@wentorai/research-plugins 1.0.0 → 1.2.0

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

@@ -0,0 +1,243 @@
+---
+name: paper-parse-guide
+description: "Deep dual-mode reading of academic papers from PDF or URL sources"
+metadata:
+  openclaw:
+    emoji: "microscope"
+    category: "tools"
+    subcategory: "document"
+    keywords: ["paper reading", "PDF parsing", "academic paper", "deep reading", "annotation", "GROBID"]
+    source: "https://github.com/wentor-ai/research-plugins"
+---
+
+# Paper Parse Guide
+
+Perform structured, dual-mode deep reading of academic papers from PDF files or URLs. Mode A provides a rapid overview suitable for screening during literature reviews. Mode B delivers exhaustive section-by-section analysis for papers central to your research.
+
+## Overview
+
+Reading academic papers efficiently is a core research skill, yet the density and conventions of scholarly writing make it time-consuming. A typical researcher reads dozens of papers per week during a literature review phase, requiring different levels of depth for different papers. Some need only a quick scan to determine relevance; others demand line-by-line scrutiny of methods and results.
+
+This skill implements a dual-mode reading system. Mode A (Survey Mode) extracts key metadata, the main argument, methods summary, and key findings in under two minutes of processing time. Mode B (Deep Analysis Mode) performs exhaustive section-by-section analysis including methodology critique, statistical evaluation, figure interpretation, and connection to broader literature.
+
+Both modes begin by parsing the paper's structure from its PDF or HTML source, extracting clean text with section boundaries, figures, tables, equations, and references. The parsing pipeline handles the common challenges of academic PDFs: two-column layouts, footnotes, headers/footers, embedded equations, and supplementary materials.
+
+## Paper Acquisition and Parsing
+
+### Input Sources
+
+| Source | Method | Notes |
+|--------|--------|-------|
+| Local PDF | Direct file path | Best quality, no network needed |
+| 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 |
+
+### PDF Parsing Pipeline
+
+```python
+from pathlib import Path
+import fitz  # PyMuPDF
+
+def parse_paper(pdf_path: str) -> dict:
+    doc = fitz.open(pdf_path)
+    sections = []
+    current_section = {"title": "Header", "content": []}
+
+    for page in doc:
+        blocks = page.get_text("dict")["blocks"]
+        for block in blocks:
+            if block["type"] == 0:  # Text block
+                for line in block["lines"]:
+                    text = " ".join(span["text"] for span in line["spans"])
+                    font_size = max(span["size"] for span in line["spans"])
+                    is_bold = any("Bold" in span["font"] for span in line["spans"])
+
+                    # Detect section headings
+                    if font_size > 11 and is_bold:
+                        if current_section["content"]:
+                            sections.append(current_section)
+                        current_section = {"title": text.strip(), "content": []}
+                    else:
+                        current_section["content"].append(text)
+
+    sections.append(current_section)
+    return {
+        "title": extract_title(doc),
+        "authors": extract_authors(doc),
+        "sections": sections,
+        "references": extract_references(doc),
+        "page_count": len(doc)
+    }
+```
+
+### GROBID Integration
+
+For higher-quality structural parsing, use GROBID (GeneRation Of BIbliographic Data):
+
+```bash
+# Start GROBID server
+docker run --rm -p 8070:8070 lfoppiano/grobid:0.8.0
+
+# Parse a paper
+curl -X POST "http://localhost:8070/api/processFulltextDocument" \
+  -F "input=@paper.pdf" \
+  -F "consolidateHeader=1" \
+  -F "consolidateCitations=1" \
+  -H "Accept: application/xml" \
+  -o parsed_paper.xml
+```
+
+GROBID returns TEI XML with structured sections, author affiliations, parsed references, and figure/table captions. It handles two-column layouts, footnotes, and complex formatting better than simple text extraction.
+
+## Mode A: Survey Reading
+
+Designed for rapid screening. Produces a structured summary in 5 components:
+
+### 1. Identity Card
+
+```
+Title:      [Extracted title]
+Authors:    [First author et al., year]
+Venue:      [Journal/Conference name]
+DOI:        [DOI if available]
+Pages:      [Page count]
+Type:       [Empirical / Theoretical / Review / Methods]
+```
+
+### 2. Core Argument (1-2 sentences)
+
+Extract from abstract + introduction: What is the main claim?
+
+### 3. Methods Snapshot
+
+- Study design (experimental, observational, computational, theoretical)
+- Sample/dataset description
+- Key techniques or models used
+
+### 4. Key Findings (3-5 bullets)
+
+Extract from results section and abstract.
+
+### 5. Relevance Assessment
+
+- Relevance to current research question: High / Medium / Low
+- Methodological quality signal: sample size, controls, statistical rigor
+- Recommended action: Deep read / Cite only / Skip
+
+## Mode B: Deep Analysis
+
+Exhaustive section-by-section reading with critical evaluation.
+
+### Introduction Analysis
+
+- What gap in the literature does this paper address?
+- What is the stated research question or hypothesis?
+- How does the framing position the contribution?
+
+### Literature Review Evaluation
+
+- Which theoretical frameworks are invoked?
+- Are there notable omissions in cited literature?
+- How does the paper position itself relative to competing approaches?
+
+### Methodology Critique
+
+- Is the methodology appropriate for the research question?
+- Sample size and power analysis: reported? adequate?
+- Threats to internal and external validity
+- Reproducibility: are methods described in sufficient detail?
+- Statistical tests: appropriate? assumptions met?
+
+### Results Assessment
+
+- Do the results support the claims?
+- Effect sizes: reported? meaningful?
+- Confidence intervals vs. p-values
+- Figures and tables: do they accurately represent the data?
+- Any signs of p-hacking or selective reporting?
+
+### Discussion Evaluation
+
+- Are limitations adequately acknowledged?
+- Are alternative explanations considered?
+- Do the conclusions follow logically from the results?
+- Are implications overstated?
+
+### Reference Network
+
+- Extract all cited works with metadata
+- Identify seminal references (cited by many papers in this field)
+- Flag self-citations
+- Map citation clusters by topic
+
+## Output Formats
+
+### Structured Note (Markdown)
+
+```markdown
+## [Paper Title] ([Year])
+
+**Authors**: [Authors]
+**Venue**: [Venue]
+**DOI**: [DOI]
+
+### Summary
+[2-3 sentence summary]
+
+### Key Contributions
+1. [Contribution 1]
+2. [Contribution 2]
+
+### Methodology
+[Methods description]
+
+### Strengths
+- [Strength 1]
+- [Strength 2]
+
+### Weaknesses
+- [Weakness 1]
+- [Weakness 2]
+
+### Relevance to My Research
+[How this paper connects to your work]
+
+### Key Quotes
+> "[Notable quote]" (p. X)
+
+### References to Follow
+- [Ref 1]: [Why relevant]
+- [Ref 2]: [Why relevant]
+```
+
+### BibTeX Entry
+
+Automatically extract or generate a BibTeX entry for the parsed paper, including all available fields (author, title, journal, year, volume, pages, doi).
+
+## Batch Processing
+
+For systematic reviews, process multiple papers in sequence:
+
+```python
+papers = ["paper1.pdf", "paper2.pdf", "paper3.pdf"]
+summaries = []
+
+for pdf in papers:
+    parsed = parse_paper(pdf)
+    summary = mode_a_survey(parsed)
+    summaries.append(summary)
+
+# Generate comparison matrix
+comparison = create_comparison_table(summaries,
+    columns=["methods", "sample_size", "key_finding", "relevance"])
+```
+
+## References
+
+- GROBID: https://github.com/kermitt2/grobid
+- PyMuPDF: https://pymupdf.readthedocs.io
+- Semantic Scholar API: https://api.semanticscholar.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/document/weknora-guide/SKILL.md

@@ -0,0 +1,216 @@
+---
+name: weknora-guide
+description: "Tencent document understanding engine with RAG capabilities"
+metadata:
+  openclaw:
+    emoji: "📑"
+    category: "tools"
+    subcategory: "document"
+    keywords: ["WeKnora", "document understanding", "RAG", "text mining", "Tencent", "knowledge extraction"]
+    source: "https://github.com/Tencent/WeKnora"
+---
+
+# WeKnora Guide
+
+## Overview
+
+WeKnora is Tencent's open-source document understanding and retrieval-augmented generation engine. It processes complex documents (PDF, DOCX, HTML) into structured knowledge, supporting layout analysis, table extraction, formula recognition, and multi-modal content parsing. Integrates with RAG pipelines for question answering over document collections. Suited for academic paper processing, report analysis, and enterprise document intelligence.
+
+## Installation
+
+```bash
+# Install WeKnora
+pip install weknora
+
+# With GPU support
+pip install weknora[gpu]
+
+# With all optional dependencies
+pip install weknora[all]
+```
+
+## Document Parsing
+
+```python
+from weknora import DocumentParser
+
+parser = DocumentParser()
+
+# Parse a PDF document
+doc = parser.parse("research_paper.pdf")
+
+print(f"Pages: {doc.num_pages}")
+print(f"Sections: {len(doc.sections)}")
+print(f"Tables: {len(doc.tables)}")
+print(f"Figures: {len(doc.figures)}")
+print(f"Equations: {len(doc.equations)}")
+
+# Access structured content
+for section in doc.sections:
+    print(f"\n## {section.title}")
+    print(f"   {section.text[:200]}...")
+    if section.tables:
+        print(f"   Tables: {len(section.tables)}")
+```
+
+## Layout Analysis
+
+```python
+from weknora import LayoutAnalyzer
+
+analyzer = LayoutAnalyzer(model="layoutlmv3")
+
+# Detect document layout elements
+layout = analyzer.analyze("paper.pdf")
+
+for page in layout.pages:
+    print(f"\nPage {page.number}:")
+    for element in page.elements:
+        print(f"  [{element.type}] ({element.bbox}) "
+              f"{element.text[:50]}...")
+    # Element types: title, text, table, figure,
+    #   equation, header, footer, caption, list
+```
+
+## Table Extraction
+
+```python
+from weknora import TableExtractor
+
+extractor = TableExtractor()
+
+# Extract tables from document
+tables = extractor.extract("paper.pdf")
+
+for i, table in enumerate(tables):
+    print(f"\nTable {i+1}: {table.caption}")
+    df = table.to_dataframe()
+    print(df.head())
+
+    # Export
+    df.to_csv(f"table_{i+1}.csv")
+
+# Extract specific table by page
+table = extractor.extract_from_page("paper.pdf", page=5, index=0)
+```
+
+## Formula Recognition
+
+```python
+from weknora import FormulaRecognizer
+
+recognizer = FormulaRecognizer()
+
+# Extract formulas from document
+formulas = recognizer.extract("paper.pdf")
+
+for formula in formulas:
+    print(f"Page {formula.page}: {formula.latex}")
+    # Output: "\\mathcal{L} = -\\sum_{i} y_i \\log(\\hat{y}_i)"
+    print(f"  Type: {formula.type}")  # inline or display
+```
+
+## RAG Pipeline
+
+```python
+from weknora import RAGPipeline
+
+# Build RAG over document collection
+rag = RAGPipeline(
+    embedding_model="bge-large-zh-v1.5",
+    chunk_size=512,
+    chunk_overlap=64,
+)
+
+# Index documents
+rag.add_documents([
+    "papers/transformer.pdf",
+    "papers/bert.pdf",
+    "papers/gpt3.pdf",
+])
+
+# Query
+result = rag.query(
+    "What is the computational complexity of self-attention?"
+)
+print(result.answer)
+for source in result.sources:
+    print(f"  [{source.document}] p.{source.page}: "
+          f"{source.text[:80]}...")
+```
+
+## Multi-Modal Processing
+
+```python
+from weknora import MultiModalParser
+
+parser = MultiModalParser()
+
+# Process document with figures and tables
+doc = parser.parse("paper.pdf", extract_all=True)
+
+# Access figure descriptions
+for fig in doc.figures:
+    print(f"Figure {fig.number}: {fig.caption}")
+    fig.save_image(f"figures/fig_{fig.number}.png")
+
+# Cross-reference tables and text
+for ref in doc.cross_references:
+    print(f"'{ref.text}' → {ref.target_type} {ref.target_id}")
+```
+
+## Batch Processing
+
+```python
+from weknora import BatchProcessor
+
+processor = BatchProcessor(
+    workers=4,
+    output_dir="./parsed_docs",
+)
+
+# Process directory of documents
+results = processor.process_directory(
+    "papers/",
+    formats=["pdf", "docx"],
+    output_format="json",  # or "markdown"
+)
+
+print(f"Processed: {results.success}/{results.total}")
+print(f"Failed: {results.failures}")
+```
+
+## Configuration
+
+```python
+from weknora import Config
+
+config = Config(
+    parser={
+        "layout_model": "layoutlmv3",
+        "ocr_engine": "paddleocr",
+        "formula_engine": "latex_ocr",
+        "language": "en",  # or "zh", "multi"
+    },
+    rag={
+        "embedding_model": "bge-large-zh-v1.5",
+        "reranker": "bge-reranker-large",
+        "chunk_strategy": "semantic",
+        "vector_store": "faiss",
+    },
+)
+```
+
+## Use Cases
+
+1. **Paper parsing**: Extract structured content from academic PDFs
+2. **Table digitization**: Convert paper tables to spreadsheets
+3. **Document QA**: RAG-based question answering over papers
+4. **Knowledge extraction**: Build knowledge bases from documents
+5. **Report analysis**: Process and compare technical reports
+
+## References
+
+- [WeKnora GitHub](https://github.com/Tencent/WeKnora)
+- [LayoutLMv3](https://arxiv.org/abs/2204.08387)
+- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)

package/skills/tools/document/zotero-addon-market-guide/SKILL.md

@@ -0,0 +1,108 @@
+---
+name: zotero-addon-market-guide
+description: "Plugin marketplace and discovery platform for Zotero"
+metadata:
+  openclaw:
+    emoji: "🏪"
+    category: "tools"
+    subcategory: "document"
+    keywords: ["Zotero", "plugin marketplace", "add-ons", "plugin discovery", "extension manager"]
+    source: "https://github.com/syt2/zotero-addons"
+---
+
+# Zotero Add-on Market Guide
+
+## Overview
+
+Zotero Add-ons is a plugin marketplace and discovery platform for Zotero 7 that provides a centralized hub to browse, install, and manage Zotero plugins. Instead of manually finding .xpi files on GitHub, researchers can search, filter, and one-click install plugins directly within Zotero. Tracks plugin compatibility, update status, and user ratings.
+
+## Installation
+
+```bash
+# Download .xpi from GitHub releases
+# Zotero 7: Tools → Add-ons → Install Add-on From File
+
+# After installation: Tools → Add-on Market
+```
+
+## Features
+
+```markdown
+### Plugin Discovery
+- Browse all available Zotero 7 plugins
+- Search by name, category, or keyword
+- Filter: compatible version, update date, popularity
+- Plugin descriptions with screenshots
+
+### Categories
+- **Reference Management**: Better BibTeX, DOI Manager
+- **PDF Tools**: PDF Translate, Sci-Hub, annotations
+- **Organization**: Style, Actions & Tags, ZotMoov
+- **Integration**: Notero, Obsidian, Logseq connectors
+- **UI Enhancement**: Night theme, custom columns
+- **Automation**: Actions & Tags, batch operations
+
+### Management
+- One-click install from marketplace
+- Auto-update notifications
+- Compatibility warnings
+- Disable/enable without uninstall
+- Bulk update all plugins
+```
+
+## Recommended Plugin Stack
+
+```markdown
+### Essential Stack for Researchers
+
+1. **Zotero Connector** (built-in) — Browser import
+2. **Better BibTeX** — Citation key management
+3. **Zotero Style** — Custom columns, visual tags
+4. **Zotero PDF Translate** — In-reader translation
+5. **ZotMoov** — Attachment organization
+6. **Zotero Actions & Tags** — Workflow automation
+
+### Extended Stack
+
+7. **Zotero Night** — Dark mode
+8. **Zoplicate** — Deduplication
+9. **Zotero Sci-Hub** — PDF retrieval fallback
+10. **Notero** — Notion sync
+11. **Zotero AI Butler** — AI summarization
+
+### For Specific Workflows
+
+- **Systematic reviews**: Zoplicate + Actions & Tags
+- **LaTeX writing**: Better BibTeX + Style
+- **Knowledge management**: Notero + Zotero-Obsidian
+- **International**: PDF Translate + multi-language support
+```
+
+## Plugin Development
+
+```markdown
+### Creating Zotero 7 Plugins
+
+1. Use zotero-plugin-template (scaffolding)
+2. Write in TypeScript/JavaScript
+3. Package as .xpi (ZIP with manifest)
+4. Submit to zotero-addons registry
+
+### Plugin Template
+- Source: github.com/windingwind/zotero-plugin-template
+- Includes: build setup, hot reload, bootstrap code
+- Supports: Zotero 7 APIs, Fluent localization
+```
+
+## Use Cases
+
+1. **Plugin discovery**: Find plugins for your research workflow
+2. **Stack building**: Assemble optimized plugin combinations
+3. **Updates**: Keep all plugins current and compatible
+4. **Development**: Starting point for creating Zotero plugins
+
+## References
+
+- [Zotero Add-ons GitHub](https://github.com/syt2/zotero-addons)
+- [Zotero Plugin Template](https://github.com/windingwind/zotero-plugin-template)
+- [Zotero 7 Plugin Development](https://www.zotero.org/support/dev/client_coding/plugin_development)

package/skills/tools/document/zotero-night-theme-guide/SKILL.md

@@ -0,0 +1,142 @@
+---
+name: zotero-night-theme-guide
+description: "Dark mode theme plugin for Zotero reference manager"
+metadata:
+  openclaw:
+    emoji: "🌙"
+    category: "tools"
+    subcategory: "document"
+    keywords: ["Zotero", "dark mode", "theme", "night mode", "UI customization", "eye comfort"]
+    source: "https://github.com/tefkah/zotero-night"
+---
+
+# Zotero Night Theme Guide
+
+## Overview
+
+Zotero Night is a dark mode theme plugin for Zotero that transforms the entire UI — library view, PDF reader, note editor, and preferences — into a comfortable dark interface. Reduces eye strain during long reading sessions and matches system-wide dark mode preferences. Works with Zotero 7 and integrates with other Zotero plugins.
+
+## Installation
+
+```bash
+# Download latest .xpi from GitHub releases
+# In Zotero 7: Tools → Add-ons → Install Add-on From File
+
+# Or via Zotero Plugin Market
+# Search "Zotero Night" in zotero-addons marketplace
+```
+
+## Configuration
+
+```markdown
+### Settings (Tools → Zotero Night)
+
+**Theme Mode:**
+- Dark — Always dark
+- Light — Always light
+- System — Follow OS dark/light mode
+- Schedule — Dark between custom hours
+
+**PDF Reader:**
+- Dark background with inverted text
+- Sepia mode for reduced blue light
+- Custom brightness/contrast
+- Preserve figure colors (don't invert images)
+
+**Colors:**
+- Background: customizable (default #1E1E1E)
+- Text: customizable (default #D4D4D4)
+- Accent: customizable (matches Zotero theme)
+- Link color: customizable
+```
+
+## Theme Variants
+
+```css
+/* Built-in theme presets */
+
+/* Default Dark */
+--background: #1E1E1E;
+--surface: #252526;
+--text: #D4D4D4;
+--text-secondary: #808080;
+--accent: #007ACC;
+--border: #3C3C3C;
+
+/* OLED Dark */
+--background: #000000;
+--surface: #121212;
+--text: #E0E0E0;
+
+/* Nord */
+--background: #2E3440;
+--surface: #3B4252;
+--text: #ECEFF4;
+--accent: #88C0D0;
+
+/* Solarized Dark */
+--background: #002B36;
+--surface: #073642;
+--text: #839496;
+--accent: #268BD2;
+```
+
+## PDF Reader Dark Mode
+
+```markdown
+### How It Works
+1. Applies CSS filter to PDF viewer canvas
+2. Inverts luminance while preserving hue
+3. Special handling for:
+   - Figures/images: excluded from inversion
+   - Highlighted text: color preserved
+   - Annotations: maintain original colors
+   - Links: distinct clickable appearance
+
+### Settings
+- Brightness: 80-120% (adjustable)
+- Contrast: 90-110% (adjustable)
+- Invert images: on/off (default off)
+- Sepia filter: 0-100% (for warm tones)
+```
+
+## Integration with Other Plugins
+
+```markdown
+### Compatible Plugins
+- **Zotero Style** — Custom columns work in dark mode
+- **Zotero PDF Translate** — Translation overlay themed
+- **Better BibTeX** — Citation dialog themed
+- **Zotero Actions Tags** — Tag colors adapt to dark background
+
+### CSS Customization
+For advanced users, override via userChrome.css:
+  Zotero profile → chrome/userChrome.css
+```
+
+## Scheduled Dark Mode
+
+```json
+{
+  "schedule": {
+    "enabled": true,
+    "darkStart": "18:00",
+    "darkEnd": "07:00",
+    "useSystemSunrise": true,
+    "transition": "gradual"
+  }
+}
+```
+
+## Use Cases
+
+1. **Night reading**: Comfortable PDF reading in low light
+2. **Eye health**: Reduce blue light and screen glare
+3. **Consistency**: Match OS/IDE dark mode preferences
+4. **Long sessions**: Extended literature review comfort
+5. **Presentation**: Professional dark UI for screen sharing
+
+## References
+
+- [Zotero Night GitHub](https://github.com/tefkah/zotero-night)
+- [Zotero 7 Theming](https://www.zotero.org/support/preferences)