@wentorai/research-plugins 1.0.0 → 1.2.0

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

@@ -0,0 +1,111 @@
+---
+name: zotero-gpt-guide
+description: "Guide to Zotero GPT for AI-powered research assistance within Zotero"
+metadata:
+  openclaw:
+    emoji: "🤖"
+    category: "writing"
+    subcategory: "citation"
+    keywords: ["zotero", "gpt", "ai-assistant", "research-ai", "paper-analysis"]
+    source: "https://github.com/MuiseDestiny/zotero-gpt"
+---
+
+# Zotero GPT Guide
+
+## Overview
+
+Zotero GPT brings large language model capabilities directly into the Zotero reference manager, allowing researchers to interact with their library and papers through natural language. With over 7,000 GitHub stars, it has become one of the most sought-after Zotero plugins as researchers increasingly look for ways to integrate AI into their academic workflows.
+
+The plugin connects Zotero to various LLM providers including OpenAI, Azure OpenAI, and compatible API endpoints. Researchers can ask questions about papers, generate summaries, extract key findings, compare methodologies across studies, and perform many other analytical tasks without leaving Zotero. The AI has access to the context of your current paper, selected text, annotations, and library metadata.
+
+What makes Zotero GPT particularly powerful for academic work is its tight integration with the Zotero ecosystem. Unlike standalone AI tools where you must copy and paste text, Zotero GPT understands the structure of your library and can reference specific papers, annotations, and collections. This contextual awareness makes it far more effective for research tasks than generic chatbot interfaces.
+
+## Installation and Setup
+
+Install Zotero GPT through the Zotero add-on system:
+
+1. Download the latest `.xpi` file from https://github.com/MuiseDestiny/zotero-gpt/releases
+2. In Zotero, navigate to Tools > Add-ons > gear icon > Install Add-on From File
+3. Select the `.xpi` file and restart Zotero
+
+Configure your LLM provider:
+
+- Open Zotero Preferences > Zotero GPT
+- Select your API provider (OpenAI, Azure, or custom endpoint)
+- Set your API key through environment variables for security:
+  - For OpenAI: configure `$OPENAI_API_KEY` in your system environment
+  - For Azure: configure `$AZURE_OPENAI_KEY` and `$AZURE_OPENAI_ENDPOINT`
+  - For custom endpoints: configure `$ZOTERO_GPT_API_KEY` and the endpoint URL
+- Select your preferred model (GPT-4 recommended for research tasks)
+- Set the maximum token limit for responses
+- Configure temperature (lower values like 0.3 produce more focused, deterministic outputs)
+
+Additional configuration options:
+
+- Set default prompts for common research tasks
+- Configure context window behavior (how much of the paper to include)
+- Enable or disable streaming responses
+- Set up custom prompt templates for your specific research needs
+
+## Core Features
+
+**Paper Summarization**: Select a paper in your library and ask Zotero GPT to generate a structured summary. The AI reads the available metadata, abstract, and any annotations you have made to produce a concise overview of the paper's contributions, methods, and findings.
+
+**Question Answering**: While reading a PDF in Zotero's reader, highlight a passage and ask questions about it. The AI provides explanations, contextual information, and connections to broader concepts. This is particularly useful for understanding dense technical content outside your primary expertise.
+
+**Annotation Analysis**: Zotero GPT can analyze your annotations across a paper or collection, identifying themes, contradictions, and patterns in your reading notes. This helps synthesize information from multiple sources into coherent research narratives.
+
+**Methodology Comparison**: When reviewing papers for a literature review, ask the AI to compare methodologies, sample sizes, statistical approaches, and experimental designs across selected papers. This structured comparison accelerates the review process significantly.
+
+**Writing Assistance**: Generate draft text based on your notes and annotations. The AI can help structure arguments, suggest transitions between ideas, and identify gaps in your reasoning that need additional evidence.
+
+**Custom Prompts and Commands**: Define reusable prompt templates for tasks you perform regularly:
+
+```
+Command: /critique
+Prompt: Analyze the methodology of this paper. Identify strengths,
+weaknesses, potential biases, and threats to validity. Structure your
+response with clear headings for each category.
+```
+
+```
+Command: /extract-findings
+Prompt: Extract and list the key findings from this paper. For each
+finding, note the evidence strength, sample characteristics, and
+any caveats mentioned by the authors.
+```
+
+## Research Workflow Integration
+
+**Literature Screening**: When processing a large batch of papers from a database search, use Zotero GPT to quickly generate summaries and relevance assessments. Create a custom prompt that evaluates each paper against your specific inclusion criteria, dramatically speeding up the screening phase of systematic reviews.
+
+**Deep Reading Assistance**: During close reading of important papers, use the AI as a discussion partner. Ask it to explain unfamiliar methods, clarify statistical procedures, or provide background on referenced theories. This is especially valuable when reading interdisciplinary papers that span multiple fields.
+
+**Synthesis and Gap Analysis**: After annotating a collection of papers, ask Zotero GPT to identify recurring themes, methodological trends, and research gaps across your annotations. Use the output as a starting point for the synthesis section of your literature review.
+
+**Draft Generation**: When moving from reading to writing, use writing assistance features to generate initial draft paragraphs based on your collected annotations and notes. The AI maintains awareness of your sources, making it easier to produce properly attributed text.
+
+**Recommended Workflow Practices**:
+- Always verify AI-generated summaries against the original text
+- Use low temperature settings for factual extraction tasks
+- Use higher temperature for brainstorming and idea generation
+- Keep custom prompts in a shared document for lab-wide consistency
+- Review AI outputs critically, especially for numerical claims and citations
+- Combine Zotero GPT with Better Notes for a comprehensive knowledge pipeline
+
+## Privacy and Ethical Considerations
+
+When using Zotero GPT with cloud-based LLM providers, be aware that paper content is sent to external servers for processing. Consider these guidelines:
+
+- Review your institution's policies on sending research data to third-party AI services
+- For sensitive or embargoed research, consider using local LLM endpoints
+- Do not send unpublished manuscripts or confidential data through cloud APIs
+- Be transparent about AI assistance in your research methodology sections
+- Always attribute AI-generated content appropriately in your publications
+
+## References
+
+- GitHub Repository: https://github.com/MuiseDestiny/zotero-gpt
+- Zotero Plugin Directory: https://www.zotero.org/support/plugins
+- OpenAI API Documentation: https://platform.openai.com/docs
+- Responsible AI Use in Research: https://www.nature.com/articles/d41586-023-00056-7

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

@@ -0,0 +1,164 @@
+---
+name: zotero-mcp-guide
+description: "Guide to Zotero MCP for connecting Zotero library with AI assistants"
+metadata:
+  openclaw:
+    emoji: "🔗"
+    category: "writing"
+    subcategory: "citation"
+    keywords: ["zotero", "mcp", "claude", "ai-assistant", "model-context-protocol"]
+    source: "https://github.com/54yyyu/zotero-mcp"
+---
+
+# Zotero MCP Guide
+
+## Overview
+
+Zotero MCP is an emerging tool with over 2,000 GitHub stars that implements the Model Context Protocol (MCP) to connect your Zotero reference library with AI assistants such as Claude. By exposing your Zotero library as a structured data source through MCP, it allows AI models to search, retrieve, and reason about your collected academic papers, annotations, and notes during conversations.
+
+The Model Context Protocol provides a standardized way for AI applications to access external data sources. Zotero MCP leverages this protocol to give AI assistants direct, read-only access to your research library. Instead of manually copying and pasting paper details into a chat, you can ask an AI assistant to look up papers in your Zotero library, summarize your annotations on a specific topic, find related references, or help draft text based on your collected sources.
+
+This integration is particularly valuable for researchers who maintain comprehensive Zotero libraries and want to leverage AI assistance for literature reviews, writing, and knowledge synthesis. The AI can work with the full context of your library rather than being limited to whatever you paste into the conversation, making interactions more productive and contextually grounded.
+
+## Installation and Setup
+
+Zotero MCP requires both a running Zotero instance and an MCP-compatible AI client.
+
+**Prerequisites**:
+- Zotero 6 or 7 installed and running
+- Node.js 18 or later
+- An MCP-compatible AI client (Claude Desktop, or another MCP host)
+
+**Install the MCP Server**:
+
+```bash
+# Clone the repository
+git clone https://github.com/54yyyu/zotero-mcp.git
+cd zotero-mcp
+
+# Install dependencies
+npm install
+
+# Build the server
+npm run build
+```
+
+**Configure Zotero**:
+- Ensure the Zotero local API is enabled (it is by default on port 23119)
+- The MCP server communicates with Zotero through its local HTTP API
+- No API key is needed for local connections; Zotero must simply be running
+
+**Configure Your AI Client**:
+
+For Claude Desktop, add the Zotero MCP server to your configuration file (`claude_desktop_config.json`):
+
+```json
+{
+  "mcpServers": {
+    "zotero": {
+      "command": "node",
+      "args": ["/path/to/zotero-mcp/dist/index.js"]
+    }
+  }
+}
+```
+
+For other MCP hosts, follow their respective documentation for adding MCP servers. The server communicates over stdio using the standard MCP transport protocol.
+
+**Verify the Connection**:
+1. Start Zotero
+2. Launch your AI client with the MCP configuration
+3. Ask the AI to search your Zotero library (e.g., "Find papers about machine learning in my Zotero library")
+4. If the AI returns results from your library, the connection is working
+
+## Core Features
+
+**Library Search**: The MCP server exposes a search tool that allows AI assistants to query your Zotero library using natural language or structured queries. The AI can search by:
+- Title keywords
+- Author names
+- Publication year or date range
+- Tags and collections
+- Full-text content (if Zotero full-text indexing is enabled)
+
+**Item Retrieval**: Retrieve complete metadata for specific items including:
+- Bibliographic information (title, authors, journal, year, DOI, etc.)
+- Abstract and keywords
+- Tags and collection membership
+- Attached file information
+- Related items
+
+**Annotation Access**: The AI can read your PDF annotations and notes for specific items. This means you can ask questions like "What did I highlight in the Smith 2024 paper?" or "Summarize my annotations on papers about transformer architectures" and the AI will access your actual annotations to formulate a response.
+
+**Collection Browsing**: Navigate your Zotero collection hierarchy to understand how you have organized your library. The AI can list collections, show items within specific collections, and understand the taxonomic structure of your research.
+
+**Note Reading**: Access standalone notes and item notes in your Zotero library. This is useful for AI-assisted writing where your accumulated research notes provide the source material for drafting text.
+
+**Citation Formatting**: Request formatted citations for items in your library. The AI can generate citations in various styles (APA, MLA, Chicago, etc.) by accessing the complete bibliographic data through MCP.
+
+## Research Workflow Integration
+
+**AI-Assisted Literature Review**:
+1. Collect papers on your topic in a Zotero collection as you normally would
+2. Read and annotate the papers in Zotero's PDF reader
+3. Start a conversation with your AI assistant
+4. Ask the AI to review your collection and annotations on the topic
+5. The AI accesses your library through MCP and synthesizes your annotations
+6. Iterate with the AI to identify themes, gaps, and connections you may have missed
+
+**Intelligent Writing Support**:
+- Ask the AI to draft a paragraph about a topic, referencing papers from your library
+- The AI retrieves relevant items and annotations to ground the draft in your sources
+- Request properly formatted citations that match your collected references
+- Iterate on the draft with the AI having full context of your source materials
+
+**Research Question Exploration**:
+- Pose a research question to the AI
+- Ask it to search your library for relevant papers
+- The AI identifies which of your collected papers relate to the question
+- Discuss the state of knowledge based on your library, not general training data
+
+**Library Management Assistance**:
+- Ask the AI to identify potential duplicate entries in your library
+- Request suggestions for how to reorganize collections based on content analysis
+- Have the AI suggest tags for untagged items based on their metadata and content
+
+**Example Conversations**:
+
+```
+You: What papers do I have about attention mechanisms in neural networks?
+
+AI: [Searches Zotero via MCP] I found 12 papers in your library related
+to attention mechanisms. The earliest is Bahdanau et al. (2014) and the
+most recent is...
+
+You: Summarize what I highlighted in the Vaswani 2017 paper.
+
+AI: [Retrieves annotations via MCP] In the Vaswani et al. (2017)
+"Attention Is All You Need" paper, you highlighted three key passages...
+```
+
+## Security and Privacy Considerations
+
+Zotero MCP operates locally on your machine. All communication between the MCP server and Zotero happens over localhost, and your library data is not uploaded to any external service. However, when you use the MCP integration with a cloud-based AI assistant, the content retrieved from your library is sent to the AI provider as part of the conversation context.
+
+**Best practices for privacy**:
+- Be aware that paper content, annotations, and notes accessed through MCP will be included in your conversation with the AI provider
+- Avoid using MCP with sensitive or embargoed research content when the AI provider is cloud-based
+- For maximum privacy, use MCP with locally-hosted AI models
+- Review your AI provider's data retention and usage policies
+- The MCP server provides read-only access; it cannot modify your Zotero library
+
+## Troubleshooting
+
+**AI Cannot Find Zotero**: Ensure Zotero is running before starting your AI client. The MCP server connects to Zotero's local API on port 23119. If you have changed the default port, update the MCP server configuration accordingly.
+
+**Search Returns No Results**: Verify that your Zotero library has items and that full-text indexing is enabled for better search coverage. Check that the MCP server is properly connected by reviewing its console output for any error messages.
+
+**Slow Responses**: Large libraries may take longer to search. Consider using more specific queries or searching within particular collections to narrow the scope. Enabling Zotero's search cache can improve response times.
+
+## References
+
+- GitHub Repository: https://github.com/54yyyu/zotero-mcp
+- Model Context Protocol Specification: https://modelcontextprotocol.io
+- Zotero Local API Documentation: https://www.zotero.org/support/dev/web_api/v3/basics
+- Claude Desktop MCP Configuration: https://docs.anthropic.com/en/docs/claude-desktop

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

@@ -0,0 +1,162 @@
+---
+name: zotero-mdnotes-guide
+description: "Export Zotero items and annotations to Markdown note files"
+version: 1.0.0
+author: wentor-community
+source: https://github.com/argenos/zotero-mdnotes
+metadata:
+  openclaw:
+    category: "writing"
+    subcategory: "citation"
+    keywords:
+      - zotero
+      - markdown
+      - note-export
+      - annotations
+      - knowledge-management
+      - literature-notes
+---
+
+# Zotero MDNotes Guide
+
+A skill for exporting Zotero items, annotations, and notes to structured Markdown files for use in knowledge management systems like Obsidian, Logseq, or plain Markdown workflows. Based on zotero-mdnotes (1K stars), this skill creates a bridge between your reference library and your personal knowledge base.
+
+## Overview
+
+Zotero is excellent for managing references and reading PDFs, but its note-taking capabilities are limited compared to dedicated knowledge management tools. MDNotes solves this by exporting Zotero data to Markdown files that can be used in any Markdown-compatible system. Each exported file contains bibliographic metadata, your annotations, and your notes in a structured, interlinked format.
+
+This approach gives researchers the best of both worlds: Zotero's powerful reference management with the flexibility and interconnection capabilities of Markdown-based knowledge systems.
+
+## Configuration
+
+**Template System**
+- MDNotes uses Nunjucks-based templates to control the output format
+- Default templates produce well-structured Markdown with YAML frontmatter
+- Templates can be customized to match your preferred note structure
+- Separate templates exist for item metadata, annotations, and combined notes
+- Template variables provide access to all Zotero metadata fields
+
+**Key Configuration Options**
+- Output directory: where exported Markdown files are saved
+- File naming convention: citation key, title, or custom pattern
+- Frontmatter fields: which metadata fields to include in YAML header
+- Annotation grouping: by color, type, page, or section
+- Link format: wiki-links, Markdown links, or plain text references
+
+**Frontmatter Configuration**
+- Title, authors, year, journal, DOI are standard frontmatter fields
+- Tags from Zotero are converted to note tags
+- Custom fields can be added (read status, rating, project association)
+- Zotero item key is included for bidirectional linking
+- Date fields use ISO 8601 format for consistent sorting
+
+## Export Workflows
+
+**Single Item Export**
+- Right-click a Zotero item and select the MDNotes export option
+- Choose between metadata only, annotations only, or combined export
+- The plugin generates the Markdown file in the configured output directory
+- If a file with the same name exists, choose to overwrite or create a new version
+- The exported file opens automatically in the configured editor (optional)
+
+**Batch Export**
+- Select multiple items or an entire collection in Zotero
+- Apply export to the full selection
+- Each item generates its own Markdown file
+- A summary index file can optionally be generated listing all exported items
+- Batch exports respect the same templates and configuration as single exports
+
+**Annotation Export**
+- PDF highlights are exported with their color, page number, and surrounding text
+- Comments attached to highlights are included as sub-items
+- Free-text notes from the Zotero note editor are exported as separate sections
+- Annotations are grouped according to the configured strategy (color, page, etc.)
+- Each annotation includes a link back to the specific PDF location in Zotero
+
+## Template Customization
+
+**Metadata Template**
+- Controls the structure of the bibliographic information section
+- Standard fields: title, authors, year, journal, volume, pages, DOI, URL
+- Extended fields: abstract, keywords, collection path, date added
+- Custom fields: any Zotero extra field data
+- The template determines the order and formatting of each field
+
+**Annotation Template**
+- Controls how individual annotations are formatted
+- Color mapping: assign semantic meaning to highlight colors (yellow for key findings, blue for methodology, etc.)
+- Include or exclude the page number, annotation date, and comment
+- Format as blockquotes, bullet points, or plain text
+- Group by color to create thematic sections automatically
+
+**Combined Template**
+- Merges metadata and annotations into a single cohesive note
+- Includes section headings for clear structure
+- Adds a personal notes section at the bottom for your own synthesis
+- Includes a placeholder for connections to other notes
+- Provides a reading status field for tracking progress
+
+## Knowledge Management Integration
+
+**Obsidian Integration**
+- Export to the Obsidian vault's literature notes folder
+- Use wiki-link format for interoperability with Obsidian's linking system
+- Tags are formatted as Obsidian-compatible hashtags
+- Dataview-compatible frontmatter enables dynamic queries
+- Graph view shows connections between literature notes and your other notes
+
+**Logseq Integration**
+- Export in Logseq-compatible Markdown format
+- Use page references for linking between notes
+- Properties block replaces YAML frontmatter for Logseq compatibility
+- Block-level references are supported for granular linking
+- Journal page references connect reading dates to daily notes
+
+**Plain Markdown Workflows**
+- Export to any directory for use with any Markdown editor
+- Standard Markdown formatting ensures compatibility
+- Frontmatter follows common conventions for static site generators
+- Links use standard Markdown link syntax for maximum portability
+- Files are self-contained with no external dependencies
+
+## Advanced Usage
+
+**Selective Field Export**
+- Configure which Zotero fields are exported to reduce noise
+- Create focused templates for different project needs
+- Academic fields: include abstract, methodology tags, dataset references
+- Reading group fields: include discussion questions, presenter notes
+- Writing project fields: include relevance score, key quotes, argument position
+
+**Incremental Updates**
+- Re-export items after adding new annotations
+- The plugin can append new annotations or regenerate the full file
+- Track changes between exports using version control
+- Maintain a changelog of reading progress through dated annotations
+- Sync exported files across devices using standard file sync tools
+
+**Custom Post-Processing**
+- Apply regex transformations to exported files
+- Add custom metadata computed from Zotero fields
+- Generate index files grouping exports by tag, year, or author
+- Create citation graph files from the exported reference data
+- Format exports for specific publishing pipelines
+
+## Integration with Research-Claw
+
+This skill connects with the Research-Claw knowledge management workflow:
+
+- Export Zotero annotations as the first step in building literature reviews
+- Feed exported notes to synthesis and writing skills
+- Connect with other citation skills for a complete reference workflow
+- Use exported metadata for bibliometric analysis
+- Store exported notes in the Research-Claw knowledge base for agent access
+
+## Best Practices
+
+- Establish your template before exporting in bulk to avoid reformatting later
+- Use a consistent color scheme for annotations across all papers
+- Export promptly after reading to capture your fresh understanding
+- Include a personal synthesis section in each literature note beyond just annotations
+- Use tags consistently to enable useful filtering and grouping
+- Back up both Zotero and the exported notes directory regularly

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

@@ -0,0 +1,139 @@
+---
+name: zotero-reference-guide
+description: "PDF references add-on for enriching Zotero library metadata"
+version: 1.0.0
+author: wentor-community
+source: https://github.com/MuiseDestiny/zotero-reference
+metadata:
+  openclaw:
+    category: "writing"
+    subcategory: "citation"
+    keywords:
+      - zotero
+      - references
+      - pdf-parsing
+      - bibliography
+      - metadata-enrichment
+      - citation-linking
+---
+
+# Zotero Reference Guide
+
+A skill for using the Zotero Reference add-on to automatically parse, link, and enrich reference lists from PDF documents within Zotero. Based on zotero-reference (3K stars), this skill streamlines the process of building comprehensive, interconnected reference libraries from the papers you read.
+
+## Overview
+
+When reading academic papers, the reference list at the end contains valuable connections to related work. Manually looking up and adding these references to your library is tedious and error-prone. Zotero Reference automates this by parsing the reference section of PDFs, matching references against academic databases, and offering one-click addition to your Zotero library. This transforms passive reading into active library building.
+
+The plugin is particularly powerful for literature reviews, where you need to systematically follow citation chains, and for new researchers building their initial reference collection in a new field.
+
+## Core Features
+
+**Reference Parsing**
+- Automatically detects and parses the reference section of PDF documents
+- Extracts individual reference entries with author, title, year, and venue information
+- Handles multiple reference formatting styles (numbered, author-year, footnote)
+- Works with references spanning multiple columns and pages
+- Identifies DOIs, arXiv IDs, and other persistent identifiers within references
+
+**Database Matching**
+- Matches parsed references against Crossref, Semantic Scholar, 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
+- Caches lookup results to avoid redundant API calls
+
+**Library Integration**
+- One-click addition of matched references to the Zotero library
+- Automatically downloads available PDFs for added references
+- Places new references in the same collection as the source paper
+- Creates "related" links between the source paper and its references
+- Tracks which references from each paper have been added to the library
+
+## Workflow
+
+**Reading-Driven Library Building**
+- Open a PDF in the Zotero reader
+- The plugin's sidebar displays the parsed reference list
+- Each reference shows its match status (matched, uncertain, unmatched)
+- Click to preview metadata for any reference
+- Click the add button to import the reference into your Zotero library
+- Star references for later follow-up without immediate import
+
+**Systematic Citation Chasing**
+- Open a key paper in your research area
+- Review all references and add the relevant ones to your library
+- Open each newly added paper and repeat the process
+- Continue until you reach saturation (no new relevant references found)
+- The plugin tracks which papers have been processed to avoid revisiting
+
+**Reference Verification**
+- When the automatic match is uncertain, the plugin shows candidate matches
+- Compare the parsed reference text with each candidate's metadata
+- Select the correct match or search manually if none are correct
+- For references with no database match (grey literature, old publications), manually enter metadata
+- The verification status is saved to avoid repeated checking
+
+## Advanced Features
+
+**Batch Processing**
+- Process multiple papers in a collection simultaneously
+- Generate a combined reference list across all papers in a collection
+- Identify the most frequently cited references across the collection
+- Highlight references that appear in multiple papers (high-relevance indicators)
+- Export the frequency-ranked reference list for systematic review screening
+
+**Citation Network Visualization**
+- View how papers in your library cite each other
+- Identify clusters of closely related papers
+- Find bridge papers connecting different research themes
+- Visualize the chronological development of a research thread
+- Export citation network data for analysis in external tools
+
+**Missing Reference Detection**
+- Compare your library against the complete reference lists of key papers
+- Identify important references you have not yet added
+- Prioritize missing references by citation frequency across your collection
+- Generate reading lists from the most-cited missing references
+- Track library completeness for systematic review requirements
+
+## Handling Edge Cases
+
+The plugin manages several common challenges:
+
+**Malformed References**
+- References with typos or formatting errors may fail to parse correctly
+- The plugin highlights uncertain parses for manual review
+- Users can edit the parsed text before attempting database matching
+- Common formatting issues (missing year, abbreviated journal names) are handled automatically
+
+**Preprints and Working Papers**
+- arXiv papers are matched using arXiv IDs when present
+- Working papers from SSRN, NBER, and similar repositories are supported
+- Conference papers are matched against DBLP and ACL Anthology
+- When multiple versions exist (preprint and published), the published version is preferred
+
+**Non-English References**
+- References in non-Latin scripts are handled with Unicode support
+- Cross-language matching uses transliterated author names
+- Database coverage varies by language (English has the best coverage)
+- Manual entry is recommended for references in less-covered languages
+
+## Integration with Research-Claw
+
+This skill enhances the Research-Claw reference management pipeline:
+
+- Automatically build comprehensive bibliographies while reading papers
+- Feed parsed references to literature search skills for deeper exploration
+- Connect with citation management skills for consistent formatting
+- Support systematic review workflows with complete reference tracking
+- Enable citation network analysis across the entire research project
+
+## Best Practices
+
+- Process reference lists from your most important papers first to build a high-quality seed library
+- Always verify uncertain matches before adding to your library
+- Use collections in Zotero to organize references by project or review topic
+- Periodically check for updated metadata on previously added references
+- Combine with Zotero's duplicate detection to keep the library clean
+- Export processed reference lists as documentation for systematic review methods sections