Deep Research

collaborative-deep-research/agent-papers-cli

This is a structured workflow for academic research that knows how to use paper search tools properly. It starts with broad Google and Semantic Scholar queries to map the landscape, then narrows down with filters for citations and recency, reads full papers from arXiv, and follows citation graphs both forward and backward to find related work. The workflow is opinionated about sequence: scan widely before reading deeply, always cross-reference web sources against papers, and synthesize findings with proper citations and BibTeX entries. It's designed for when you need more than a quick search, like literature reviews or understanding a research area from multiple angles.

skills.sh installs: 320
GitHub stars: 50
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add collaborative-deep-research/agent-papers-cli --skill deep-research --agent claude-code

Installs into .claude/skills of the current project.

Files

Research "$ARGUMENTS" in depth using the paper and paper-search CLI tools. Follow this workflow:

1. Broad Discovery

Start with broad searches to map the landscape:

paper-search google web "$ARGUMENTS"
paper-search semanticscholar papers "$ARGUMENTS" --limit 10

Scan titles, snippets, and citation counts. Identify the most relevant papers and key terms.

2. Narrow and Filter

Refine based on what you found:

paper-search semanticscholar papers "<refined query>" --year 2023-2025 --min-citations 10
paper-search semanticscholar snippets "<specific question>"
paper-search pubmed "<query>"   # if biomedical

3. Deep Read

For the most relevant papers (at least 3-5), read in depth:

paper outline <arxiv_id>           # understand structure first
paper skim <arxiv_id> --lines 3    # quick overview
paper read <arxiv_id> <section>    # read key sections

For web sources: