Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub ยท Developer Tools
ScholarGraph
AI toolkit for academic research that finds papers, extracts insights, builds knowledge graphs, tracks trends, and reveals literature gaps.
skill openclawclawhub Free
AI toolkit for academic research that finds papers, extracts insights, builds knowledge graphs, tracks trends, and reveals literature gaps.
โฌ 0 downloads โ
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- CHANGELOG.md, cli.ts, concept-extractor/scripts/extract.ts, concept-extractor/scripts/types.ts, concept-learner/scripts/learn.ts, concept-learner/scripts/types.ts
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 1.4.3
Provenance
- Publisher
- Josephyb97
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Overview
ScholarGraph is a comprehensive academic literature intelligence toolkit that helps researchers efficiently search, analyze, and manage academic papers using AI-powered tools. Features 11 academic search sources with intelligent domain-based source selection and PDF download capabilities.
Security & Privacy
This skill operates with the following permissions: Network Access: Queries academic APIs (arXiv, Semantic Scholar, OpenAlex, PubMed, CrossRef, DBLP, IEEE, CORE, Google Scholar, Unpaywall) and web search services File System: Reads/writes configuration files, downloads PDFs, stores knowledge graphs in SQLite database (data/knowledge-graphs.db) LLM Integration: Sends custom system prompts to AI providers for structured JSON output (concept extraction, paper analysis, etc.) Optional Python: PDF figure extraction (pymupdf) and PPT export (python-pptx) require Python 3.8+ Data Storage: All data is stored locally. No telemetry or analytics are collected. API Keys: Optional API keys are only used for their respective services and are never transmitted elsewhere. Source Code: Open source under MIT license at https://github.com/Josephyb97/ScholarGraph
Core Modules (6)
Literature Search - Multi-source academic paper discovery (11 sources) Free sources: arXiv, Semantic Scholar, OpenAlex (250M+), PubMed (biomedical), CrossRef (150M+ DOI), DBLP (CS), Web Search API-key sources: IEEE Xplore, CORE, Google Scholar (SerpAPI), Unpaywall (OA PDF) Adapter-based plugin architecture for easy extension Complementary search strategy with auto domain detection (biomedical/cs/engineering/physics) Priority-based source selection per domain Query expansion for better search results PDF download with multi-strategy URL resolution Concept Learner - Rapid knowledge framework construction Generate structured learning cards Include code examples and related papers Support beginner/intermediate/advanced depth levels Knowledge Gap Detector - Proactive blind spot identification Analyze knowledge coverage in specific domains Identify critical, recommended, and optional gaps Provide learning recommendations and time estimates Progress Tracker - Real-time field monitoring Track research topics and keywords Generate daily/weekly/monthly reports Monitor trending papers and topics Paper Analyzer - Deep paper analysis Extract key contributions and insights Support quick/standard/deep analysis modes Generate structured analysis reports Knowledge Graph Builder - Concept relationship visualization Build interactive knowledge graphs Support Mermaid and JSON output formats Find learning paths between concepts SQLite-based persistent storage Bidirectional concept-paper indexing
Advanced Features (9)
Review Detector - Automatic review paper identification Multi-dimensional scoring (title 30% + citations 25% + abstract 25% + AI 20%) Chinese and English keyword support Confidence-based filtering with user confirmation Concept Extractor - Extract concepts from review papers AI-powered extraction of 15-30 core concepts Four-level categorization (foundation/core/advanced/application) Importance scoring and relationship identification Cross-review deduplication and merging Review-to-Graph Workflow - End-to-end pipeline Search reviews -> Detect -> Confirm -> Analyze -> Extract concepts Build knowledge graph -> Enrich with key papers -> Index -> Store Interactive or automatic confirmation mode Knowledge Graph Query - Bidirectional literature indexing Concept -> papers: find papers related to a concept Paper -> concepts: find concepts covered by a paper Paper recommendations based on multiple concepts SQLite-optimized high-performance queries Compare Concepts - Compare two concepts Identify similarities and differences Provide use case recommendations Compare Papers - Compare multiple papers Find common themes and differences Generate synthesis analysis Critique - Critical paper analysis Identify strengths and weaknesses Find research gaps and improvement suggestions Support custom focus areas Learning Path - Find optimal learning paths Discover paths between concepts Generate topological learning order Visualize with Mermaid diagrams Graph Management - Manage persistent knowledge graphs List all saved graphs View graph statistics Export graphs to JSON Visualize with Mermaid Paper Visualization - Interactive paper presentation Convert paper analysis to HTML slide presentations Academic dark/light themes with responsive typography Keyboard/touch/scroll navigation, edit mode (E key) PDF figure extraction (pymupdf) and PPT export (python-pptx) 8+ slides: title, abstract, key points, methodology, experiments, contributions, limitations, references Interactive Knowledge Graph - D3.js force-directed visualization Convert knowledge graphs to interactive HTML with D3.js v7 Node size reflects paper count, edge thickness reflects concept tightness Zoom/pan, node dragging, click-to-detail panel, search, legend Paper preview bridge: click "View Presentation" to open paper slides in new tab Category colors: foundation=#4FC3F7, core=#FFB74D, advanced=#CE93D8, application=#81C784
Technical Features
11 Academic Search Sources: arXiv, Semantic Scholar, OpenAlex, PubMed, CrossRef, DBLP, IEEE Xplore, CORE, Google Scholar, Unpaywall, Web Search Complementary Search Strategy: Auto-detects query domain and selects optimal source combination Adapter Pattern: Plugin-based search source architecture for easy extension PDF Download: Multi-strategy URL resolution (direct, Unpaywall, OpenAlex OA, CORE) Multi-AI Provider Support: 15+ AI providers including OpenAI, Anthropic, DeepSeek, Qwen, Zhipu AI, etc. SQLite Persistence: Knowledge graphs stored in SQLite database via bun:sqlite Bidirectional Indexing: Concept-paper and paper-concept bidirectional query support Rate Limiting: Per-source rate limiting with automatic retry and delay Interactive HTML Output: Paper slide presentations, D3.js knowledge graph visualizations Multiple Output Formats: Markdown, JSON, Mermaid, HTML, PPTX TypeScript + Bun: Fast and type-safe runtime CLI + API: Both command-line and programmatic interfaces
Installation
# Clone repository git clone https://github.com/Josephyb97/ScholarGraph.git cd ScholarGraph # Install dependencies bun install # Initialize configuration bun run cli.ts config init
Configuration
Set up your AI provider: # Using OpenAI export AI_PROVIDER=openai export OPENAI_API_KEY="your-api-key" # Using DeepSeek export AI_PROVIDER=deepseek export DEEPSEEK_API_KEY="your-api-key" # Using Qwen (้ไนๅ้ฎ) export AI_PROVIDER=qwen export QWEN_API_KEY="your-api-key"
Academic Source API Keys (optional, expand search coverage)
export NCBI_API_KEY="your-key" # PubMed high-speed access (10 req/s) export IEEE_API_KEY="your-key" # IEEE Xplore engineering papers export CORE_API_KEY="your-key" # CORE open access full text export UNPAYWALL_EMAIL="your@email.com" # Unpaywall OA PDF resolver export CROSSREF_MAILTO="your@email.com" # CrossRef polite pool (higher rate) export SERPAPI_KEY="your-key" # Google Scholar (via SerpAPI) export SERPER_API_KEY="your-key" # Web search via Serper
Search Literature
# Auto-select best sources based on query domain lit search "transformer attention" --limit 20 # Specify domain for optimized source selection lit search "CRISPR gene editing" --domain biomedical # Use specific sources (comma-separated) lit search "deep learning" --source semantic_scholar,arxiv,openalex --sort citations # Search and download PDFs lit search "attention is all you need" --download --limit 3
Download PDFs
# Search and download PDFs lit download "transformer" --limit 5 --output ./papers
Learn Concepts
lit learn "BERT" --depth advanced --papers --code --output bert-card.md
Detect Knowledge Gaps
lit detect --domain "Deep Learning" --known "CNN,RNN" --output gaps.md
Analyze Papers
lit analyze "https://arxiv.org/abs/1706.03762" --mode deep --output analysis.md
Build Knowledge Graph
lit graph transformer attention BERT GPT --format mermaid --output graph.md
Compare Concepts
lit compare concepts CNN RNN --output comparison.md
Compare Papers
lit compare papers "url1" "url2" "url3" --output comparison.md
Critical Analysis
lit critique "paper-url" --focus "novelty,scalability" --output critique.md
Find Learning Path
lit path "Machine Learning" "Deep Learning" --concepts "Neural Networks" --output path.md
Search Review Papers
lit review-search "attention mechanism" --limit 10
Build Knowledge Graph from Reviews
# From search query (interactive mode) lit review-graph "deep learning" --output dl-graph --enrich # From specific URL lit review-graph "https://arxiv.org/abs/xxxx" --output my-graph --enrich # Auto-confirm mode (non-interactive) lit review-graph "transformer" --output tf-graph --enrich --auto-confirm
Query Knowledge Graph
# Find papers by concept lit query concept "transformer" --graph dl-graph --limit 20 # Find concepts by paper lit query paper "https://arxiv.org/abs/1706.03762" --graph dl-graph
Manage Knowledge Graphs
# List all graphs lit graph-list # View graph statistics lit graph-stats dl-graph # Visualize graph lit graph-viz dl-graph --format mermaid --output graph.md # Export graph lit graph-export dl-graph --output dl-graph.json
Paper Visualization
# Generate interactive HTML presentation lit paper-viz "https://arxiv.org/abs/1706.03762" --output attention.html # With theme and PPT export lit paper-viz "https://arxiv.org/abs/1706.03762" --mode deep --theme academic-light --ppt # Manually provide figures lit paper-viz "https://example.com/paper" --figures ./my-figures
Interactive Knowledge Graph
# Generate interactive D3.js graph from existing knowledge graph lit graph-interactive dl-graph --output dl-interactive.html # Without paper data (lighter weight) lit graph-interactive my-graph --no-paper-viz
1. Quick Field Onboarding
Learn core concepts Detect prerequisite gaps Build knowledge graph Plan learning path
2. Deep Paper Understanding
Analyze paper in depth Perform critical analysis Learn new concepts from paper Compare with related papers
3. Research Progress Tracking
Monitor research topics Track latest papers Generate progress reports
4. Concept Comparison
Compare technical approaches Evaluate different models Build comparison graphs
5. Review-Driven Knowledge Building
Search and identify review papers Extract concepts from reviews Build persistent knowledge graphs Query concept-paper relationships
6. Paper Visualization & Graph Exploration
Analyze paper and generate interactive HTML presentation Build knowledge graph from reviews Generate interactive D3.js graph with paper preview Click nodes to view paper details and open presentations
Project Structure
ScholarGraph/ โโโ cli.ts # Unified CLI entry โโโ config.ts # Configuration management โโโ README.md # Project documentation โโโ CHANGELOG.md # Version history โโโ SKILL.md # This file โ โโโ shared/ # Shared modules โ โโโ ai-provider.ts # AI provider abstraction โ โโโ types.ts # Type definitions โ โโโ validators.ts # Parameter validation โ โโโ errors.ts # Error handling โ โโโ utils.ts # Utility functions โ โโโ literature-search/ # Literature search module โ โโโ scripts/ โ โโโ search.ts # Search engine core โ โโโ types.ts # Type definitions โ โโโ query-expander.ts # Query expansion โ โโโ search-strategy.ts # Complementary search strategy โ โโโ pdf-downloader.ts # PDF download module โ โโโ adapters/ # Search source adapters โ โโโ base.ts # Adapter interface & base class โ โโโ registry.ts # Adapter registry โ โโโ index.ts # Barrel export โ โโโ arxiv-adapter.ts โ โโโ semantic-scholar-adapter.ts โ โโโ web-adapter.ts โ โโโ openalex-adapter.ts โ โโโ pubmed-adapter.ts โ โโโ crossref-adapter.ts โ โโโ dblp-adapter.ts โ โโโ ieee-adapter.ts โ โโโ core-adapter.ts โ โโโ unpaywall-adapter.ts โ โโโ google-scholar-adapter.ts โ โโโ concept-learner/ # Concept learning module โโโ knowledge-gap-detector/ # Gap detection module โโโ progress-tracker/ # Progress tracking module โโโ paper-analyzer/ # Paper analysis module โ โโโ review-detector/ # Review paper identification โ โโโ scripts/ โ โโโ detect.ts # Multi-dimensional scoring โ โโโ types.ts โ โโโ concept-extractor/ # Concept extraction from reviews โ โโโ scripts/ โ โโโ extract.ts # AI-powered extraction โ โโโ types.ts โ โโโ knowledge-graph/ # Knowledge graph module โ โโโ scripts/ โ โโโ graph.ts # Graph building core โ โโโ indexer.ts # Bidirectional indexing โ โโโ storage.ts # SQLite persistence โ โโโ enricher.ts # Key paper association โ โโโ paper-viz/ # Paper visualization โ โโโ scripts/ โ โโโ types.ts # Presentation data interfaces โ โโโ slide-builder.ts # PaperAnalysis โ slides โ โโโ html-generator.ts # Self-contained HTML generation โ โโโ pdf-figure-extractor.ts # PDF figure extraction (pymupdf) โ โโโ ppt-exporter.ts # PPT export (python-pptx) โ โโโ graph-viz/ # Interactive knowledge graph โ โโโ scripts/ โ โโโ types.ts # D3 graph data interfaces โ โโโ graph-data-adapter.ts # KnowledgeGraph โ D3 data โ โโโ html-generator.ts # Interactive HTML (D3.js v7) โ โโโ paper-viz-bridge.ts # Graph โ paper presentation bridge โ โโโ workflows/ # End-to-end workflows โ โโโ review-to-graph.ts # Review to graph pipeline โ โโโ data/ # Data directory (auto-created) โ โโโ knowledge-graphs.db # SQLite database โ โโโ downloads/ # PDF downloads (auto-created) โ โโโ pdfs/ โ โโโ metadata.json # Download index โ โโโ test/ # Tests and documentation โโโ ADVANCED_FEATURES.md โโโ TEST_RESULTS.md โโโ scripts/
International
OpenAI Anthropic (Claude) Azure OpenAI Groq Together AI Ollama (local)
China
้ไนๅ้ฎ (Qwen/DashScope) DeepSeek ๆบ่ฐฑ AI (GLM) MiniMax Moonshot (Kimi) ็พๅท AI (Baichuan) ้ถไธไธ็ฉ (Yi) ่ฑๅ (Doubao)
Markdown Reports
Concept cards with definitions, components, history, applications Gap reports with analysis and recommendations Progress reports with trending topics Paper analyses with methods, experiments, contributions Comparison analyses with similarities and differences Critical analyses with strengths, weaknesses, and suggestions
JSON Data
Structured data for programmatic processing
Mermaid Diagrams
Interactive knowledge graphs and learning paths
Interactive HTML
Paper slide presentations with keyboard/scroll/touch navigation D3.js force-directed knowledge graph with zoom, search, and paper panel
Requirements
Bun 1.3+ or Node.js 18+ AI provider API key Internet connection for paper search Python 3.8+ (optional, for PDF figure extraction and PPT export)
License
MIT License
Links
GitHub: https://github.com/Josephyb97/ScholarGraph Issues: https://github.com/Josephyb97/ScholarGraph/issues Discussions: https://github.com/Josephyb97/ScholarGraph/discussions
Version
Current version: 1.0.0
Author
ScholarGraph Team Design Inspirations: frontend-slides - Paper slide presentation design reference Argo Scholar - Interactive knowledge graph design reference For detailed documentation, see README.md For advanced features, see test/ADVANCED_FEATURES.md For test results, see test/TEST_RESULTS.md
Category context
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
5 Scripts1 Docs
- CHANGELOG.md
- cli.ts
- concept-extractor/scripts/extract.ts
- concept-extractor/scripts/types.ts
- concept-learner/scripts/learn.ts
- concept-learner/scripts/types.ts