$npx -y skills add LeonChaoX/qinyan-academic-skills --skill research-lookupLook up current research information using the Parallel Chat API (primary) or Perplexity sonar-pro-search (academic paper searches). Automatically routes queries to the best backend. Use for finding papers, gathering research data, and verifying scientific information.
| 1 | # Research Information Lookup |
| 2 | |
| 3 | ## Overview |
| 4 | |
| 5 | This skill provides real-time research information lookup with **intelligent backend routing**: |
| 6 | |
| 7 | - **Parallel Chat API** (`core` model): Default backend for all general research queries. Provides comprehensive, multi-source research reports with inline citations via the OpenAI-compatible Chat API at `https://api.parallel.ai`. |
| 8 | - **Perplexity sonar-pro-search** (via OpenRouter): Used only for academic-specific paper searches where scholarly database access is critical. |
| 9 | |
| 10 | The skill automatically detects query type and routes to the optimal backend. |
| 11 | |
| 12 | ## When to Use This Skill |
| 13 | |
| 14 | Use this skill when you need: |
| 15 | |
| 16 | - **Current Research Information**: Latest studies, papers, and findings |
| 17 | - **Literature Verification**: Check facts, statistics, or claims against current research |
| 18 | - **Background Research**: Gather context and supporting evidence for scientific writing |
| 19 | - **Citation Sources**: Find relevant papers and studies to cite |
| 20 | - **Technical Documentation**: Look up specifications, protocols, or methodologies |
| 21 | - **Market/Industry Data**: Current statistics, trends, competitive intelligence |
| 22 | - **Recent Developments**: Emerging trends, breakthroughs, announcements |
| 23 | |
| 24 | ## Visual Enhancement with Scientific Schematics |
| 25 | |
| 26 | **When creating documents with this skill, always consider adding scientific diagrams and schematics to enhance visual communication.** |
| 27 | |
| 28 | If your document does not already contain schematics or diagrams: |
| 29 | - Use the **scientific-schematics** skill to generate AI-powered publication-quality diagrams |
| 30 | - Simply describe your desired diagram in natural language |
| 31 | |
| 32 | ```bash |
| 33 | python scripts/generate_schematic.py "your diagram description" -o figures/output.png |
| 34 | ``` |
| 35 | |
| 36 | --- |
| 37 | |
| 38 | ## Automatic Backend Selection |
| 39 | |
| 40 | The skill automatically routes queries to the best backend based on content: |
| 41 | |
| 42 | ### Routing Logic |
| 43 | |
| 44 | ``` |
| 45 | Query arrives |
| 46 | | |
| 47 | +-- Contains academic keywords? (papers, DOI, journal, peer-reviewed, etc.) |
| 48 | | YES --> Perplexity sonar-pro-search (academic search mode) |
| 49 | | |
| 50 | +-- Everything else (general research, market data, technical info, analysis) |
| 51 | --> Parallel Chat API (core model) |
| 52 | ``` |
| 53 | |
| 54 | ### Academic Keywords (Routes to Perplexity) |
| 55 | |
| 56 | Queries containing these terms are routed to Perplexity for academic-focused search: |
| 57 | |
| 58 | - Paper finding: `find papers`, `find articles`, `research papers on`, `published studies` |
| 59 | - Citations: `cite`, `citation`, `doi`, `pubmed`, `pmid` |
| 60 | - Academic sources: `peer-reviewed`, `journal article`, `scholarly`, `arxiv`, `preprint` |
| 61 | - Review types: `systematic review`, `meta-analysis`, `literature search` |
| 62 | - Paper quality: `foundational papers`, `seminal papers`, `landmark papers`, `highly cited` |
| 63 | |
| 64 | ### Everything Else (Routes to Parallel) |
| 65 | |
| 66 | All other queries go to the Parallel Chat API (core model), including: |
| 67 | |
| 68 | - General research questions |
| 69 | - Market and industry analysis |
| 70 | - Technical information and documentation |
| 71 | - Current events and recent developments |
| 72 | - Comparative analysis |
| 73 | - Statistical data retrieval |
| 74 | - Complex analytical queries |
| 75 | |
| 76 | ### Manual Override |
| 77 | |
| 78 | You can force a specific backend: |
| 79 | |
| 80 | ```bash |
| 81 | # Force Parallel Deep Research |
| 82 | python research_lookup.py "your query" --force-backend parallel |
| 83 | |
| 84 | # Force Perplexity academic search |
| 85 | python research_lookup.py "your query" --force-backend perplexity |
| 86 | ``` |
| 87 | |
| 88 | --- |
| 89 | |
| 90 | ## Core Capabilities |
| 91 | |
| 92 | ### 1. General Research Queries (Parallel Chat API) |
| 93 | |
| 94 | **Default backend.** Provides comprehensive, multi-source research with citations via the Chat API (`core` model). |
| 95 | |
| 96 | ``` |
| 97 | Query Examples: |
| 98 | - "Recent advances in CRISPR gene editing 2025" |
| 99 | - "Compare mRNA vaccines vs traditional vaccines for cancer treatment" |
| 100 | - "AI adoption in healthcare industry statistics" |
| 101 | - "Global renewable energy market trends and projections" |
| 102 | - "Explain the mechanism underlying gut microbiome and depression" |
| 103 | ``` |
| 104 | |
| 105 | **Response includes:** |
| 106 | - Comprehensive research report in markdown |
| 107 | - Inline citations from authoritative web sources |
| 108 | - Structured sections with key findings |
| 109 | - Multiple perspectives and data points |
| 110 | - Source URLs for verification |
| 111 | |
| 112 | ### 2. Academic Paper Search (Perplexity sonar-pro-search) |
| 113 | |
| 114 | **Used for academic-specific queries.** Prioritizes scholarly databases and peer-reviewed sources. |
| 115 | |
| 116 | ``` |
| 117 | Query Examples: |
| 118 | - "Find papers on transformer attention mechanisms in NeurIPS 2024" |
| 119 | - "Foundational papers on quantum error correction" |
| 120 | - "Systematic review of immunotherapy in non-small cell lung cancer" |
| 121 | - "Cite the original BERT paper and its most influential follow-ups" |
| 122 | - "Published studies on CRISPR off-t |