+```bash
+# Search by title/keywords
+curl -H "Authorization: Bearer $TOKEN" \
+  "https://api.mendeley.com/catalog?query=deep+learning+NLP&limit=20"
+
+# Search by DOI
+curl -H "Authorization: Bearer $TOKEN" \
+  "https://api.mendeley.com/catalog?doi=10.1038/nature14539"
+
+# Search by title
+curl -H "Authorization: Bearer $TOKEN" \
+  "https://api.mendeley.com/catalog?title=attention+is+all+you+need"
+```
+
+### User Library
+
+```bash
+# List documents in personal library
+curl -H "Authorization: Bearer $TOKEN" \
+  "https://api.mendeley.com/documents?limit=50&sort=created&order=desc"
+
+# Get document details
+curl -H "Authorization: Bearer $TOKEN" \
+  "https://api.mendeley.com/documents/{doc_id}"
+
+# Add document to library
+curl -X POST -H "Authorization: Bearer $TOKEN" \
+  -H "Content-Type: application/vnd.mendeley-document.1+json" \
+  -d '{"title":"My Paper","type":"journal","year":2025,"authors":[{"first_name":"A","last_name":"B"}]}' \
+  "https://api.mendeley.com/documents"
+```
+
+### Folders and Groups
+
+```bash
+# List folders
+curl -H "Authorization: Bearer $TOKEN" \
+  "https://api.mendeley.com/folders"
+
+# List group documents
+curl -H "Authorization: Bearer $TOKEN" \
+  "https://api.mendeley.com/documents?group_id={group_id}"
+```
+
+### Annotations
+
+```bash
+# Get annotations for a document
+curl -H "Authorization: Bearer $TOKEN" \
+  "https://api.mendeley.com/annotations?document_id={doc_id}"
+```
+
+## Query Parameters
+
+| Parameter | Description | Example |
+|-----------|-------------|---------|
+| `query` | Free-text search | `query=transformer+model` |
+| `doi` | DOI lookup | `doi=10.1234/example` |
+| `title` | Title search | `title=BERT` |
+| `author` | Author filter | `author=LeCun` |
+| `min_year` | From year | `min_year=2020` |
+| `max_year` | To year | `max_year=2026` |
+| `limit` | Results per page (max 500) | `limit=50` |
+| `sort` | Sort field | `created`, `title`, `year` |
+| `order` | Sort direction | `asc` or `desc` |
+| `view` | Response detail | `bib` (bibliographic), `stats` (reader counts) |
+
+## Catalog Response
+
+```json
+{
+  "id": "abc123-...",
+  "title": "Attention Is All You Need",
+  "type": "conference_proceedings",
+  "year": 2017,
+  "authors": [
+    {"first_name": "Ashish", "last_name": "Vaswani"}
+  ],
+  "source": "NeurIPS",
+  "identifiers": {
+    "doi": "10.5555/3295222.3295349",
+    "arxiv": "1706.03762"
+  },
+  "keywords": ["attention mechanism", "transformer"],
+  "abstract": "The dominant sequence transduction models...",
+  "reader_count": 15432,
+  "link": "https://www.mendeley.com/catalogue/..."
+}
+```
+
+## Python Usage
+
+```python
+import os
+import requests
+
+CLIENT_ID = os.environ["MENDELEY_CLIENT_ID"]
+CLIENT_SECRET = os.environ["MENDELEY_CLIENT_SECRET"]
+TOKEN_URL = "https://api.mendeley.com/oauth/token"
+BASE_URL = "https://api.mendeley.com"
+
+
+def get_token() -> str:
+    """Obtain access token via client credentials."""
+    resp = requests.post(TOKEN_URL, data={
+        "grant_type": "client_credentials",
+        "scope": "all",
+        "client_id": CLIENT_ID,
+        "client_secret": CLIENT_SECRET,
+    })
+    resp.raise_for_status()
+    return resp.json()["access_token"]
+
+
+def search_catalog(query: str, limit: int = 20,
+                   min_year: int = None) -> list:
+    """Search the Mendeley catalog."""
+    token = get_token()
+    params = {"query": query, "limit": limit, "view": "bib"}
+    if min_year:
+        params["min_year"] = min_year
+
+    resp = requests.get(
+        f"{BASE_URL}/catalog",
+        headers={"Authorization": f"Bearer {token}"},
+        params=params,
+    )
+    resp.raise_for_status()
+
+    results = []
+    for doc in resp.json():
+        results.append({
+            "title": doc.get("title"),
+            "authors": [f"{a['first_name']} {a['last_name']}"
+                        for a in doc.get("authors", [])],
+            "year": doc.get("year"),
+            "source": doc.get("source"),
+            "doi": doc.get("identifiers", {}).get("doi"),
+            "readers": doc.get("reader_count", 0),
+        })
+    return results
+
+
+def lookup_by_doi(doi: str) -> dict:
+    """Look up a single document by DOI."""
+    token = get_token()
+    resp = requests.get(
+        f"{BASE_URL}/catalog",
+        headers={"Authorization": f"Bearer {token}"},
+        params={"doi": doi, "view": "bib"},
+    )
+    resp.raise_for_status()
+    items = resp.json()
+    return items[0] if items else {}
+
+
+# Example
+papers = search_catalog("federated learning privacy", min_year=2023)
+for p in papers:
+    print(f"[{p['year']}] {p['title']} — readers: {p['readers']}")
+```
+
+## Reader Statistics
+
+Mendeley tracks how many users have saved each paper, providing a real-time measure of scholarly interest (unlike citation counts which lag by months).
+
+```python
+def get_popular_papers(topic: str, limit: int = 10) -> list:
+    """Find most-read papers on a topic via reader counts."""
+    results = search_catalog(topic, limit=limit)
+    return sorted(results, key=lambda x: x["readers"], reverse=True)
+```
+
+## Rate Limits
+
+| Tier | Requests/hour | Catalog access |
+|------|--------------|----------------|
+| Free | 150 | Read-only catalog + personal library |
+| Institutional | Higher | Full API access |
+
+## References
+
+- [Mendeley API Documentation](https://dev.elsevier.com/mendeley.html)
+- [Mendeley Developer Portal](https://dev.elsevier.com/)
+- [Mendeley API Reference](https://api.mendeley.com/apidocs/)

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

@@ -0,0 +1,164 @@
+---
+name: obsidian-citation-guide
+description: "Citation plugin for Obsidian note-taking with BibTeX support"
+version: 1.0.0
+author: wentor-community
+source: https://github.com/hans/obsidian-citation-plugin
+metadata:
+  openclaw:
+    category: "writing"
+    subcategory: "citation"
+    keywords:
+      - obsidian
+      - citations
+      - bibtex
+      - literature-notes
+      - reference-linking
+      - knowledge-management
+---
+
+# Obsidian Citation Guide
+
+A skill for using the Obsidian Citation Plugin to integrate bibliographic references from BibTeX or CSL-JSON files into the Obsidian knowledge management workflow. Based on obsidian-citation-plugin (1K stars), this skill enables researchers to create literature notes, insert citations, and build interconnected knowledge bases grounded in their reference libraries.
+
+## Overview
+
+Academic researchers need their notes to be deeply connected to their references. The Obsidian Citation Plugin bridges BibTeX or CSL-JSON bibliography files with Obsidian's note-taking system, enabling seamless creation of literature notes from reference entries, quick citation insertion while writing, and automatic backlinking between notes and their source references.
+
+Unlike Zotero-specific integrations, this plugin works with any tool that exports standard BibTeX or CSL-JSON, making it compatible with Zotero, JabRef, Mendeley, EndNote, and even hand-crafted .bib files.
+
+## Setup and Configuration
+
+**Prerequisites**
+- Obsidian with community plugins enabled
+- A BibTeX (.bib) or CSL-JSON (.json) bibliography file
+- The bibliography file should be accessible from the Obsidian vault directory
+
+**Installation**
+- Open Obsidian Settings and navigate to Community Plugins
+- Search for "Citations" in the plugin browser
+- Install the Citations plugin and enable it
+- Navigate to the plugin settings to configure your bibliography source
+
+**Configuration**
+- Set the path to your .bib or .json bibliography file
+- Configure the literature note folder (e.g., `references/` or `literature/`)
+- Set the literature note template with desired frontmatter fields
+- Define the citation format for in-text insertions
+- Configure the citation key format used for note file names
+
+**Template Variables**
+- `{{citekey}}` - the unique citation key for the reference
+- `{{title}}` - the full title of the work
+- `{{authorString}}` - formatted author list
+- `{{year}}` - publication year
+- `{{abstract}}` - the abstract if available in the bibliography
+- `{{DOI}}` - Digital Object Identifier
+- `{{URL}}` - web link to the publication
+- `{{containerTitle}}` - journal or conference name
+- `{{page}}` - page numbers
+- `{{tags}}` - keywords or tags from the bibliography entry
+
+## Core Workflows
+
+**Creating Literature Notes**
+- Use the command palette to open the citation picker
+- Search by author, title, year, or any metadata field
+- Select a reference to create a new literature note from the template
+- The note is populated with metadata from the bibliography entry
+- Add your own annotations, summaries, and connections to the note
+
+**Inserting Citations**
+- While writing in any Obsidian note, trigger the citation insertion command
+- Search and select the desired reference
+- The citation is inserted in the configured format (e.g., `[@citekey]`, `[[@citekey]]`)
+- Citations create automatic backlinks to the corresponding literature notes
+- Multiple citation formats can be configured for different output targets
+
+**Browsing References**
+- Open the citation panel to browse your entire bibliography
+- Filter by type (article, book, chapter, conference), year, or author
+- Preview reference details without creating a note
+- Quickly jump to existing literature notes for any reference
+- Identify references that do not yet have corresponding notes
+
+## Literature Note Strategies
+
+**Minimal Notes (Quick Reference)**
+- Include only the frontmatter metadata (citekey, title, authors, year)
+- Add a single-paragraph summary of the paper's contribution
+- Tag with 2-3 topic tags for filtering
+- Useful for references that provide supporting context but are not central to your work
+
+**Standard Notes (Working Knowledge)**
+- Include full metadata frontmatter
+- Add sections for: summary, key findings, methodology, strengths, limitations
+- Extract 3-5 key quotes with page references
+- Link to related literature notes and concept notes
+- Tag with topic, method, and status tags
+
+**Deep Notes (Core References)**
+- Include everything from standard notes plus:
+- Detailed methodology breakdown with your assessment
+- Figure and table descriptions with your interpretation
+- Questions and ideas prompted by the paper
+- Connections to your own research with specific implications
+- Reading timeline notes tracking your evolving understanding
+
+## Building a Connected Knowledge Base
+
+**Linking Strategies**
+- Link literature notes to concept notes that represent key ideas
+- Create MOC (Map of Content) notes that curate references by theme
+- Use tags consistently to enable cross-cutting queries
+- Link literature notes to project notes where the reference is cited
+- Create methodology notes that reference the papers using each method
+
+**Dataview Integration**
+- Use the Dataview plugin to create dynamic literature dashboards
+- Query literature notes by tag, date, status, or any frontmatter field
+- Generate reading lists filtered by topic and reading status
+- Create citation frequency tables showing your most-used references
+- Build project-specific reference lists from linked literature notes
+
+**Graph View Usage**
+- The Obsidian graph view shows the link structure between all notes
+- Clusters of densely linked literature notes indicate research themes
+- Isolated literature notes may need more connections or may be peripheral
+- Hub notes (with many connections) are candidates for synthesis writing
+- Use the graph to discover unexpected connections between research areas
+
+## Multi-Tool Workflows
+
+**Zotero to Obsidian Pipeline**
+- Export from Zotero via Better BibTeX to keep the .bib file continuously updated
+- The citation plugin detects changes to the .bib file automatically
+- Create literature notes in Obsidian for papers annotated in Zotero
+- Use Zotero for PDF management and Obsidian for knowledge synthesis
+- This separation leverages the strengths of each tool
+
+**Writing Pipeline**
+- Draft manuscripts in Obsidian using Pandoc-compatible citation syntax
+- Use Pandoc to compile Markdown to LaTeX, DOCX, or HTML with formatted citations
+- The citation keys in your notes map directly to your bibliography file
+- Generate bibliographies automatically from cited references
+- This pipeline supports any citation style via CSL
+
+## Integration with Research-Claw
+
+This skill enhances the Research-Claw knowledge management workflow:
+
+- Create literature notes programmatically from search results
+- Build connected knowledge bases that inform writing and analysis tasks
+- Enable citation insertion during AI-assisted manuscript drafting
+- Connect with other Obsidian and Zotero skills for comprehensive workflows
+- Support systematic review note-taking with structured templates
+
+## Best Practices
+
+- Keep your bibliography file in the Obsidian vault for reliable path resolution
+- Use a consistent citation key format across all tools in your workflow
+- Create literature notes soon after reading to capture fresh insights
+- Review and update literature notes periodically as your understanding deepens
+- Use templates to ensure consistent structure across all literature notes
+- Back up both the bibliography file and the vault regularly

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

@@ -0,0 +1,137 @@
+---
+name: obsidian-zotero-guide
+description: "Insert citations and notes from Zotero into Obsidian knowledge bases"
+version: 1.0.0
+author: wentor-community
+source: https://github.com/mgmeyers/obsidian-zotero-integration
+metadata:
+  openclaw:
+    category: "writing"
+    subcategory: "citation"
+    keywords:
+      - obsidian
+      - zotero
+      - citation-management
+      - note-taking
+      - knowledge-base
+      - bibliography
+---
+
+# Obsidian-Zotero Guide
+
+A skill for integrating Zotero reference management with Obsidian note-taking to create a seamless academic knowledge management workflow. Based on the obsidian-zotero-integration plugin (2K stars), this skill guides the agent through setting up, configuring, and optimizing the bridge between your reference library and your personal knowledge base.
+
+## Overview
+
+Academic researchers accumulate hundreds or thousands of papers over a career, each containing insights that need to be connected, synthesized, and retrieved when writing new work. Zotero excels at organizing references and PDFs, while Obsidian excels at creating interlinked notes and building knowledge graphs. This integration bridges the two, allowing annotations made in Zotero to flow into Obsidian as linked notes, and enabling citation insertion directly from the Obsidian editor.
+
+The result is a unified research workflow where reading, annotating, note-taking, and writing happen in a connected ecosystem rather than in isolated tools.
+
+## Setup and Configuration
+
+**Prerequisites**
+- Zotero 6 or 7 with the Better BibTeX plugin installed
+- Obsidian with community plugins enabled
+- A designated vault folder for literature notes (e.g., `references/` or `literature/`)
+
+**Installation Steps**
+- Install the Zotero Integration plugin from the Obsidian community plugins browser
+- Configure the Zotero data directory path in the plugin settings
+- Set up the Better BibTeX citation key format (recommended: `authYear` or `authYearTitle`)
+- Define the literature note template (see Template Configuration below)
+- Test the connection by inserting a citation from a known Zotero entry
+
+**Template Configuration**
+- Create a template file that defines the structure of imported literature notes
+- Include frontmatter fields: citekey, authors, year, journal, DOI, tags
+- Include body sections: abstract, key findings, methodology notes, personal comments
+- Use Nunjucks template syntax for dynamic field insertion
+- Configure annotation extraction to pull highlights and comments from PDFs
+
+## Citation Workflow
+
+The primary citation workflow during writing:
+
+**Inserting Citations**
+- Use the command palette or hotkey to open the Zotero citation picker
+- Search by author, title, year, or tag to find the desired reference
+- Insert the citation in the desired format (pandoc, LaTeX, plain text)
+- The plugin creates a backlink to the corresponding literature note
+- Multiple citation formats can be configured for different output targets
+
+**Managing Literature Notes**
+- Each imported Zotero entry generates a literature note in Obsidian
+- Notes are named by citation key for consistent linking
+- Tags from Zotero are imported as Obsidian tags for cross-referencing
+- PDF annotations (highlights, comments) are extracted into structured sections
+- Notes are automatically updated when Zotero metadata changes
+
+**Building Connections**
+- Link literature notes to topic notes, project notes, and concept notes
+- Use Obsidian's graph view to visualize connections between references
+- Create MOC (Map of Content) notes that curate papers by theme
+- Track reading status with custom frontmatter fields (unread, reading, read, reviewed)
+- Use dataview queries to generate dynamic reading lists and bibliographies
+
+## Annotation Extraction
+
+One of the most powerful features is extracting PDF annotations:
+
+**Highlight Extraction**
+- Color-coded highlights can be mapped to different note sections
+- Yellow highlights for key findings, blue for methodology, green for quotes
+- Each highlight includes the page number and surrounding context
+- Highlights are formatted as blockquotes with source attribution
+- Batch extraction processes all annotations from a paper at once
+
+**Comment Extraction**
+- Marginal comments from Zotero's PDF reader are imported alongside highlights
+- Comments are distinguished from highlights with different formatting
+- Time-stamped comments preserve the reading chronology
+- Comments can be tagged for follow-up actions (verify, discuss, replicate)
+
+**Image Extraction**
+- Area annotations (image selections) from PDFs can be extracted
+- Extracted images are saved to a designated assets folder
+- Image annotations include captions from the Zotero comment field
+- Useful for capturing key figures, tables, and equations from papers
+
+## Advanced Workflows
+
+**Systematic Review Support**
+- Import entire Zotero collections as literature note sets
+- Use Obsidian dataview to create screening matrices
+- Track inclusion/exclusion decisions with frontmatter fields
+- Generate evidence tables from structured literature notes
+- Export curated collections back to Zotero for bibliography generation
+
+**Collaborative Research**
+- Share Obsidian vaults via Git for team-based literature reviews
+- Merge literature notes from multiple team members
+- Use consistent templates to ensure compatible note structures
+- Track who added which annotations and comments
+
+**Writing Integration**
+- Use pandoc with citeproc to render citations in final documents
+- Export bibliography in any CSL-supported format
+- Generate reference lists directly from cited literature notes
+- Support for footnote, author-date, and numeric citation styles
+
+## Integration with Research-Claw
+
+This skill enhances the Research-Claw reference management capabilities:
+
+- Automate literature note creation from newly added Zotero entries
+- Generate synthesis notes combining insights from multiple papers
+- Suggest connections between newly imported papers and existing notes
+- Help maintain consistent tagging and categorization across the library
+- Assist with writing literature review sections from interlinked notes
+
+## Best Practices
+
+- Establish a consistent citation key format before importing any references
+- Create templates before importing to avoid reformatting existing notes
+- Use a dedicated folder for literature notes separate from personal notes
+- Regularly sync Zotero and re-extract annotations after additional reading
+- Back up the Obsidian vault before bulk import operations
+- Keep literature note templates versioned to track structural changes over time

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

@@ -0,0 +1,168 @@
+---
+name: onecite-reference-guide
+description: "AI toolkit to parse, complete, and format academic references"
+metadata:
+  openclaw:
+    emoji: "📌"
+    category: "writing"
+    subcategory: "citation"
+    keywords: ["OneCite", "reference formatting", "citation parser", "BibTeX", "metadata completion", "MCP"]
+    source: "https://github.com/HzaCode/OneCite"
+---
+
+# OneCite Reference Guide
+
+## 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.
+
+## Installation
+
+```bash
+# Python package
+pip install onecite
+
+# MCP server
+npx @onecite/mcp-server
+```
+
+## Reference Parsing
+
+```python
+from onecite import parse_reference
+
+# Parse messy reference string
+ref = parse_reference(
+    "Vaswani et al. Attention Is All You Need. "
+    "NeurIPS 2017. arXiv:1706.03762"
+)
+
+print(ref.title)      # "Attention Is All You Need"
+print(ref.authors)    # ["Vaswani, A.", "Shazeer, N.", ...]
+print(ref.year)       # 2017
+print(ref.venue)      # "NeurIPS"
+print(ref.arxiv_id)   # "1706.03762"
+print(ref.doi)        # "10.48550/arXiv.1706.03762"
+```
+
+## Metadata Completion
+
+```python
+from onecite import complete_reference
+
+# Fill in missing metadata from APIs
+ref = complete_reference(
+    title="Attention Is All You Need",
+    # Automatically looks up: DOI, authors, venue,
+    # abstract, citation count, pages, volume
+)
+
+print(f"DOI: {ref.doi}")
+print(f"Authors: {', '.join(ref.authors)}")
+print(f"Pages: {ref.pages}")
+print(f"Volume: {ref.volume}")
+print(f"Citations: {ref.citation_count}")
+```
+
+## Format Conversion
+
+```python
+from onecite import format_reference, parse_reference
+
+ref = parse_reference(
+    "B. Kerbl et al., '3D Gaussian Splatting for Real-Time "
+    "Radiance Field Rendering,' SIGGRAPH 2023"
+)
+
+# Output in different styles
+print(format_reference(ref, style="apa"))
+# Kerbl, B., Kopanas, G., Leimkühler, T., & Drettakis, G.
+# (2023). 3D Gaussian Splatting for Real-Time Radiance Field
+# Rendering. ACM SIGGRAPH 2023.
+
+print(format_reference(ref, style="bibtex"))
+# @inproceedings{kerbl2023,
+#   title = {3D Gaussian Splatting...},
+#   author = {Kerbl, Bernhard and ...},
+#   booktitle = {ACM SIGGRAPH 2023},
+#   year = {2023}
+# }
+
+print(format_reference(ref, style="mla"))
+print(format_reference(ref, style="chicago"))
+print(format_reference(ref, style="ieee"))
+```
+
+## Batch Processing
+
+```python
+from onecite import process_references
+
+# Process a list of raw reference strings
+raw_refs = [
+    "Vaswani et al. Attention Is All You Need. NeurIPS 2017",
+    "Devlin et al. BERT. NAACL 2019",
+    "Brown et al. Language Models are Few-Shot Learners. 2020",
+]
+
+results = process_references(
+    raw_refs,
+    complete=True,     # Fill missing metadata
+    format="bibtex",   # Output format
+    deduplicate=True,  # Remove duplicates
+)
+
+# Save as .bib file
+with open("references.bib", "w") as f:
+    for ref in results:
+        f.write(ref.formatted + "\n\n")
+```
+
+## MCP Server Usage
+
+```json
+{
+  "mcpServers": {
+    "onecite": {
+      "command": "npx",
+      "args": ["@onecite/mcp-server"],
+      "tools": [
+        "parse_reference",
+        "complete_reference",
+        "format_reference",
+        "search_paper",
+        "get_bibtex"
+      ]
+    }
+  }
+}
+```
+
+## Reference Validation
+
+```python
+from onecite import validate_references
+
+# Check a .bib file for issues
+issues = validate_references("references.bib")
+
+for issue in issues:
+    print(f"[{issue.severity}] {issue.entry}: {issue.message}")
+    # [WARNING] smith2023: Missing DOI
+    # [ERROR] jones2024: Author field empty
+    # [INFO] chen2022: Title case inconsistency
+```
+
+## Use Cases
+
+1. **Reference cleanup**: Fix messy bibliographies
+2. **Format conversion**: Convert between citation styles
+3. **Metadata completion**: Fill in missing DOIs, pages, venues
+4. **Agent integration**: MCP server for AI citation workflows
+5. **Validation**: Check references for completeness and errors
+
+## References
+
+- [OneCite GitHub](https://github.com/HzaCode/OneCite)
+- [CrossRef API](https://api.crossref.org/)
+- [Citation Style Language](https://citationstyles.org/)