Agent skill · Data & Analytics

research-lookup

Look up current research information using parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), 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. Note: query text is transmitted to api.parallel.ai (PARALLEL_API_KEY) and, for academic searches, to openrouter.ai (OPENROUTER_API_KEY).

majiayu000github.com/majiayu000GitHub ↗
claude-codecan modify filesMIT
Install
npx skills add majiayu000/claude-skill-registry --skill research-lookup-k-dense-ai-scientific-agent-ski --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 23 KB
Bundled scripts: none
Allowed tools: ReadWriteEditBash
Requires: parallel-cli required (primary); PARALLEL_API_KEY and OPENROUTER_API_KEY optional for deep/academic backends
Path: skills/analysis/research-lookup-k-dense-ai-scientific-agent-ski/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

Review
written from the skill's own SKILL.md · Aug 5, 2026

What it does

This skill looks up current research information by routing queries to the best backend among parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), and Perplexity sonar-pro-search (academic papers). It automatically directs queries to the most appropriate backend and supports use for finding papers, gathering research data, and verifying scientific information. It notes that query text is transmitted to api.parallel.ai via PARALLEL_API_KEY and to openrouter.ai via OPENROUTER_API_KEY for academic searches.

How it works

  • Default backend: parallel-cli search for fast web search with academic source prioritization. Uses commands like parallel-cli search with --include-domains to target scholarly sources, and saves results to a file under sources/research_<topic>.json.
  • Academic searches: routed to Perplexity sonar-pro-search (via OpenRouter) when academic keywords are present (e.g., papers, doi, journal, peer-reviewed). Academic results are saved under sources/research_<topic>-academic.json or via Perplexity-specific paths as described.
  • Deep research: triggered when user explicitly asks for deep/synthetic analysis; uses Parallel Chat API (core model) for multi-source synthesis with Markdown output and inline citations.
  • Manual overrides: can force a specific backend using dedicated commands or Python script invocations (e.g., python research_lookup.py with --force-backend options).
  • Saving rule: All results must be saved to the sources/ folder using the appropriate -o filename pattern for the chosen backend.

When to use it

Use this skill when you need current research information, literature verification, background research, citation sources, technical documentation, or market/industry data related to scientific topics. It is intended for acquiring papers, data, and validated information from scholarly sources, with academic results prioritized where applicable.

What it can touch

  • Command-line tool: parallel-cli search (primary backend)
  • Optional backends: Parallel Chat API (via https://api.parallel.ai) and Perplexity sonar-pro-search (OpenRouter)
  • Scripting: python research_lookup.py for forced-backend or batch usage
  • Output destinations: files under the sources/ directory (e.g., sources/research_<topic>.json, sources/research_<topic>-academic.json, or sources/papers_<topic>.md)

Caveats

  • Backends require appropriate API keys (PARALLEL_API_KEY and OPENROUTER_API_KEY) for deep/academic searches. The skill notes the transmission of query text to these services.
  • The workflow emphasizes saving results to the sources/ folder for reproducibility and includes specific filename patterns depending on backend.
From the SKILL.md

# Research Information Lookup ## Overview This skill provides real-time research information lookup with **intelligent backend routing**: - **parallel-cli search** (parallel-web skill): **Primary and default backend** for all research queries. Fast, cost-effective web search with academic source prioritization. Uses `parallel-cli search` with `--include-domains` for scholarly sources. - **Parallel Chat API** (`core` model): Secondary backend for complex, multi-source deep research requiring extended synthesis (60s-5min latency). Use only when explicitly needed. - **Perplexity sonar-pro-search** (via OpenRouter): Used only for academic-specific paper searches where scholarly database access is critical. The skill automatically detects query type and routes to the optimal backend. ## When to Use This Skill Use this skill when you need: - **Current Research Information**: Latest studies, papers, and findings - **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 - **Technical Documentation**: Look

What's inside
Steps it walks through
  1. Overview
  2. When to Use This Skill
  3. Visual Enhancement with Scientific Schematics
  4. Automatic Backend Selection
  5. Routing Logic
  6. Default: parallel-cli search (parallel-web skill)
  7. Academic Keywords (Routes to Perplexity)
  8. Deep Research (Routes to Parallel Chat API)
  9. Manual Override
  10. Core Capabilities
  11. 1. General Research Queries (parallel-cli search — DEFAULT)
  12. 2. Academic Paper Search (Perplexity sonar-pro-search)
  13. 3. Deep Research (Parallel Chat API — on request only)
  14. 4. Technical and Methodological Information
Ships with 1 file
  • metadata.json
Commands it runs
python scripts/generate_schematic.py "your diagram description" -o figures/output.png
parallel-cli search "your research query" -q "keyword1" -q "keyword2" \
Force parallel-cli search (fast web search)
parallel-cli search "your query" -q "keyword" --json --max-results 10 -o sources/research_<topic>.json
Force Parallel Deep Research (slow, exhaustive)
python research_lookup.py "your query" --force-backend parallel
Force Perplexity academic search
python research_lookup.py "your query" --force-backend perplexity
parallel-cli search "Recent advances in CRISPR gene editing 2025" \
parallel-cli search "Western blot protocol for protein detection" \
More from claude-skill-registry
All skills →
descriptive-statisticsSummarizing and visualizing data through measures of center, spread, shape, and position. Covers…Data & Analyticsperplexity-researcher-reasoning-proHighest level of research and reasoning capabilities for complex decision-making with significant…OtherretroBrutally honest engineering retrospective. Analyzes git history for what actually happened — not…Data & AnalyticsanalyzeUniversal multi-perspective analyzer for any topic, file, idea, or decision. Extract key points…Otherarize-prompt-optimizationINVOKE THIS SKILL when optimizing, improving, or debugging LLM prompts using production trace data…Data & Analyticscellxgene-contextGuide for integrating CellxGene Census single-cell data with ENCODE bulk experiments. Use when…Data & Analytics
About this skill
What does the research-lookup skill do?

Look up current research information using parallel-cli search (primary, fast web search), the Parallel Chat API (deep research), 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. Note: query text is transmitted to api.parallel.ai (PARALLEL_API_KEY) and, for academic searches, to openrouter.ai (OPENROUTER_API_KEY).

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill research-lookup-k-dense-ai-scientific-agent-ski --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.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these skills come from, watched daily.
The people behind them →
Makers and builders across the ecosystem.