research-lookup
Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations.
npx skills add majiayu000/claude-skill-registry --skill research-lookup-k-dense-ai-claude-scientific-wr --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Gathers real-time research information by querying Perplexity's Sonar models through OpenRouter. It automatically chooses between Sonar Pro Search for fast lookups and Sonar Reasoning Pro for deep analytical queries, based on query complexity. It provides access to academic papers, recent studies, technical documentation, and general research information with citations and source attribution.
How it works
- Uses OpenRouter API to access Perplexity models: Sonar Pro Search for straightforward lookups and Sonar Reasoning Pro for complex analyses.
- Automatically detects query complexity via indicators like analytical, comparative, synthesis, causal, and other keywords to trigger Reasoning Pro when needed.
- Returns results with citations, authors, titles, journals, years, DOIs or stable URLs, and source links from academic databases.
- For new documents, suggests adding scientific schematics generated by the scientific-schematics workflow and provides commands to create diagrams:
- Generate schematics command:
python scripts/generate_schematic.py "your diagram description" -o figures/output.png - Optional fallback should schematics be unavailable: it mentions use of the
scientific-schematicsskill.
- Generate schematics command:
- Supports various query types: academic literature searches, protocol/method lookups, statistical data, and citation assistance.
- Includes explicit model-selection configuration and optional manual overrides via
force_modelin code examples, and command-line usage examples for forcing models or saving JSON outputs.
When to use it
- When you need current research information: latest studies, papers, findings.
- For literature verification, background research, and citation sources.
- To locate technical documentation, protocols, and methodologies.
- To obtain recent statistics, survey results, and expert opinions.
- When high-quality citations and source attribution are required, prioritizing peer-reviewed sources and high-impact venues.
What it can touch
- OpenRouter API (via environment variable OPENROUTER_API_KEY) for model access.
- Models: perplexity/sonar-pro-search and perplexity/sonar-reasoning-pro-online.
- Output: JSON or textual results with citations and links.
- Command-line usage and Python examples for model forcing and output formats.
Caveats
- Requires an OpenRouter API key and a credits-enabled account.
- Output assumes access to academic databases and reliable citations; quality depends on source availability.
- OpenRouter configuration emphasizes scholarly sources and recent literature (2020-2024).
- The skill prioritizes high-quality, influential papers and Tier-1 venues; exact citation counts are provided when available and may be approximate.
# Research Information Lookup ## Overview This skill enables real-time research information lookup using Perplexity's Sonar models through OpenRouter. It intelligently selects between **Sonar Pro Search** (fast, efficient lookup) and **Sonar Reasoning Pro** (deep analytical reasoning) based on query complexity. The skill provides access to current academic literature, recent studies, technical documentation, and general research information with proper citations and source attribution. ## When to Use This Skill Use this skill when you need: - **Current Research Information**: Latest studies, papers, and findings in a specific field - **Literature Verification**: Check facts, statistics, or claims against current research - **Background Research**: Gather context and supporting evidence for scientific writing - **Citation Sources**: Find relevant papers and studies to cite in manuscripts - **Technical Documentation**: Look up specifications, protocols, or methodologies - **Recent Developments**: Stay current with emerging trends and breakthroughs - **Statistical Data**: Find recent statistics, survey results, or research findings - **Expert Opinions**: Access insights from recent in
- Overview
- When to Use This Skill
- Visual Enhancement with Scientific Schematics
- Core Capabilities
- 1. Academic Research Queries
- 2. Technical and Methodological Information
- 3. Statistical and Data Information
- 4. Citation and Reference Assistance
- Automatic Model Selection
- Model Types
- Complexity Assessment
- Manual Override
- Technical Integration
- OpenRouter API Configuration
python scripts/generate_schematic.py "your diagram description" -o figures/output.png Force Sonar Pro Search python research_lookup.py "your query" --force-model pro Force Sonar Reasoning Pro python research_lookup.py "your query" --force-model reasoning Automatic (no flag) python research_lookup.py "your query" Save output to a file python research_lookup.py "your query" -o results.txt Output as JSON (useful for programmatic access)
What does the research-lookup skill do?
Look up current research information using Perplexity's Sonar Pro Search or Sonar Reasoning Pro models through OpenRouter. Automatically selects the best model based on query complexity. Search academic papers, recent studies, technical documentation, and general research information with citations.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill research-lookup-k-dense-ai-claude-scientific-wr --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.