Stats
Actions
Tags
The 4-phase paper search workflow from parallel search to download. Use when coordinating the multi-agent paper search pipeline.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-teams-papersearch:search-workflowThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
| Phase | Name | Lead | Output |
| Phase | Name | Lead | Output |
|---|---|---|---|
| 1 | Parallel Search | Marshall (3 scouts) | Raw results from 14+ databases |
| 2 | Aggregation | Marshall + Archivist | Deduplicated, ranked paper list |
| 3 | Presentation | Marshall | Formatted tables for user |
| 4 | Download | Librarian | PDF files or manual links |
Phase 1: Scout-Core ──┐
Scout-Domain ─┤──→ Phase 2 ──→ Phase 3 ──→ Phase 4
Scout-Cloud ──┘ ▲ │
│ │
Archivist Librarian
(deduplicate) (download)
| Tier | Databases | Agent |
|---|---|---|
| 1 Core | Google Scholar, Semantic Scholar, OpenAlex, CrossRef | Scout-Core |
| 2 Domain | arXiv, PubMed, bioRxiv, medRxiv, DBLP, SSRN, IACR, OpenAIRE, BASE, CORE, DOAJ, Zenodo, Unpaywall, PMC, EuropePMC | Scout-Domain |
| 3 Cloud | Consensus, Scholar Gateway, ResearchGate (Tavily) | Scout-Cloud |
npx claudepluginhub xinjing-guo/agent-teams-papersearch --plugin agent-teams-papersearchGuides systematic scientific literature searches using PubMed, arXiv, Google Scholar, AI tools, PICO framework, MeSH terms, boolean queries, and three-tiered strategies. Use when planning searches or reviews.
Searches 10 academic paper databases (PubMed, arXiv, Semantic Scholar, etc.) via REST APIs for papers, citations, DOIs, abstracts, full text, and open access PDFs.
Dispatches parallel subagents to screen 50+ papers from PubMed, perform deep dives, extract data, and explore citations for large literature reviews.